Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Applied Sciences applsci	2.7	4.5	2011	16.9 Days	CHF 2400
Machines machines	2.6	2.1	2013	15.6 Days	CHF 2400
Processes processes	3.5	4.7	2013	13.7 Days	CHF 2400
Sensors sensors	3.9	6.8	2001	17 Days	CHF 2600
Journal of Manufacturing and Materials Processing jmmp	3.2	5.5	2017	14.2 Days	CHF 1800
Chips chips	-	-	2022	15.0 days *	CHF 1000

16 pages, 4500 KiB

Open AccessArticle

A Methodology to Automatically Segment 3D Ultrasonic Data Using X-ray Computed Tomography and a Convolutional Neural Network

by Juan-Ignacio Caballero, Guillermo Cosarinsky, Jorge Camacho, Ernestina Menasalvas, Consuelo Gonzalo-Martin and Federico Sket

Appl. Sci. 2023, 13(10), 5933; https://doi.org/10.3390/app13105933 - 11 May 2023

Cited by 1 | Viewed by 1565

Abstract

Ultrasonic non-destructive testing (UT) is a proficient method for detecting damage in composite materials; however, conventional manual testing procedures are time-consuming and labor-intensive. We propose a semi-automated defect segmentation methodology employing a convolutional neural network (CNN) on 3D ultrasonic data, facilitated by the [...] Read more.

Ultrasonic non-destructive testing (UT) is a proficient method for detecting damage in composite materials; however, conventional manual testing procedures are time-consuming and labor-intensive. We propose a semi-automated defect segmentation methodology employing a convolutional neural network (CNN) on 3D ultrasonic data, facilitated by the fusion of X-ray computed tomography (XCT) and Phased-Array Ultrasonic Testing (PAUT) data. This approach offers the ability to develop supervised datasets for cases where UT techniques inadequately assess defects and enables the creation of models with genuine defects rather than artificially introduced ones. During the training process, we recommend processing the 3D volumes as a sequence of 2D slices derived from each technique. Our methodology was applied to segment porosity, a common defect in composite materials, for which characteristics such as void size and shape remain immeasurable via UT. Precision, recall, F1 score, and Intersection over Union (IoU) metrics were used in the evaluation. The results of the evaluation show that the following challenges have to be faced for improvement: (i) achieving accurate 3D registration, (ii) discovering suitable similar keypoints for XCT and UT data registration, (iii) differentiating ultrasonic echoes originating from porosity versus those related to noise or microstructural features (interfaces, resin pockets, fibers, etc.), and, (iv) single out defect echoes located near the edges of the component. In fact, an average F1 score of 0.66 and IoU of 0.5 were obtained. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

12 pages, 748 KiB

Open AccessArticle

A Quantitative Review of Automated Neural Search and On-Device Learning for Tiny Devices

by Danilo Pietro Pau, Prem Kumar Ambrose and Fabrizio Maria Aymone

Chips 2023, 2(2), 130-141; https://doi.org/10.3390/chips2020008 - 09 May 2023

Cited by 5 | Viewed by 1985

Abstract

This paper presents a state-of-the-art review of different approaches for Neural Architecture Search targeting resource-constrained devices such as microcontrollers, as well as the implementations of on-device learning techniques for them. Approaches such as MCUNet have been able to drive the design of tiny [...] Read more.

This paper presents a state-of-the-art review of different approaches for Neural Architecture Search targeting resource-constrained devices such as microcontrollers, as well as the implementations of on-device learning techniques for them. Approaches such as MCUNet have been able to drive the design of tiny neural architectures with low memory and computational requirements which can be deployed effectively on microcontrollers. Regarding on-device learning, there are various solutions that have addressed concept drift and have coped with the accuracy drop in real-time data depending on the task targeted, and these rely on a variety of learning methods. For computer vision, MCUNetV3 uses backpropagation and represents a state-of-the-art solution. The Restricted Coulomb Energy Neural Network is a promising method for learning with an extremely low memory footprint and computational complexity, which should be considered for future investigations. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

31 pages, 17076 KiB

Open AccessArticle

Enhancing Heart Disease Prediction Accuracy through Machine Learning Techniques and Optimization

by Nadikatla Chandrasekhar and Samineni Peddakrishna

Processes 2023, 11(4), 1210; https://doi.org/10.3390/pr11041210 - 14 Apr 2023

Cited by 26 | Viewed by 7825

Abstract

In the medical domain, early identification of cardiovascular issues poses a significant challenge. This study enhances heart disease prediction accuracy using machine learning techniques. Six algorithms (random forest, K-nearest neighbor, logistic regression, Naïve Bayes, gradient boosting, and AdaBoost classifier) are utilized, with datasets [...] Read more.

In the medical domain, early identification of cardiovascular issues poses a significant challenge. This study enhances heart disease prediction accuracy using machine learning techniques. Six algorithms (random forest, K-nearest neighbor, logistic regression, Naïve Bayes, gradient boosting, and AdaBoost classifier) are utilized, with datasets from the Cleveland and IEEE Dataport. Optimizing model accuracy, GridsearchCV, and five-fold cross-validation are employed. In the Cleveland dataset, logistic regression surpassed others with 90.16% accuracy, while AdaBoost excelled in the IEEE Dataport dataset, achieving 90% accuracy. A soft voting ensemble classifier combining all six algorithms further enhanced accuracy, resulting in a 93.44% accuracy for the Cleveland dataset and 95% for the IEEE Dataport dataset. This surpassed the performance of the logistic regression and AdaBoost classifiers on both datasets. This study’s novelty lies in the use of GridSearchCV with five-fold cross-validation for hyperparameter optimization, determining the best parameters for the model, and assessing performance using accuracy and negative log loss metrics. This study also examined accuracy loss for each fold to evaluate the model’s performance on both benchmark datasets. The soft voting ensemble classifier approach improved accuracies on both datasets and, when compared to existing heart disease prediction studies, this method notably exceeded their results. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

18 pages, 4048 KiB

Open AccessArticle

Applying Industrial Internet of Things Analytics to Manufacturing

by Chun-Ho Wu, Stephen Chi-Hung Ng, Keith Chun-Man Kwok and Kai-Leung Yung

Machines 2023, 11(4), 448; https://doi.org/10.3390/machines11040448 - 02 Apr 2023

Viewed by 1570

Abstract

The proliferation of Industry 4.0 (I4.0) technologies has created a new manufacturing landscape for manufacturing, requiring that companies follow I4.0 trends to stay competitive. However, in this novel digital automated environment, these companies must also ensure that lean manufacturing principles are upheld. This [...] Read more.

The proliferation of Industry 4.0 (I4.0) technologies has created a new manufacturing landscape for manufacturing, requiring that companies follow I4.0 trends to stay competitive. However, in this novel digital automated environment, these companies must also ensure that lean manufacturing principles are upheld. This study proposes a data-driven framework for analysing raw data across machines in manufacturing systems that can provide a comprehensive understanding of idle time and facilitate adjustments to reduce defect rates. This framework offers an alternative approach to improving manufacturing processes that involves utilising the power of I4.0 technologies in conjunction with lean manufacturing principles. This study’s examination of unprocessed data also provides guidance on improving legislation. The findings of this study provide direction for future research in the field of manufacturing and offer useful advice to businesses wishing to integrate I4.0 technologies into their operations. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

15 pages, 4551 KiB

Open AccessArticle

Buckle Pose Estimation Using a Generative Adversarial Network

by Hanfeng Feng, Xiyu Chen, Jiayan Zhuang, Kangkang Song, Jiangjian Xiao and Sichao Ye

Appl. Sci. 2023, 13(7), 4220; https://doi.org/10.3390/app13074220 - 27 Mar 2023

Viewed by 888

Abstract

The buckle before the lens coating is still typically disassembled manually. The difference between the buckle and the background is small, while that between the buckles is large. This mechanical disassembly can also damage the lens. Therefore, it is important to estimate pose [...] Read more.

The buckle before the lens coating is still typically disassembled manually. The difference between the buckle and the background is small, while that between the buckles is large. This mechanical disassembly can also damage the lens. Therefore, it is important to estimate pose with high accuracy. This paper proposes a buckle pose estimation method based on a generative adversarial network. An edge extraction model is designed based on a segmentation network as the generator. Spatial attention is added to the discriminator to help it better distinguish between generated and real graphs. The generator thus generates delicate external contours and center edge lines with help from the discriminator. The external rectangle and the least square methods are used to determine the center position and deflection angle of the buckle, respectively. The center point and angle accuracies of the test datasets are 99.5% and 99.3%, respectively. The pixel error of the center point distance and the absolute error of the angle to the horizontal line are within 7.36 pixels and 1.98°, respectively. This method achieves the highest center point and angle accuracies compared to Hed, RCF, DexiNed, and PidiNet. It can meet practical requirements and boost the production efficiency of lens coatings. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

17 pages, 449 KiB

Open AccessArticle

Cluster-Based Regression Transfer Learning for Dynamic Multi-Objective Optimization

by Xi Zhang, Feng Qian and Liping Zhang

Processes 2023, 11(2), 613; https://doi.org/10.3390/pr11020613 - 17 Feb 2023

Cited by 2 | Viewed by 1234

Abstract

Many multi-objective optimization problems in the real world have conflicting objectives, and these objectives change over time, known as dynamic multi-objective optimization problems (DMOPs). In recent years, transfer learning has attracted growing attention to solve DMOPs, since it is capable of leveraging historical [...] Read more.

Many multi-objective optimization problems in the real world have conflicting objectives, and these objectives change over time, known as dynamic multi-objective optimization problems (DMOPs). In recent years, transfer learning has attracted growing attention to solve DMOPs, since it is capable of leveraging historical information to guide the evolutionary search. However, there is still much room for improvement in the transfer effect and the computational efficiency. In this paper, we propose a cluster-based regression transfer learning-based dynamic multi-objective evolutionary algorithm named CRTL-DMOEA. It consists of two components, which are the cluster-based selection and cluster-based regression transfer. In particular, once a change occurs, we employ a cluster-based selection mechanism to partition the previous Pareto optimal solutions and find the clustering centroids, which are then fed into autoregression prediction model. Afterwards, to improve the prediction accuracy, we build a strong regression transfer model based on TrAdaboost.R2 by taking advantage of the clustering centroids. Finally, a high-quality initial population for the new environment is predicted with the regression transfer model. Through a comparison with some chosen state-of-the-art algorithms, the experimental results demonstrate that the proposed CRTL-DMOEA is capable of improving the performance of dynamic optimization on different test problems. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

13 pages, 4490 KiB

Open AccessArticle

ConvLSTM-Att: An Attention-Based Composite Deep Neural Network for Tool Wear Prediction

by Renwang Li, Xiaolei Ye, Fangqing Yang and Ke-Lin Du

Machines 2023, 11(2), 297; https://doi.org/10.3390/machines11020297 - 16 Feb 2023

Cited by 3 | Viewed by 1829

Abstract

In order to improve the accuracy of tool wear prediction, an attention-based composite neural network, referred to as the ConvLSTM-Att model (1DCNN-LSTM-Attention), is proposed. Firstly, local multidimensional feature vectors are extracted with the help of a one-dimensional convolutional neural network (1D-CNN), which avoids [...] Read more.

In order to improve the accuracy of tool wear prediction, an attention-based composite neural network, referred to as the ConvLSTM-Att model (1DCNN-LSTM-Attention), is proposed. Firstly, local multidimensional feature vectors are extracted with the help of a one-dimensional convolutional neural network (1D-CNN), which avoids the loss of wear features caused by manual feature extraction. Then the temporal relationship learning between multidimensional feature vectors is performed by introducing a long short-term memory (LSTM) network to make up for the lack of long-short distance dependence of the captured sequence of the CNN network. Finally, an attention mechanism is applied to strengthen the ability to extract key information from tool-wearing temporal features. The proposed ConvLSTM-Att model is trained with the measured tool wear data and then performs as a tool wear predictor. The model is compared with several state-of-the-art models on the PHM tool wear data sets. It significantly outperforms the other models in terms of prediction accuracy, but with similar computational complexity. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

17 pages, 2951 KiB

Open AccessArticle

Pixel-Level Concrete Crack Segmentation Using Pyramidal Residual Network with Omni-Dimensional Dynamic Convolution

by Hao Tan and Shaojiang Dong

Processes 2023, 11(2), 546; https://doi.org/10.3390/pr11020546 - 10 Feb 2023

Cited by 5 | Viewed by 1741

Abstract

Automated crack detection technologies based on deep learning have been extensively used as one of the indicators of performance degradation of concrete structures. However, there are numerous drawbacks of existing methods in crack segmentation due to the fine and microscopic properties of cracks. [...] Read more.

Automated crack detection technologies based on deep learning have been extensively used as one of the indicators of performance degradation of concrete structures. However, there are numerous drawbacks of existing methods in crack segmentation due to the fine and microscopic properties of cracks. Aiming to address this issue, a crack segmentation method is proposed. First, a pyramidal residual network based on encoder–decoder using Omni-Dimensional Dynamic Convolution is suggested to explore the network suitable for the task of crack segmentation. Additionally, the proposed method uses the mean intersection over union as the network evaluation index to lessen the impact of background features on the network performance in the evaluation and adopts a multi-loss calculation of positive and negative sample imbalance to weigh the negative impact of sample imbalance. As a final step in performance evaluation, a dataset for concrete cracks is developed. By using our dataset, the proposed method is validated to have an accuracy of 99.05% and an mIoU of 87.00%. The experimental results demonstrate that the concrete crack segmentation method is superior to the well-known networks, such as SegNet, DeeplabV3+, and Swin-unet. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

17 pages, 854 KiB

Open AccessArticle

Efficient Convolutional Neural Networks for Semiconductor Wafer Bin Map Classification

by Eunmi Shin and Chang D. Yoo

Sensors 2023, 23(4), 1926; https://doi.org/10.3390/s23041926 - 08 Feb 2023

Cited by 4 | Viewed by 2296

Abstract

The results obtained in the wafer test process are expressed as a wafer map and contain important information indicating whether each chip on the wafer is functioning normally. The defect patterns shown on the wafer map provide information about the process and equipment [...] Read more.

The results obtained in the wafer test process are expressed as a wafer map and contain important information indicating whether each chip on the wafer is functioning normally. The defect patterns shown on the wafer map provide information about the process and equipment in which the defect occurred, but automating pattern classification is difficult to apply to actual manufacturing sites unless processing speed and resource efficiency are supported. The purpose of this study was to classify these defect patterns with a small amount of resources and time. To this end, we explored an efficient convolutional neural network model that can incorporate three properties: (1) state-of-the-art performances, (2) less resource usage, and (3) faster processing time. In this study, we dealt with classifying nine types of frequently found defect patterns: center, donut, edge-location, edge-ring, location, random, scratch, near-full type, and None type using open dataset WM-811K. We compared classification performance, resource usage, and processing time using EfficientNetV2, ShuffleNetV2, MobileNetV2 and MobileNetV3, which are the smallest and latest light-weight convolutional neural network models. As a result, the MobileNetV3-based wafer map pattern classifier uses 7.5 times fewer parameters than ResNet, and the training speed is 7.2 times and the inference speed is 4.9 times faster, while the accuracy is 98% and the F1 score is 89.5%, achieving the same level. Therefore, it can be proved that it can be used as a wafer map classification model without high-performance hardware in an actual manufacturing system. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

21 pages, 6104 KiB

Open AccessArticle

Detection of Missing Insulator Caps Based on Machine Learning and Morphological Detection

by Zhaoyun Zhang, Hefan Chen and Shihong Huang

Sensors 2023, 23(3), 1557; https://doi.org/10.3390/s23031557 - 31 Jan 2023

Cited by 2 | Viewed by 1429

Abstract

Missing insulator caps are the key focus of transmission line inspection work. Insulators with a missing cap will experience decreased insulation and mechanical strength and cause transmission line safety accidents. As missing insulator caps often occur in glass and porcelain insulators, this paper [...] Read more.

Missing insulator caps are the key focus of transmission line inspection work. Insulators with a missing cap will experience decreased insulation and mechanical strength and cause transmission line safety accidents. As missing insulator caps often occur in glass and porcelain insulators, this paper proposes a detection method for missing insulator caps in these materials. First, according to the grayscale and color characteristics of these insulators, similar characteristic regions of the insulators are extracted from inspection images, and candidate boxes are generated based on these characteristic regions. Second, the images captured by these boxes are input into the classifier composed of SVM (Support Vector Machine) to identify and locate the insulators. The accuracy, recall and average accuracy of the classifier are all higher than 90%. Finally, this paper proposes a processing method based on the insulator morphology to determine whether an insulator cap is missing. The proposed method can also detect the number of remaining insulators, which can help power supply enterprises to evaluate the degree of insulator damage. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

27 pages, 5047 KiB

Open AccessReview

Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review

by Shaohua Qiu, Xiaopeng Cui, Zuowei Ping, Nanliang Shan, Zhong Li, Xianqiang Bao and Xinghua Xu

Sensors 2023, 23(3), 1305; https://doi.org/10.3390/s23031305 - 23 Jan 2023

Cited by 26 | Viewed by 8931

Abstract

Fault diagnosis and prognosis (FDP) tries to recognize and locate the faults from the captured sensory data, and also predict their failures in advance, which can greatly help to take appropriate actions for maintenance and avoid serious consequences in industrial systems. In recent [...] Read more.

Fault diagnosis and prognosis (FDP) tries to recognize and locate the faults from the captured sensory data, and also predict their failures in advance, which can greatly help to take appropriate actions for maintenance and avoid serious consequences in industrial systems. In recent years, deep learning methods are being widely introduced into FDP due to the powerful feature representation ability, and its rapid development is bringing new opportunities to the promotion of FDP. In order to facilitate the related research, we give a summary of recent advances in deep learning techniques for industrial FDP in this paper. Related concepts and formulations of FDP are firstly given. Seven commonly used deep learning architectures, especially the emerging generative adversarial network, transformer, and graph neural network, are reviewed. Finally, we give insights into the challenges in current applications of deep learning-based methods from four different aspects of imbalanced data, compound fault types, multimodal data fusion, and edge device implementation, and provide possible solutions, respectively. This paper tries to give a comprehensive guideline for further research into the problem of intelligent industrial FDP for the community. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

20 pages, 6770 KiB

Open AccessArticle

Early Fault Diagnosis of Rolling Bearing Based on Threshold Acquisition U-Net

by Dongsheng Zhang, Laiquan Zhang, Naikang Zhang, Shuo Yang and Yuhao Zhang

Machines 2023, 11(1), 119; https://doi.org/10.3390/machines11010119 - 15 Jan 2023

Cited by 2 | Viewed by 1642

Abstract

Considering the problem that the early fault signal of rolling bearing is easily interfered with by background information, such as noise, and it is difficult to extract fault features, a method of rolling bearing early fault diagnosis based on the threshold acquisition U-Net [...] Read more.

Considering the problem that the early fault signal of rolling bearing is easily interfered with by background information, such as noise, and it is difficult to extract fault features, a method of rolling bearing early fault diagnosis based on the threshold acquisition U-Net (TA-UNet) is proposed. First, to improve the feature extraction ability of U-Net, the channel spatial threshold acquisition network (CS-TAN) and the dilated convolution module (DCM) based on different dilated rate combinations are introduced into the U-Net to construct the TA-UNet. Among them, the CS-TAN can adaptively learn the threshold, reduce the interference of noise in the signal, and the DCM can improve the multi-scale feature extraction ability of the network. Then, the TA-UNet is used for early fault diagnosis, and the method is divided into two steps: The model training phase and the vibration signal fault feature extraction phase. In the first step, additive gaussian white noise is added to the vibration signal to obtain the noise-added vibration signal, and the TA-UNet is trained to learn how to denoise the noise-added vibration signal. In the second step, the trained TA-UNet is used to extract the fault features of vibration signals and diagnose the early fault types of rolling bearing. The two-step method solves the problem that U-Net, as a supervised neural network, needs corresponding labeled data to be trained, as it realizes the fault diagnosis of unlabeled data. The feature extraction capability of the TA-UNet is evaluated by denoising the simulated signal of rolling bearing. The effectiveness of the proposed diagnostic method is demonstrated by the early fault diagnosis of open-source datasets. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

32 pages, 2644 KiB

Open AccessArticle

Ensemble Classifier for Recognition of Small Variation in X-Bar Control Chart Patterns

by Waseem Alwan, Nor Hasrul Akhmal Ngadiman, Adnan Hassan, Syahril Ramadhan Saufi and Salwa Mahmood

Machines 2023, 11(1), 115; https://doi.org/10.3390/machines11010115 - 14 Jan 2023

Cited by 5 | Viewed by 1338

Abstract

Manufacturing processes have become highly accurate and precise in recent years, particularly in the chemical, aerospace, and electronics industries. This has attracted researchers to investigate improved procedures for monitoring and detection of small process variations to remain in line with such advances. Among [...] Read more.

Manufacturing processes have become highly accurate and precise in recent years, particularly in the chemical, aerospace, and electronics industries. This has attracted researchers to investigate improved procedures for monitoring and detection of small process variations to remain in line with such advances. Among these techniques, statistical process controls (SPC), in particular the control chart pattern (CCP), have become a popular choice for monitoring process variance, being utilized in numerous industrial and manufacturing applications. This study provides an improved control chart pattern recognition (CCPR) method focusing on X-bar chart patterns of small process variations using an ensemble classifier comprised of five complementing algorithms: decision tree, artificial neural network, linear support vector machine, Gaussian support vector machine, and k-nearest neighbours. Before advancing to the classification step, Nelson’s Rus Rules were utilized as a monitoring rule to distinguish between stable and unstable processes. The study’s findings indicate that the proposed method improves classification performance for patterns with mean changes of less than 1.5 sigma, and confirm that the performance of the ensemble classifier is superior to that of the individual classifier. The ensemble classifier can distinguish unstable pattern types with a classification accuracy of 99.55% and an ARL1 of 11.94. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

18 pages, 432 KiB

Open AccessArticle

An Objective Metallographic Analysis Approach Based on Advanced Image Processing Techniques

by Xabier Sarrionandia, Javier Nieves, Beñat Bravo, Iker Pastor-López and Pablo G. Bringas

J. Manuf. Mater. Process. 2023, 7(1), 17; https://doi.org/10.3390/jmmp7010017 - 04 Jan 2023

Cited by 3 | Viewed by 3449

Abstract

Metallographic analyses of nodular iron casting methods are based on visual comparisons according to measuring standards. Specifically, the microstructure is analyzed in a subjective manner by comparing the extracted image from the microscope to pre-defined image templates. The achieved classifications can be confused, [...] Read more.

Metallographic analyses of nodular iron casting methods are based on visual comparisons according to measuring standards. Specifically, the microstructure is analyzed in a subjective manner by comparing the extracted image from the microscope to pre-defined image templates. The achieved classifications can be confused, due to the fact that the features extracted by a human being could be interpreted differently depending on many variables, such as the conditions of the observer. In particular, this kind of problem represents an uncertainty when classifying metallic properties, which can influence the integrity of castings that play critical roles in safety devices or structures. Although there are existing solutions working with extracted images and applying some computer vision techniques to manage the measurements of the microstructure, those results are not too accurate. In fact, they are not able to characterize all specific features of the image and, they cannot be adapted to several characterization methods depending on the specific regulation or customer. Hence, in order to solve this problem, we propose a framework to improve and automatize the evaluations by combining classical machine vision techniques for feature extraction and deep learning technologies, to objectively make classifications. To adapt to the real analysis environments, all included inputs in our models were gathered directly from the historical repository of metallurgy from the Azterlan Research Centre (labeled using expert knowledge from engineers). The proposed approach concludes that these techniques (a classification under a pipeline of deep neural networks and the quality classification using an ANN classifier) are viable to carry out the extraction and classification of metallographic features with great accuracy and time, and it is possible to deploy software with the models to work on real-time situations. Moreover, this method provides a direct way to classify the metallurgical quality of the molten metal, allowing us to determine the possible behaviors of the final produced parts. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

12 pages, 3179 KiB

Open AccessArticle

Convolution Neural Network with Laser-Induced Breakdown Spectroscopy as a Monitoring Tool for Laser Cleaning Process

by Soojin Choi and Changkyoo Park

Sensors 2023, 23(1), 83; https://doi.org/10.3390/s23010083 - 22 Dec 2022

Viewed by 1515

Abstract

In this study, eight different painted stainless steel 304L specimens were laser-cleaned using different process parameters, such as laser power, scan speed, and the number of repetitions. Laser-induced breakdown spectroscopy (LIBS) was adopted as the monitoring tool for laser cleaning. Identification of LIBS [...] Read more.

In this study, eight different painted stainless steel 304L specimens were laser-cleaned using different process parameters, such as laser power, scan speed, and the number of repetitions. Laser-induced breakdown spectroscopy (LIBS) was adopted as the monitoring tool for laser cleaning. Identification of LIBS spectra with similar chemical compositions is challenging. A convolutional neural network (CNN)-based deep learning method was developed for accurate and rapid analysis of LIBS spectra. By applying the LIBS-coupled CNN method, the classification CNN model accuracy of laser-cleaned specimens was 94.55%. Moreover, the LIBS spectrum analysis time was 0.09 s. The results verified the possibility of using the LIBS-coupled CNN method as an in-line tool for the laser cleaning process. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

13 pages, 3492 KiB

Open AccessArticle

Bearing Fault Diagnosis of Split Attention Network Based on Deep Subdomain Adaptation

by Haitao Wang and Lindong Pu

Appl. Sci. 2022, 12(24), 12762; https://doi.org/10.3390/app122412762 - 12 Dec 2022

Cited by 3 | Viewed by 1364

Abstract

The insufficient learning ability of traditional convolutional neural network for key fault features, as well as the characteristic distribution of vibration data of rolling bearing collected under variable working conditions is inconsistent, and decreases the bearing fault diagnosis accuracy. To address the problem, [...] Read more.

The insufficient learning ability of traditional convolutional neural network for key fault features, as well as the characteristic distribution of vibration data of rolling bearing collected under variable working conditions is inconsistent, and decreases the bearing fault diagnosis accuracy. To address the problem, a deep subdomain adaptation split attention network (SPDSAN) is proposed for intelligent fault diagnosis of bearings. Firstly, the time-frequency diagram of a vibration signal is obtained by the continuous wavelet transform to show the time-frequency characteristics. Secondly, a residual split-attention network (ResNeSt) that integrates multi-path and channel attention mechanisms is constructed to extract the key features of rolling bearings to prevent feature loss. Then, a subdomain adaptation layer is added to ResNeSt to align the distribution of related subdomain data by minimizing the local maximum mean difference. Finally, the SPDSAN model is validated using the Case Western Reserve University datasets. The results show that the average diagnostic accuracy of the proposed method is 99.9% when the test set samples are not labeled, which is higher compared to the accuracy of other mainstream intelligent fault diagnosis models. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

17 pages, 2342 KiB

Open AccessArticle

Transfer-Learning-Based Opinion Mining for New-Product Portfolio Configuration over the Case-Based Reasoning Cycle

by Shui Ming Li and Carman Ka Man Lee

Appl. Sci. 2022, 12(23), 12477; https://doi.org/10.3390/app122312477 - 06 Dec 2022

Viewed by 1136

Abstract

Due to the ever-changing business environment, enterprises are facing unprecedented challenges in their new-product development (NPD) processes, while the success and survival of NPD projects have become increasingly challenging in recent years. Thus, most enterprises are eager to revamp existing NPD processes so [...] Read more.

Due to the ever-changing business environment, enterprises are facing unprecedented challenges in their new-product development (NPD) processes, while the success and survival of NPD projects have become increasingly challenging in recent years. Thus, most enterprises are eager to revamp existing NPD processes so as to enhance the likelihood of new products succeeding in the market. In addition to the determination of sustainable new-product ideas and designs, new-product portfolio management (NPPM) is an active research area for allocating adequate resources to boost project development, while projects that perform poorly can be terminated. Since the existing new-product portfolio configuration is manually decided, this study explores the possibility of standardising NPPM, particularly the configuration mechanism, in a systematic manner. Subsequently, case-based reasoning can be applied to structure the entire NPPM process, in which past knowledge and successful cases can be used to configure new projects. Furthermore, customer feedback was analyzed using the transfer-learning-based text classification model in the case-retrieval process to balance the values of enterprises and customers. A new-product portfolio was therefore configured to facilitate NPPM under an agile–stage-gate model. To verify the effectiveness of the proposed system, a case study in a printer manufacturing company was conducted, where positive feedback and performances were found. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

20 pages, 4355 KiB

Open AccessArticle

Working Condition Recognition of a Mineral Flotation Process Using the DSFF-DenseNet-DT

by Hongchang Liu, Mingfang He, Weiwei Cai, Guoxiong Zhou, Yanfeng Wang and Liujun Li

Appl. Sci. 2022, 12(23), 12223; https://doi.org/10.3390/app122312223 - 29 Nov 2022

Cited by 1 | Viewed by 1078

Abstract

The commonly used working condition recognition method in the mineral flotation process is based on shallow features of flotation froth images. However, the shallow features of flotation froth images frequently have an excessive amount of redundant and noisy information, which has an impact [...] Read more.

The commonly used working condition recognition method in the mineral flotation process is based on shallow features of flotation froth images. However, the shallow features of flotation froth images frequently have an excessive amount of redundant and noisy information, which has an impact on the recognition effect and prevents the flotation process from being effectively optimized. Therefore, a working condition recognition method for the mineral flotation process based on a deep and shallow feature fusion densely connected network decision tree (DSFF-DenseNet-DT) is proposed in this paper. Firstly, the color texture distribution (CTD) and size distribution (SD) of a flotation froth image obtained in advance are approximated by the nonparametric kernel density estimation method, and a set of kernel function weights is obtained to represent the color texture and size features, while the deep features of the flotation froth image are extracted through the densely connected network (DenseNet). Secondly, a two-stage feature fusion method based on a stacked autoencoder after Concat (Cat-SAE) is proposed to fuse and reduce the dimensionality of the extracted shallow features and deep features so as to maximize the comprehensive description of the features and eliminate redundant and noisy information. Finally, the feature vectors after fusion dimensionality reduction are fed into the densely connected network decision tree (DenseNet-DT) for working condition recognition. Multiple experiments employing self-built industrial datasets reveal that the suggested method’s average recognition accuracy, precision, recall and F1 score reach 92.67%, 93.9%, 94.2% and 0.94, respectively. These results demonstrate the proposed method’s usefulness. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

26 pages, 13275 KiB

Open AccessEditor’s ChoiceArticle

Fault Detection for CNC Machine Tools Using Auto-Associative Kernel Regression Based on Empirical Mode Decomposition

by Seunghwan Jung, Minseok Kim, Baekcheon Kim, Jinyong Kim, Eunkyeong Kim, Jonggeun Kim, Hyeonuk Lee and Sungshin Kim

Processes 2022, 10(12), 2529; https://doi.org/10.3390/pr10122529 - 28 Nov 2022

Cited by 4 | Viewed by 1876

Abstract

In manufacturing processes using computerized numerical control (CNC) machines, machine tools are operated repeatedly for a long period for machining hard and difficult-to-machine materials, such as stainless steel. These operating conditions frequently result in tool breakage. The failure of machine tools significantly degrades [...] Read more.

In manufacturing processes using computerized numerical control (CNC) machines, machine tools are operated repeatedly for a long period for machining hard and difficult-to-machine materials, such as stainless steel. These operating conditions frequently result in tool breakage. The failure of machine tools significantly degrades the product quality and efficiency of the target process. To solve these problems, various studies have been conducted for detecting faults in machine tools. However, the most related studies used only the univariate signal obtained from CNC machines. The fault-detection methods using univariate signals have a limitation in that multivariate models cannot be applied. This can restrict in performance improvement of the fault detection. To address this problem, we employed empirical mode decomposition to construct a multivariate dataset from the univariate signal. Subsequently, auto-associative kernel regression was used to detect faults in the machine tool. To verify the proposed method, we obtained a univariate current signal measured from the machining center in an actual industrial plant. The experimental results demonstrate that the proposed method successfully detects faults in the actual machine tools. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

16 pages, 4189 KiB

Open AccessArticle

Two-Stage Ultrasound Signal Recognition Method Based on Envelope and Local Similarity Features

by Liwei Wang, Senxiang Lu, Xiaoyuan Liu and Jinhai Liu

Machines 2022, 10(12), 1111; https://doi.org/10.3390/machines10121111 - 23 Nov 2022

Viewed by 1347

Abstract

Accurate identification of ultrasonic signals can effectively improve the accuracy of a defect detection and inversion. Current methods, based on machine learning and deep learning have been able to classify signals with significant differences. However, the ultrasonic internal detection signal is interspersed with [...] Read more.

Accurate identification of ultrasonic signals can effectively improve the accuracy of a defect detection and inversion. Current methods, based on machine learning and deep learning have been able to classify signals with significant differences. However, the ultrasonic internal detection signal is interspersed with a large number of anomalous signals of an unknown origin and is affected by the time shift of echo features and noise interference, which leads to the low recognition accuracy of the ultrasonic internal detection signal, at this stage. To address the above problems, this paper proposes a two-stage ultrasonic signal recognition method, based on the envelope and local similarity features (TS-ES). In the first stage, a normal signal classification method, based on the envelope feature extraction and fusion is proposed to solve the problem of the low ultrasonic signal classification accuracy under the conditions of the echo feature time shift and noise interference. In the second stage, an abnormal signal detection method, based on the local similarity feature extraction and enhancement is proposed to solve the problem of detecting abnormal signals in ultrasound internal detection data. The experimental results show that the accuracy of the two-stage ultrasonic signal recognition method, based on the envelope and local similarity features (TS-ES) in this paper is 97.43%, and the abnormal signal detection accuracy and recall rate are as high as 99.7% and 97.81%. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

13 pages, 1950 KiB

Open AccessArticle

AIE-YOLO: Auxiliary Information Enhanced YOLO for Small Object Detection

by Bingnan Yan, Jiaxin Li, Zhaozhao Yang, Xinpeng Zhang and Xiaolong Hao

Sensors 2022, 22(21), 8221; https://doi.org/10.3390/s22218221 - 27 Oct 2022

Cited by 15 | Viewed by 3847

Abstract

Small object detection is one of the key challenges in the current computer vision field due to the low amount of information carried and the information loss caused by feature extraction. You Only Look Once v5 (YOLOv5) adopts the Path Aggregation Network to [...] Read more.

Small object detection is one of the key challenges in the current computer vision field due to the low amount of information carried and the information loss caused by feature extraction. You Only Look Once v5 (YOLOv5) adopts the Path Aggregation Network to alleviate the problem of information loss, but it cannot restore the information that has been lost. To this end, an auxiliary information-enhanced YOLO is proposed to improve the sensitivity and detection performance of YOLOv5 to small objects. Firstly, a context enhancement module containing a receptive field size of 21×21 is proposed, which captures the global and local information of the image by fusing multi-scale receptive fields, and introduces an attention branch to enhance the expressive ability of key features and suppress background noise. To further enhance the feature expression ability of small objects, we introduce the high- and low-frequency information decomposed by wavelet transform into PANet to participate in multi-scale feature fusion, so as to solve the problem that the features of small objects gradually disappear after multiple downsampling and pooling operations. Experiments on the challenging dataset Tsinghua–Tencent 100 K show that the mean average precision of the proposed model is 9.5% higher than that of the original YOLOv5 while maintaining the real-time speed, which is better than the mainstream object detection models. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

20 pages, 14392 KiB

Open AccessArticle

Super-Resolving Methodology for Noisy Unpaired Datasets

by Sung-Jun Min, Young-Su Jo and Suk-Ju Kang

Sensors 2022, 22(20), 8003; https://doi.org/10.3390/s22208003 - 20 Oct 2022

Viewed by 1753

Abstract

Although it is possible to acquire high-resolution and low-resolution paired datasets, their use in directly supervised learning is impractical in real-world applications. In the present work, we focus on a practical methodology for image acquisition in real-world conditions. The main method of noise [...] Read more.

Although it is possible to acquire high-resolution and low-resolution paired datasets, their use in directly supervised learning is impractical in real-world applications. In the present work, we focus on a practical methodology for image acquisition in real-world conditions. The main method of noise reduction involves averaging multiple noisy input images into a single image with reduced noise; we also consider unpaired datasets that contain misalignments between the high-resolution and low-resolution images. The results show that when more images are used for average denoising, better performance is achieved in the super-resolution task. Quantitatively, for a fixed noise level with a variance of 60, the proposed method of using 16 images for average denoising shows better performance than using 4 images for average denoising; it shows 0.68 and 0.0279 higher performance for the peak signal-to-noise ratio and structural similarity index map metrics, as well as 0.0071 and 1.5553 better performance for the learned perceptual image patch similarity and natural image quality evaluator metrics, respectively. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

25 pages, 12129 KiB

Open AccessArticle

Distribution Network Fault-Line Selection Method Based on MICEEMDAN–Recurrence Plot–Yolov5

by Sizu Hou, Yan Xu and Wei Guo

Processes 2022, 10(10), 2127; https://doi.org/10.3390/pr10102127 - 19 Oct 2022

Cited by 2 | Viewed by 1270

Abstract

Distribution system fault signals contain severe noise components. In order to solve the problem of distribution network fault-line selection, a fault-line selection method based on modifying the Improved Complete Ensemble Empirical Mode Decomposition Adaptive Noise (MICEEMDAN) algorithm, Recurrence Plot, and Yolov5 network is [...] Read more.

Distribution system fault signals contain severe noise components. In order to solve the problem of distribution network fault-line selection, a fault-line selection method based on modifying the Improved Complete Ensemble Empirical Mode Decomposition Adaptive Noise (MICEEMDAN) algorithm, Recurrence Plot, and Yolov5 network is proposed. First, ICEEMDAN is optimized using multi-scale weighted permutation entropy (MWPE). MICEEMDAN can decompose an electrical signal into a series of intrinsic mode functions (IMFs). Recurrence Plot transformation of all IMFs, obtained from decomposition and stitching from top to bottom, realizes the conversion of 1D time series to 2D images. Then, the recurrence maps obtained from all lines in the distribution network are stitched to obtain the distribution network recurrence map, realizing the mining of the fault-signal features of the whole distribution network. Finally, the Yolov5 network is used to mine the fault features of the recurrence map of the distribution network autonomously to realize the fault-line selection. The experiments show that the method has a good noise immunity and 99.98% fault-selection accuracy, which can effectively complete the distribution network fault selection. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

14 pages, 2654 KiB

Open AccessArticle

Single-Stage Underwater Target Detection Based on Feature Anchor Frame Double Optimization Network

by Huilin Ge, Yuewei Dai, Zhiyu Zhu and Xu Zang

Sensors 2022, 22(20), 7875; https://doi.org/10.3390/s22207875 - 17 Oct 2022

Cited by 5 | Viewed by 1532

Abstract

Objective: The shallow underwater environment is complex, with problems of color shift, uneven illumination, blurring, and distortion in the imaging process. These scenes are very unfavorable for the reasoning of the detection network. Additionally, typical object identification algorithms struggle to maintain high resilience [...] Read more.

Objective: The shallow underwater environment is complex, with problems of color shift, uneven illumination, blurring, and distortion in the imaging process. These scenes are very unfavorable for the reasoning of the detection network. Additionally, typical object identification algorithms struggle to maintain high resilience in underwater environments due to picture domain offset, making underwater object detection problematic. Methods: This paper proposes a single-stage detection method with the double enhancement of anchor boxes and features. The feature context relevance is improved by proposing a composite-connected backbone network. The receptive field enhancement module is introduced to enhance the multi-scale detection capability. Finally, a prediction refinement strategy is proposed, which refines the anchor frame and features through two regressions, solves the problem of feature anchor frame misalignment, and improves the detection performance of the single-stage underwater algorithm. Results: We achieved an effect of 80.2 mAP on the Labeled Fish in the Wild dataset, which saves some computational resources and time while still improving accuracy. On the original basis, UWNet can achieve 2.1 AP accuracy improvement due to the powerful feature extraction function and the critical role of multi-scale functional modules. At an input resolution of 300 × 300, UWNet can provide an accuracy of 32.4 AP. When choosing the number of prediction layers, the accuracy of the four and six prediction layer structures is compared. The experiments show that on the Labeled Fish in the Wild dataset, the six prediction layers are better than the four. Conclusion: The single-stage underwater detection model UWNet proposed in this research has a double anchor frame and feature optimization. By adding three functional modules, the underwater detection of the single-stage detector is enhanced to address the issue that it is simple to miss detection while detecting small underwater targets. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

21 pages, 7767 KiB

Open AccessArticle

Intelligent Fault Diagnosis for Inertial Measurement Unit through Deep Residual Convolutional Neural Network and Short-Time Fourier Transform

by Gang Xiang, Jing Miao, Langfu Cui and Xiaoguang Hu

Machines 2022, 10(10), 851; https://doi.org/10.3390/machines10100851 - 23 Sep 2022

Cited by 3 | Viewed by 1754

Abstract

An Inertial Measurement Unit (IMU) is a significant component of a spacecraft, and its fault diagnosis results directly affect the spacecraft’s stability and reliability. In recent years, deep learning-based fault diagnosis methods have made great achievements; however, some problems such as how to [...] Read more.

An Inertial Measurement Unit (IMU) is a significant component of a spacecraft, and its fault diagnosis results directly affect the spacecraft’s stability and reliability. In recent years, deep learning-based fault diagnosis methods have made great achievements; however, some problems such as how to extract effective fault features and how to promote the training process of deep networks are still to be solved. Therefore, in this study, a novel intelligent fault diagnosis approach combining a deep residual convolutional neural network (CNN) and a data preprocessing algorithm is proposed. Firstly, the short-time Fourier transform (STFT) is adopted to transform the raw time domain data into time–frequency images so the useful information and features can be extracted. Then, the Z-score normalization and data augmentation strategies are both explored and exploited to facilitate the training of the subsequent deep model. Furthermore, a modified CNN-based deep diagnosis model, which utilizes the Parameter Rectified Linear Unit (PReLU) as activation functions and residual blocks, automatically learns fault features and classifies fault types. Finally, the experiment’s results indicate that the proposed method has good fault features’ extraction ability and performs better than other baseline models in terms of classification accuracy. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

16 pages, 3355 KiB

Open AccessArticle

A Deep Learning Model Applied to Optical Image Target Detection and Recognition for the Identification of Underwater Biostructures

by Huilin Ge, Yuewei Dai, Zhiyu Zhu and Runbang Liu

Machines 2022, 10(9), 809; https://doi.org/10.3390/machines10090809 - 15 Sep 2022

Cited by 7 | Viewed by 1891

Abstract

Objective: We propose a deep-learning-based underwater target detection system that can effectively solve the problem of underwater optical image target detection and recognition. Methods: In this paper, based on the depth of the underwater optical image target detection and recognition and using a [...] Read more.

Objective: We propose a deep-learning-based underwater target detection system that can effectively solve the problem of underwater optical image target detection and recognition. Methods: In this paper, based on the depth of the underwater optical image target detection and recognition and using a learning model, we put forward corresponding solutions using the concept of style migration solutions, such as training samples. A lack of variability and poor generalization of practical applications presents a challenge for underwater object identification. The UW_YOLOv3 lightweight model was proposed to solve the problems of calculating energy consumption and storage resource limitations in underwater application scenarios. The detection and recognition module, based on deep learning, can deal with the degradation process of underwater imaging by embedding an image enhancement module into the detection and recognition module for the joint tuning and transferring of knowledge. Results: The detection accuracy of the UW_YOLOv3 model designed in this paper outperformed the lightweight algorithm YOLOV3-TINY by 7.9% at the same image scale input. Compared with other large algorithms, the detection accuracy was lower, but the detection speed was much higher. Compared with the SSD algorithm, the detection accuracy was only 4.7 lower; the speed was 40.9 FPS higher; and the rate was nearly 16 times higher than Faster R-CNN. When the input scale was 224, although part of the accuracy was lost, the detection speed doubled, reaching 156.9 FPS. Conclusion: Based on our framework, the problem of underwater optical image target detection and recognition can be effectively solved. Relevant studies have not only enriched the theory of target detection and glory, but have also provided optical glasses with a clear vision for appropriate underwater application systems. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

18 pages, 3409 KiB

Open AccessArticle

Optimization of Shearer Drum Based on Multi-Objective Bat Algorithm with Grid (MOBA/G)

by Mingyu Duan, Qibai Huang, Ren Xu, Chenlin Wang and Jing Xu

Machines 2022, 10(9), 733; https://doi.org/10.3390/machines10090733 - 26 Aug 2022

Cited by 6 | Viewed by 1334

Abstract

The shearer drum undertakes the main function of coal falling and loading, and picks distributed on it have a great impact on the performance of the drum. However, few studies have optimized the pick and drum at the same time. In this paper, [...] Read more.

The shearer drum undertakes the main function of coal falling and loading, and picks distributed on it have a great impact on the performance of the drum. However, few studies have optimized the pick and drum at the same time. In this paper, parameters of pick and drum are considered as design variables, and the response functions of design variables are established based on the central composite experiment method. The optimal structural and working parameters of the pick and the drum of MG500/1130-WD shearer are obtained by using the multi-objective bat algorithm and multi-objective bat algorithm with grid, respectively. Comparing results of the two algorithms, the multi-objective bat algorithm with grid is more effective in improving the comprehensive performance of the drum. According to the optimized design variables, a coal mining test is carried out to verify the optimization effect of the algorithm. The result provides some theoretical references for the design and production of the drum and has some engineering application value. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

16 pages, 5751 KiB

Open AccessArticle

Link Quality Estimation for Wireless ANDON Towers Based on Deep Learning Models

by Teth Azrael Cortes-Aguilar, Jose Antonio Cantoral-Ceballos and Adriana Tovar-Arriaga

Sensors 2022, 22(17), 6383; https://doi.org/10.3390/s22176383 - 24 Aug 2022

Viewed by 1539

Abstract

Data reliability is of paramount importance for decision-making processes in the industry, and for this, having quality links for wireless sensor networks plays a vital role. Process and machine monitoring can be carried out through ANDON towers with wireless transmission and machine learning [...] Read more.

Data reliability is of paramount importance for decision-making processes in the industry, and for this, having quality links for wireless sensor networks plays a vital role. Process and machine monitoring can be carried out through ANDON towers with wireless transmission and machine learning algorithms that predict link quality (LQE) to save time, hence reducing expenses by early failure detection and problem prevention. Indeed, alarm signals used in conjunction with LQE classification models represent a novel paradigm for ANDON towers, allowing low-cost remote sensing within industrial environments. In this research, we propose a deep learning model, suitable for implementation in small workshops with limited computational resources. As part of our work, we collected a novel dataset from a realistic experimental scenario with actual industrial machinery, similar to that commonly found in industrial applications. Then, we carried out extensive data analyses using a variety of machine learning models, each with a methodical search process to adjust hyper-parameters, achieving results from common features such as payload, distance, power, and bit error rate not previously reported in the state of the art. We achieved an accuracy of 99.3% on the test dataset with very little use of computational resources. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Graphical abstract

22 pages, 2706 KiB

Open AccessArticle

Data-Based Stakeholder Identification in Technical Change Management

by Fabian Sippl, Renè Magg, Carla Paulina Gil, Steffen Düring and Gunther Reinhart

Appl. Sci. 2022, 12(16), 8205; https://doi.org/10.3390/app12168205 - 17 Aug 2022

Cited by 3 | Viewed by 1622

Abstract

The efficient and effective handling of technical changes in product and production is seen as an important factor for the long-term success of manufacturing companies. Within the associated processes, the engineering and manufacturing change management, the identification and involvement of all relevant stakeholders, [...] Read more.

The efficient and effective handling of technical changes in product and production is seen as an important factor for the long-term success of manufacturing companies. Within the associated processes, the engineering and manufacturing change management, the identification and involvement of all relevant stakeholders, i.e., departments and employees, plays an essential role. Overlooking relevant stakeholders can lead to unforeseen impacts, such as production stops or further necessary changes, and can cause unforseen increased costs. In particular, in large companies, this task is complex and error-prone due to the high number of changes and departments involved, as well as the abundant variety of changes that can take place. Therefore, this contribution introduces an approach for stakeholder identification in technical change management, which allows the automated identification of relevant stakeholders at the beginning of the reactive phases of the change management process. The approach describes all necessary steps from data preparation to the evaluation of the obtained classification models. It is based on a text-classification approach and focuses in particular on the additional integration of expert knowledge to increase model quality. The approach has been successfully applied in cooperation with a German automotive company, and the obtained model quality has been compared to an expert-based classification. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

18 pages, 1226 KiB

Open AccessArticle

Sintering Quality Prediction Model Based on Semi-Supervised Dynamic Time Feature Extraction Framework

by Yuxuan Li, Chunjie Yang and Youxian Sun

Sensors 2022, 22(15), 5861; https://doi.org/10.3390/s22155861 - 05 Aug 2022

Cited by 3 | Viewed by 1382

Abstract

In the sintering process, it is difficult to obtain the key quality variables in real time, so there is lack of real-time information to guide the production process. Furthermore, these labeled data are too few, resulting in poor performance of conventional soft sensor [...] Read more.

In the sintering process, it is difficult to obtain the key quality variables in real time, so there is lack of real-time information to guide the production process. Furthermore, these labeled data are too few, resulting in poor performance of conventional soft sensor models. Therefore, a novel semi-supervised dynamic feature extraction framework (SS-DTFEE) based on sequence pre-training and fine-tuning is proposed in this paper. Firstly, based on the DTFEE model, the time features of the sequences are extended and extracted. Secondly, a novel weighted bidirectional LSTM unit (BiLSTM) is designed to extract the latent variables of original sequence data. Based on improved BiLSTM, an encoder-decoder model is designed as a pre-training model with unsupervised learning to obtain the hidden information in the process. Next, through model migration and fine-tuning strategy, the prediction performance of labeled datasets is improved. The proposed method is applied in the actual sintering process to estimate the FeO content, which shows a significant improvement of the prediction accuracy, compared to traditional methods. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

22 pages, 8825 KiB

Open AccessArticle

Unsupervised Tool Wear Monitoring in the Corner Milling of a Titanium Alloy Based on a Cutting Condition-Independent Method

by Zhimeng Li, Wen Zhong, Yonggang Shi, Ming Yu, Jian Zhao and Guofeng Wang

Machines 2022, 10(8), 616; https://doi.org/10.3390/machines10080616 - 27 Jul 2022

Cited by 2 | Viewed by 1222

Abstract

Real-time tool condition monitoring (TCM) for corner milling often poses significant challenges. On one hand, corner milling requires configuring complex milling paths, leading to the failure of conventional feature extraction methods to characterize tool conditions. On the other hand, it is costly to [...] Read more.

Real-time tool condition monitoring (TCM) for corner milling often poses significant challenges. On one hand, corner milling requires configuring complex milling paths, leading to the failure of conventional feature extraction methods to characterize tool conditions. On the other hand, it is costly to obtain sufficient test data on corner milling for most of the current pattern recognition methods, which are based on the supervised method. In this work, we propose a time-frequency intrinsic feature extraction strategy of acoustic emission signal (AEs) to construct a cutting condition-independent method for tool wear monitoring. The proposed new feature-extraction strategy is used to obtain the tool wear conditions through the intrinsic information of the time-frequency image of AEs. In addition, an unsupervised tool condition recognition framework, including the unsupervised feature selection, the clustering based on adjacent grids searching (CAGS) and the density factor based on CAGS, is proposed to determine the relationship between tool wear values and AE features. To test the effectiveness of the monitoring system, the experiment is conducted through the corner milling of a titanium alloy workpiece. Five metrics, PUR, CSM, NMI, CluCE and ClaCE, are used to evaluate the effectiveness of the recognition results. Compared with the state-of-the-art supervised methods, our method provides commensurate monitoring effectiveness but requires much fewer test data to build the model, which greatly reduces the operating cost of the TCM system. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

19 pages, 6475 KiB

Open AccessArticle

Evaluation of Internal Cracks in Turbine Blade Thermal Barrier Coating Using Enhanced Multi-Scale Faster R-CNN Model

by Licheng Shi, Yun Long, Yuzhang Wang, Xiaohu Chen and Qunfei Zhao

Appl. Sci. 2022, 12(13), 6446; https://doi.org/10.3390/app12136446 - 24 Jun 2022

Cited by 3 | Viewed by 1579

Abstract

Thermal Barrier Coatings (TBCs) have good performance in heat insulation during service on turbine blades. However, the accumulated residual stress will form cracks, which can easily lead to coating failure. To ensure safe operation, it is necessary to find a method that can [...] Read more.

Thermal Barrier Coatings (TBCs) have good performance in heat insulation during service on turbine blades. However, the accumulated residual stress will form cracks, which can easily lead to coating failure. To ensure safe operation, it is necessary to find a method that can evaluate the health of the coating. In this paper, a non-destructive evaluation technique based on Multi-Scale Enhanced-Faster R-CNN (MSE-Faster R-CNN) is proposed. Firstly, the Visual Geometry Group Network19 layer (VGG-19) was adopted as the baseline network to find the candidate crack Region of Interest (ROI). Considering the influence of the crack on the surroundings, the ROI was expanded to obtain the context information. Secondly, a multi-scale Faster R-CNN detector was used to refine the candidate regions, and provided a comprehensive feature for better crack detection. Finally, a fusion lifetime prediction model was proposed to estimate the remaining lifetime of the TBC. Extensive experiments were conducted to evaluate the performance of the proposed method. The results demonstrated that the proposed method can accurately locate (0.898) and detect (0.806) the cracks in different scales, and the lifetime estimation result reached the best level (Root Mean Square Error (RMSE) = 2.7); there wasas also an acceptable time cost (1.63 s), and all detection conditions of the error rates were below 15%, achieving the best results among the state-of-art methods. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

18 pages, 9071 KiB

Open AccessArticle

Online Detection of Fabric Defects Based on Improved CenterNet with Deformable Convolution

by Jun Xiang, Ruru Pan and Weidong Gao

Sensors 2022, 22(13), 4718; https://doi.org/10.3390/s22134718 - 22 Jun 2022

Cited by 7 | Viewed by 2806

Abstract

The traditional manual defect detection method has low efficiency and is time-consuming and laborious. To address this issue, this paper proposed an automatic detection framework for fabric defect detection, which consists of a hardware system and detection algorithm. For the efficient and high-quality [...] Read more.

The traditional manual defect detection method has low efficiency and is time-consuming and laborious. To address this issue, this paper proposed an automatic detection framework for fabric defect detection, which consists of a hardware system and detection algorithm. For the efficient and high-quality acquisition of fabric images, an image acquisition assembly equipped with three sets of lights sources, eight cameras, and a mirror was developed. The image acquisition speed of the developed device is up to 65 m per minute of fabric. This study treats the problem of fabric defect detection as an object detection task in machine vision. Considering the real-time and precision requirements of detection, we improved some components of CenterNet to achieve efficient fabric defect detection, including the introduction of deformable convolution to adapt to different defect shapes and the introduction of i-FPN to adapt to defects of different sizes. Ablation studies demonstrate the effectiveness of our proposed improvements. The comparative experimental results show that our method achieves a satisfactory balance of accuracy and speed, which demonstrate the superiority of the proposed method. The maximum detection speed of the developed system can reach 37.3 m per minute, which can meet the real-time requirements. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

20 pages, 7340 KiB

Open AccessArticle

Picking Path Planning Method of Dual Rollers Type Safflower Picking Robot Based on Improved Ant Colony Algorithm

by He Zhang, Yun Ge, Chao Sun, Haifeng Zeng and Na Liu

Processes 2022, 10(6), 1213; https://doi.org/10.3390/pr10061213 - 17 Jun 2022

Cited by 7 | Viewed by 2216

Abstract

Aiming at the problem of automatic path planning for the whole safflower bulbs during the operation of safflower picking robots, an improved ant colony algorithm (ACA) was proposed to plan the three-dimensional path of the safflower picking points. The shortest time and distance [...] Read more.

Aiming at the problem of automatic path planning for the whole safflower bulbs during the operation of safflower picking robots, an improved ant colony algorithm (ACA) was proposed to plan the three-dimensional path of the safflower picking points. The shortest time and distance were taken as the overall goal of path planning to comprehensively improve the working efficiency of safflower picking robots. First, in order to shorten time, the angle induction factor was introduced to reduce the angle rotation of the end-effector. Second, in order to shorten the length of the picking path, the picking track was optimized. Finally, the design of the secondary path optimization reduced the number of picking points, which not only shortened the length of the picking path, but also shortened the picking time. The simulation results show that the path planned by the improved ACA was reduced by three picking points, shortening the total length by 74.32%, and reducing the picking time by 0.957 s. The simulation results verify the feasibility of the improved ACA for safflower picking path planning, which provides theoretical reference and technical support for the picking path planning of dual roller safflower picking robots. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Graphical abstract

18 pages, 3992 KiB

Open AccessArticle

Rolling Bearing Fault Diagnosis Based on Multiscale Permutation Entropy and SOA-SVM

by Xi Zhang, Hongju Wang, Mingming Ren, Mengyun He and Lei Jin

Machines 2022, 10(6), 485; https://doi.org/10.3390/machines10060485 - 16 Jun 2022

Cited by 14 | Viewed by 1851

Abstract

The service conditions of underground coal mine equipment are poor, and it is difficult to accurately extract the fault characteristics of rolling bearings. In order to better improve the accuracy of the fault identification of rolling bearings, a fault-detection method based on multiscale [...] Read more.

The service conditions of underground coal mine equipment are poor, and it is difficult to accurately extract the fault characteristics of rolling bearings. In order to better improve the accuracy of the fault identification of rolling bearings, a fault-detection method based on multiscale permutation entropy and SOA-SVM is proposed. First, the whale optimization algorithm is used to select the modal analysis number K and the penalty factor α of the variational mode decomposition algorithm. Then, the vibration signal of rolling bearings is dissolved according to the optimized variational mode decomposition algorithm, and the multi-scale permutation entropy of the main intrinsic mode function is calculated. Finally, the feature values of the matrix are entered into the SVM algorithm optimized by the seagull optimization algorithm to obtain the classification result. The experimental results based on the published rolling bearing datasets of Western Reserve University show that the identification success rate of the proposed method can reach 98.75%. The fault detection of the rolling bearings can be completed accurately and efficiently. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

12 pages, 2962 KiB

Open AccessArticle

The Development of an Automatic Rib Sequence Labeling System on Axial Computed Tomography Images with 3-Dimensional Region Growing

by Yu Jin Seol, So Hyun Park, Young Jae Kim, Young-Taek Park, Hee Young Lee and Kwang Gi Kim

Sensors 2022, 22(12), 4530; https://doi.org/10.3390/s22124530 - 15 Jun 2022

Cited by 2 | Viewed by 1878

Abstract

This paper proposes a development of automatic rib sequence labeling systems on chest computed tomography (CT) images with two suggested methods and three-dimensional (3D) region growing. In clinical practice, radiologists usually define anatomical terms of location depending on the rib’s number. Thus, with [...] Read more.

This paper proposes a development of automatic rib sequence labeling systems on chest computed tomography (CT) images with two suggested methods and three-dimensional (3D) region growing. In clinical practice, radiologists usually define anatomical terms of location depending on the rib’s number. Thus, with the manual process of labeling 12 pairs of ribs and counting their sequence, it is necessary to refer to the annotations every time the radiologists read chest CT. However, the process is tedious, repetitive, and time-consuming as the demand for chest CT-based medical readings has increased. To handle the task efficiently, we proposed an automatic rib sequence labeling system and implemented comparison analysis on two methods. With 50 collected chest CT images, we implemented intensity-based image processing (IIP) and a convolutional neural network (CNN) for rib segmentation on this system. Additionally, three-dimensional (3D) region growing was used to classify each rib’s label and put in a sequence label. The IIP-based method reported a 92.0% and the CNN-based method reported a 98.0% success rate, which is the rate of labeling appropriate rib sequences over whole pairs (1st to 12th) for all slices. We hope for the applicability thereof in clinical diagnostic environments by this method-efficient automatic rib sequence labeling system. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

18 pages, 2788 KiB

Open AccessArticle

The Amalgamation of the Object Detection and Semantic Segmentation for Steel Surface Defect Detection

by Mansi Sharma, Jongtae Lim and Hansung Lee

Appl. Sci. 2022, 12(12), 6004; https://doi.org/10.3390/app12126004 - 13 Jun 2022

Cited by 16 | Viewed by 3309

Abstract

Steel surface defect detection is challenging because it contains various atypical defects. Many studies have attempted to detect metal surface defects using deep learning and had success in applying deep learning. Despite many previous studies to solve the steel surface defect detection, it [...] Read more.

Steel surface defect detection is challenging because it contains various atypical defects. Many studies have attempted to detect metal surface defects using deep learning and had success in applying deep learning. Despite many previous studies to solve the steel surface defect detection, it remains a difficult problem. To resolve the atypical defects problem, we introduce a hierarchical approach for the classification and detection of defects on the steel surface. The proposed approach has a hierarchical structure of the binary classifier at the first stage and the object detection and semantic segmentation algorithms at the second stage. It shows 98.6% accuracy in scratch and other types of defect classification and 77.12% mean average precision (mAP) in defect detection using the Northeastern University (NEU) surface defect detection dataset. A comparative analysis with the previous studies shows that the proposed approach achieves excellent results on the NEU dataset. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

16 pages, 559 KiB

Open AccessArticle

Fault Diagnosis for Power Transformers through Semi-Supervised Transfer Learning

by Weiyun Mao, Bengang Wei, Xiangyi Xu, Lu Chen, Tianyi Wu, Zhengrui Peng and Chen Ren

Sensors 2022, 22(12), 4470; https://doi.org/10.3390/s22124470 - 13 Jun 2022

Cited by 5 | Viewed by 1876

Abstract

The fault diagnosis of power transformers is a challenging problem. The massive multisource fault is heterogeneous, the type of fault is undetermined sometimes, and one device has only met a few kinds of faults in the past. We propose a fault diagnosis method [...] Read more.

The fault diagnosis of power transformers is a challenging problem. The massive multisource fault is heterogeneous, the type of fault is undetermined sometimes, and one device has only met a few kinds of faults in the past. We propose a fault diagnosis method based on deep neural networks and a semi-supervised transfer learning framework called adaptive reinforcement (AR) to solve the above limitations. The innovation of this framework consists of its enhancement of the consistency regularization algorithm. The experiments were conducted on real-world 110 kV power transformers’ three-phase fault grounding currents of the iron cores from various devices with four types of faults: Phases A, B, C and ABC to ground. We trained the model on the source domain and then transferred the model to the target domain, which included the unbalanced and undefined fault datasets. The results show that our proposed model reaches over

95 %

accuracy in classifying the type of fault and outperforms other popular networks. Our AR framework fits target devices’ fault data with fewer dozen epochs than other novel semi-supervised techniques. Combining the deep neural network and the AR framework helps diagnose the power transformers, which lack diagnosis knowledge, with much less training time and reliable accuracy. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

17 pages, 8886 KiB

Open AccessArticle

Comparative Study of Structural Anomaly Diagnosis Based on ANN Model Using Random Displacement and Acceleration Responses with Incomplete Measurements

by Zhi-Gang Ruan and Zu-Guang Ying

Sensors 2022, 22(11), 4128; https://doi.org/10.3390/s22114128 - 29 May 2022

Cited by 1 | Viewed by 1325

Abstract

Structural anomaly diagnosis, such as damage identification, is a continuously interesting issue. Artificial neural networks have an excellent ability to model complex structure dynamics. In this paper, an artificial neural network model is used to describe the relationship between structural responses and anomalies [...] Read more.

Structural anomaly diagnosis, such as damage identification, is a continuously interesting issue. Artificial neural networks have an excellent ability to model complex structure dynamics. In this paper, an artificial neural network model is used to describe the relationship between structural responses and anomalies such as stiffness reduction due to damages. Random acceleration and displacement responses as generally measured data are used as the input to the artificial neural network, and the output of the artificial neural network is the anomaly severity. The artificial neural network model is set up by training and then validated using random vibration responses with different structural anomalies. The structural anomaly diagnosis method based on the artificial neural network model using random acceleration and displacement responses is applied to a five-story building structure under random base excitations (seismic loading). Anomalies in the structure are denoted by stiffness reduction. Structural anomaly diagnosis using random acceleration responses is compared with that using random displacement responses. The numerical results show the effects of different random vibration responses used on the accuracy of predicting stiffness reduction. The actual incomplete measurements include intensive noise, finite sampling time length, and limited measurement points. The effects of the incomplete measurements on the accuracy of predicting results are also discussed. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

27 pages, 1009 KiB

Open AccessReview

Overview of Equipment Health State Estimation and Remaining Life Prediction Methods

by Jingyi Zhao, Chunhai Gao, Tao Tang, Xiao Xiao, Ming Luo and Binbin Yuan

Machines 2022, 10(6), 422; https://doi.org/10.3390/machines10060422 - 26 May 2022

Cited by 2 | Viewed by 2792

Abstract

Health state estimation can quantitatively evaluate the current degradation state of equipment, and remaining life prediction can quantitatively predict the remaining service time of equipment. These two technologies can provide a basis for condition-based maintenance and predictive maintenance of equipment, respectively. In recent [...] Read more.

Health state estimation can quantitatively evaluate the current degradation state of equipment, and remaining life prediction can quantitatively predict the remaining service time of equipment. These two technologies can provide a basis for condition-based maintenance and predictive maintenance of equipment, respectively. In recent years, a large amount of research has been implemented in these two technologies. However, there is not any systematic review that covers these two technologies, and their engineering applications, comprehensively. To fill the gap, this paper makes a comparative analysis of existing health state estimation and remaining life prediction methods, and details the characteristics and limitations of various methods. The engineering applications of these two methods are summarized, and their applicable objects are briefly given. Finally, these two methods are summarized, and their feasibility for engineering application is discussed. This work provides guidance for the selection of industrial equipment health assessment and remaining life prediction methods. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

21 pages, 4122 KiB

Open AccessArticle

Research on Repetition Counting Method Based on Complex Action Label String

by Fanghong Yang, Gao Wang, Deping Li, Ning Liu and Feiyan Min

Machines 2022, 10(6), 419; https://doi.org/10.3390/machines10060419 - 26 May 2022

Cited by 1 | Viewed by 1850

Abstract

Smart factories have real-time demands for the statistics of productivity to meet the needs of quick reaction capabilities. To solve this problem, a counting method based on our decomposition strategy of actions was proposed for complex actions. Our method needs to decompose complex [...] Read more.

Smart factories have real-time demands for the statistics of productivity to meet the needs of quick reaction capabilities. To solve this problem, a counting method based on our decomposition strategy of actions was proposed for complex actions. Our method needs to decompose complex actions into several essential actions and define a label string for each complex action according to the sequence of the essential actions. While counting, we firstly employ an online action recognition algorithm to transform video frames into label numbers, which will be stored in a result queue. Then, the label strings are searched for their results in queue. If the search succeeds, a complex action will be considered to have occurred. Meanwhile, the corresponding counter should be updated to accomplish counting. The comparison test results in a video dataset of workers’ repetitive movements in package printing production lines and illustrate that our method has a lower counting errors, MAE (mean absolute error) less than 5% as well as an OBOA (off-by-one accuracy) more than 90%. Moreover, to enhance the adaptability of the action recognition model to deal with the change of action duration, we propose an adaptive parameter module based on the Kalman filter, which improves counting performances to a certain extent. The conclusions are that our method can achieve high counting performance, and the adaptive parameter module can further improve performances. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

20 pages, 3743 KiB

Open AccessArticle

Fast Fault Diagnosis in Industrial Embedded Systems Based on Compressed Sensing and Deep Kernel Extreme Learning Machines

by Nanliang Shan, Xinghua Xu, Xianqiang Bao and Shaohua Qiu

Sensors 2022, 22(11), 3997; https://doi.org/10.3390/s22113997 - 25 May 2022

Cited by 6 | Viewed by 1777

Abstract

With the complexity and refinement of industrial systems, fast fault diagnosis is crucial to ensuring the stable operation of industrial equipment. The main limitation of the current fault diagnosis methods is the lack of real-time performance in resource-constrained industrial embedded systems. Rapid online [...] Read more.

With the complexity and refinement of industrial systems, fast fault diagnosis is crucial to ensuring the stable operation of industrial equipment. The main limitation of the current fault diagnosis methods is the lack of real-time performance in resource-constrained industrial embedded systems. Rapid online detection can help deal with equipment failures in time to prevent equipment damage. Inspired by the ideas of compressed sensing (CS) and deep extreme learning machines (DELM), a data-driven general method is proposed for fast fault diagnosis. The method contains two modules: data sampling and fast fault diagnosis. The data sampling module non-linearly projects the intensive raw monitoring data into low-dimensional sampling space, which effectively reduces the pressure of transmission, storage and calculation. The fast fault diagnosis module introduces the kernel function into DELM to accommodate sparse signals and then digs into the inner connection between the compressed sampled signal and the fault types to achieve fast fault diagnosis. This work takes full advantage of the sparsity of the signal to enable fast fault diagnosis online. It is a general method in industrial embedded systems under data-driven conditions. The results on the CWRU dataset and real platforms show that our method not only has a significant speed advantage but also maintains a high accuracy, which verifies the practical application value in industrial embedded systems. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Graphical abstract

20 pages, 11842 KiB

Open AccessArticle

Prediction of the Comprehensive Error Field in the Machining Space of the Five-Axis Machine Tool Based on the “S”-Shaped Specimen Family

by Shi Wu, Zeyu Dong, Fei Qi and Zhendong Fan

Machines 2022, 10(5), 408; https://doi.org/10.3390/machines10050408 - 23 May 2022

Cited by 4 | Viewed by 1979

Abstract

In order to quickly and accurately predict the spatial geometric error field of the five-axis machine tool processing, a method for predicting the comprehensive error field of the five-axis machine tool processing space based on the “S”-shaped specimen family is studied. Firstly, for [...] Read more.

In order to quickly and accurately predict the spatial geometric error field of the five-axis machine tool processing, a method for predicting the comprehensive error field of the five-axis machine tool processing space based on the “S”-shaped specimen family is studied. Firstly, for the five-axis CNC machine tool in the form of A-C dual turntable, the geometric error model of the rotating axis is established based on the multi-body dynamics theory; the error mapping relationship between the processing technology system and the workpiece is analyzed based on the “S”-shaped specimen family, and the identification of 12 geometric errors of the two rotating shafts. Then, the error value of the sampling point is measured based on the “S”-shaped test piece in machine contact, and the double-circle center coordinate value is determined according to the curvature of the measured wire of the test piece, in order to identify the geometric errors of the two rotation axes of the five-axis machine tool. Finally, based on the prediction method, the comprehensive error field of the five-axis CNC machine tool processing space is analyzed. Compared with other geometric error identification methods, the measurement accuracy of this method meets the processing requirements and can further evaluate the comprehensive performance of the machine tool. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

24 pages, 7348 KiB

Open AccessArticle

Bearing Faulty Prediction Method Based on Federated Transfer Learning and Knowledge Distillation

by Yiqing Zhou, Jian Wang and Zeru Wang

Machines 2022, 10(5), 376; https://doi.org/10.3390/machines10050376 - 16 May 2022

Cited by 9 | Viewed by 2087

Abstract

In this paper, a novel bearing faulty prediction method based on federated transfer learning and knowledge distillation is proposed with three stages: (1) a “signal to image” conversion method based on the continuous wavelet transform is used as the data pre-processing method to [...] Read more.

In this paper, a novel bearing faulty prediction method based on federated transfer learning and knowledge distillation is proposed with three stages: (1) a “signal to image” conversion method based on the continuous wavelet transform is used as the data pre-processing method to satisfy the input characteristic of the proposed faulty prediction model; (2) a novel multi-source based federated transfer learning method is introduced to acquire knowledge from multiple different but related areas, enhancing the generalization ability of the proposed model; and (3) a novel multi-teacher-based knowledge distillation is introduced as the knowledge transference way to transfer multi-source knowledge with dynamic importance weighting, releasing the target data requirement and the target model parameter size, which makes it possible for the edge-computing based deployment. The effectiveness of the proposed bearing faulty prediction approach is evaluated on two case studies of two public datasets offered by the Case Western Reserve University and the Paderborn University, respectively. The evaluation result shows that the proposed approach outperforms other state-of-the-art faulty prediction approaches in terms of higher accuracy and lower parameter size with limited labeled target data. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

17 pages, 5130 KiB

Open AccessArticle

Fault Prediction of Rolling Element Bearings Using the Optimized MCKD–LSTM Model

by Leilei Ma, Hong Jiang, Tongwei Ma, Xiangfeng Zhang, Yong Shen and Lei Xia

Machines 2022, 10(5), 342; https://doi.org/10.3390/machines10050342 - 06 May 2022

Cited by 4 | Viewed by 1799

Abstract

The reliability and safety of rotating equipment depend on the performance of bearings. For complex systems with high reliability and safety needs, effectively predicting the fault data in the use stage has important guiding significance for reasonably formulating reliability plans and carrying out [...] Read more.

The reliability and safety of rotating equipment depend on the performance of bearings. For complex systems with high reliability and safety needs, effectively predicting the fault data in the use stage has important guiding significance for reasonably formulating reliability plans and carrying out reliability maintenance activities. Many methods have been used to solve the problem of reliability prediction. Due to its convenience and efficiency, the data-driven method is increasingly widely used in practical reliability prediction. In order to ensure the reliability of bearing operation, the main objective of the present study is to establish a novel model based on the optimized maximum correlation kurtosis deconvolution (MCKD) and long short-term memory (LSTM) recurrent neural network to realize early bearing fault warnings by predicting bearing fault time series. The proposed model is based on the lifecycle vibration signal of the bearing. In the first step, the cuckoo search (CS) is utilized to optimize the parameter filter length and deconvolution period of MCKD, considering the influence of periodic bearing time series, and to improve the fault impact component of the optimized MCKD deconvolution time series. Then the LSTM learning rate is selected according to the deconvolution time series. Finally, the dataset obtained through various preprocessing approaches is used to train and predict the LSTM model. The analyses performed using the XJTU-SY bearing dataset demonstrate that the prediction results are in good consistency with real fault data, and the average prediction accuracy of the optimized MCKD–LSTM model is 26% higher than that of the original time series. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

20 pages, 3497 KiB

Open AccessArticle

Causal Network Structure Learning Based on Partial Least Squares and Causal Inference of Nonoptimal Performance in the Wastewater Treatment Process

by Yuhan Wang, Dan Yang, Xin Peng, Weimin Zhong and Hui Cheng

Processes 2022, 10(5), 909; https://doi.org/10.3390/pr10050909 - 05 May 2022

Viewed by 1650

Abstract

Due to environmental fluctuations, the operating performance of complex industrial processes may deteriorate and affect economic benefits. In order to obtain maximal economic benefits, operating performance assessment is a novel focus. Therefore, this paper proposes a whole framework from operating performance assessment to [...] Read more.

Due to environmental fluctuations, the operating performance of complex industrial processes may deteriorate and affect economic benefits. In order to obtain maximal economic benefits, operating performance assessment is a novel focus. Therefore, this paper proposes a whole framework from operating performance assessment to nonoptimal cause identification based on partial-least-squares-based Granger causality analysis (PLS-GC) and Bayesian networks (BNs). The proposed method has three main contributions. First, a multiblock operating performance assessment model is established to correspondingly extract economic-related information and dynamic information. Then, a Bayesian network structure is established by PLS-GC that excludes the strong coupling of variables and simplifies the network structure. Lastly, nonoptimal root cause and and nonoptimal transmission path are identified by Bayesian inference. The effectiveness of the proposed method was verified on Benchmark Simulation Model 1. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Graphical abstract

15 pages, 2334 KiB

Open AccessArticle

MSFT-YOLO: Improved YOLOv5 Based on Transformer for Detecting Defects of Steel Surface

by Zexuan Guo, Chensheng Wang, Guang Yang, Zeyuan Huang and Guo Li

Sensors 2022, 22(9), 3467; https://doi.org/10.3390/s22093467 - 02 May 2022

Cited by 95 | Viewed by 9474

Abstract

With the development of artificial intelligence technology and the popularity of intelligent production projects, intelligent inspection systems have gradually become a hot topic in the industrial field. As a fundamental problem in the field of computer vision, how to achieve object detection in [...] Read more.

With the development of artificial intelligence technology and the popularity of intelligent production projects, intelligent inspection systems have gradually become a hot topic in the industrial field. As a fundamental problem in the field of computer vision, how to achieve object detection in the industry while taking into account the accuracy and real-time detection is an important challenge in the development of intelligent detection systems. The detection of defects on steel surfaces is an important application of object detection in the industry. Correct and fast detection of surface defects can greatly improve productivity and product quality. To this end, this paper introduces the MSFT-YOLO model, which is improved based on the one-stage detector. The MSFT-YOLO model is proposed for the industrial scenario in which the image background interference is great, the defect category is easily confused, the defect scale changes a great deal, and the detection results of small defects are poor. By adding the TRANS module, which is designed based on Transformer, to the backbone and detection headers, the features can be combined with global information. The fusion of features at different scales by combining multi-scale feature fusion structures enhances the dynamic adjustment of the detector to objects at different scales. To further improve the performance of MSFT-YOLO, we also introduce plenty of effective strategies, such as data augmentation and multi-step training methods. The test results on the NEU-DET dataset show that MSPF-YOLO can achieve real-time detection, and the average detection accuracy of MSFT-YOLO is 75.2, improving about 7% compared to the baseline model (YOLOv5) and 18% compared to Faster R-CNN, which is advantageous and inspiring. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

20 pages, 4480 KiB

Open AccessArticle

Feature-Based and Process-Based Manufacturing Cost Estimation

by Fangwei Ning, Hongquan Qu, Yan Shi, Maolin Cai and Weiqing Xu

Machines 2022, 10(5), 319; https://doi.org/10.3390/machines10050319 - 28 Apr 2022

Cited by 1 | Viewed by 2574

Abstract

The demand for mass custom parts is increasing, estimating the cost of parts to a high degree of efficiency is a matter of great concern to most manufacturing companies. Under the premise of machining operations, cost estimation based on features and processes yields [...] Read more.

The demand for mass custom parts is increasing, estimating the cost of parts to a high degree of efficiency is a matter of great concern to most manufacturing companies. Under the premise of machining operations, cost estimation based on features and processes yields high estimation accuracy, but it necessitates accurately identifying a part’s machining features and establishing the relationship between the feature and the cost. Accordingly, a feature recognition method based on syntactic pattern recognition is proposed herein. The proposed method provides a more precise feature definition and easily describes complex features using constraints. To establish the relationships between geometric features, processing modes, and cost, this study proposes a method of describing the features and the processing mode using feature quantities and adopts deep learning technology to establish the relationship between feature quantities and cost. By comparing a back propagation (BP) network and a convolutional neural network (CNN) it can be concluded that a CNN using the “RMSProp” optimizer exhibits higher accuracy. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

16 pages, 5668 KiB

Open AccessArticle

A Fault Diagnosis Model for Coaxial-Rotor Unit Using Bidirectional Gate Recurrent Unit and Highway Network

by Zhaoqin Peng, Kunyu Dong, Yan Wang and Xucong Huang

Machines 2022, 10(5), 313; https://doi.org/10.3390/machines10050313 - 27 Apr 2022

Cited by 1 | Viewed by 1511

Abstract

A turbojet engine is the most significant part of an Internal Combustion Engine (ICE) for Hybrid Electric Vehicles. Specifically, the coaxial-rotor unit is the key component, whose performance largely affects the working efficiency. Thereby, the fault diagnosis methods for coaxial-rotor units is a [...] Read more.

A turbojet engine is the most significant part of an Internal Combustion Engine (ICE) for Hybrid Electric Vehicles. Specifically, the coaxial-rotor unit is the key component, whose performance largely affects the working efficiency. Thereby, the fault diagnosis methods for coaxial-rotor units is a main focus. In line with our test results, the bearing circlip is the most vulnerable element while rotating. Moreover, the low-speed rotating fault diagnosis is even challenging for current methods. Since the fault diagnosis on the bearing circlip of coaxial-rotor units is absent, this paper establishes a test rig on a running coaxial-rotor unit under different working conditions. The three-directional vibration signals are collected and analyzed to demonstrate the working states. On the task of bearing circlip failure classification, a deep-learning-based model using the Bidirectional Gate Recurrent Unit and the Highway Network is developed, which is capable of capturing hidden features and removing unrelated information. For working performance evaluation, experiments on the data of different rotating speeds are carried out. Among all the fault diagnosis methods, our model is the best approach and achieves an average accuracy of 99.4%. The encouraging results reveal that the proposed model is effective in both the high-speed and low-speed fault diagnosis of bearing circlip malfunction. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

16 pages, 3699 KiB

Open AccessArticle

A Model-Agnostic Meta-Baseline Method for Few-Shot Fault Diagnosis of Wind Turbines

by Xiaobo Liu, Wei Teng and Yibing Liu

Sensors 2022, 22(9), 3288; https://doi.org/10.3390/s22093288 - 25 Apr 2022

Cited by 12 | Viewed by 2357

Abstract

The technology of fault diagnosis is helpful to improve the reliability of wind turbines, and further reduce the operation and maintenance cost at wind farms. However, in reality, wind turbines are not allowed to operate with faults, so few fault samples could be [...] Read more.

The technology of fault diagnosis is helpful to improve the reliability of wind turbines, and further reduce the operation and maintenance cost at wind farms. However, in reality, wind turbines are not allowed to operate with faults, so few fault samples could be obtained. With a small amount of training data, traditional fault diagnosis models that need huge samples under a deep learning framework are difficult to maintain with high accuracy and effectiveness. Few-shot learning can effectively solve the problem of overfitting caused by fewer fault samples in model training. In view of model-agnostic meta-learning (MAML), this paper proposes a model for few-shot fault diagnosis of the wind turbines drivetrain, which is named model-agnostic meta-baseline (MAMB). The training data is input to the base classification model for pre-training, then, some data is randomly selected from the training set to form multiple meta-learning tasks that are utilized to train the MAML to finally fine-tune the later layers of the model at a smaller learning rate. The proposed model was analyzed by the small samples of the bearing data from Case Western Reserve University (CWRU) data, the generator bearings, and gearboxes vibration data in wind turbines under randomly changing operating conditions. The results verified that the proposed method was superior in one-shot, five-shot, and ten-shot tasks of wind turbines. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

23 pages, 28453 KiB

Open AccessArticle

A Lightweight Model for Bearing Fault Diagnosis Based on Gramian Angular Field and Coordinate Attention

by Jialiang Cui, Qianwen Zhong, Shubin Zheng, Lele Peng and Jing Wen

Machines 2022, 10(4), 282; https://doi.org/10.3390/machines10040282 - 17 Apr 2022

Cited by 24 | Viewed by 3243

Abstract

The key to ensuring rotating machinery’s safe and reliable operation is efficient and accurate faults diagnosis. Intelligent fault diagnosis technology based on deep learning (DL) has gained increasing attention. A critical challenge is how to embed the characteristics of time series into DL [...] Read more.

The key to ensuring rotating machinery’s safe and reliable operation is efficient and accurate faults diagnosis. Intelligent fault diagnosis technology based on deep learning (DL) has gained increasing attention. A critical challenge is how to embed the characteristics of time series into DL to obtain stable features that correlate with equipment conditions. This study proposes a lightweight rolling bearing fault diagnosis method based on Gramian angular field (GAF) and coordinated attention (CA) to improve rolling bearing recognition performance and diagnosis efficiency. Firstly, the time domain signal is encoded into GAF images after downsampling and segmentation. This method retains the temporal relation of the time series and provides valuable features for DL. Secondly, a lightweight convolution neural network (CNN) model is constructed through depthwise separable convolution, inverse residual block, and linear bottleneck layer to learn advanced features. After that, CA is employed to capture the long-range dependencies and identify the precise position information of the GAF images with nearly no additional computational overhead. The proposed method is tested and evaluated by CWRU bearing dataset and experimental dataset. The results demonstrate that the CNN based on GAF and CA (GAF-CA-CNN) model can effectively reduce the calculation overhead of the model and achieve high diagnostic accuracy. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

20 pages, 3082 KiB

Open AccessArticle

Deep Reinforcement Learning for Dynamic Flexible Job Shop Scheduling with Random Job Arrival

by Jingru Chang, Dong Yu, Yi Hu, Wuwei He and Haoyu Yu

Processes 2022, 10(4), 760; https://doi.org/10.3390/pr10040760 - 13 Apr 2022

Cited by 32 | Viewed by 6153

Abstract

The production process of a smart factory is complex and dynamic. As the core of manufacturing management, the research into the flexible job shop scheduling problem (FJSP) focuses on optimizing scheduling decisions in real time, according to the changes in the production environment. [...] Read more.

The production process of a smart factory is complex and dynamic. As the core of manufacturing management, the research into the flexible job shop scheduling problem (FJSP) focuses on optimizing scheduling decisions in real time, according to the changes in the production environment. In this paper, deep reinforcement learning (DRL) is proposed to solve the dynamic FJSP (DFJSP) with random job arrival, with the goal of minimizing penalties for earliness and tardiness. A double deep Q-networks (DDQN) architecture is proposed and state features, actions and rewards are designed. A soft ε-greedy behavior policy is designed according to the scale of the problem. The experimental results show that the proposed DRL is better than other reinforcement learning (RL) algorithms, heuristics and metaheuristics in terms of solution quality and generalization. In addition, the soft ε-greedy strategy reasonably balances exploration and exploitation, thereby improving the learning efficiency of the scheduling agent. The DRL method is adaptive to the dynamic changes of the production environment in a flexible job shop, which contributes to the establishment of a flexible scheduling system with self-learning, real-time optimization and intelligent decision-making. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

18 pages, 6055 KiB

Open AccessArticle

Object Detection Algorithm for Surface Defects Based on a Novel YOLOv3 Model

by Ning Lv, Jian Xiao and Yujing Qiao

Processes 2022, 10(4), 701; https://doi.org/10.3390/pr10040701 - 05 Apr 2022

Cited by 8 | Viewed by 2064

Abstract

The surface defects of industrial structural parts have the characteristics of a large-scale span and many small objects, so a novel YOLOv3 model, the YOLOv3-ALL algorithm, is proposed in this paper to solve the problem of precise defect detection. The K-means++ algorithm is [...] Read more.

The surface defects of industrial structural parts have the characteristics of a large-scale span and many small objects, so a novel YOLOv3 model, the YOLOv3-ALL algorithm, is proposed in this paper to solve the problem of precise defect detection. The K-means++ algorithm is combined with the intersection-over-union (IoU) and comparison of the prior box for clustering, which improves the clustering effect. The convolutional block attention module (CBAM) is embedded in the network, thus improving the ability of the network to obtain key information in the image. By adding fourth-scale prediction, the detection capability of a YOLOv3 network for small-object defects is greatly improved. A loss function is designed, which adds the generalized intersection-over-union (GIoU) loss combined with focal loss to solve the problems of L2 loss and class imbalance in samples. Experiments regarding contour-defect detection for stamping parts show that the mean average precision (mAP) of the YOLOV3-ALL algorithm reaches 75.05% in defect detection, which is 25.16% higher than that of the YOLOv3 algorithm. The average detection time is 39 ms/sheet. This proves that the YOLOv3-ALL algorithm has good real-time detection efficiency and high detection accuracy. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

26 pages, 5406 KiB

Open AccessReview

Vision-Based Defect Inspection and Condition Assessment for Sewer Pipes: A Comprehensive Survey

by Yanfen Li, Hanxiang Wang, L. Minh Dang, Hyoung-Kyu Song and Hyeonjoon Moon

Sensors 2022, 22(7), 2722; https://doi.org/10.3390/s22072722 - 01 Apr 2022

Cited by 16 | Viewed by 4947

Abstract

Due to the advantages of economics, safety, and efficiency, vision-based analysis techniques have recently gained conspicuous advancements, enabling them to be extensively applied for autonomous constructions. Although numerous studies regarding the defect inspection and condition assessment in underground sewer pipelines have presently emerged, [...] Read more.

Due to the advantages of economics, safety, and efficiency, vision-based analysis techniques have recently gained conspicuous advancements, enabling them to be extensively applied for autonomous constructions. Although numerous studies regarding the defect inspection and condition assessment in underground sewer pipelines have presently emerged, we still lack a thorough and comprehensive survey of the latest developments. This survey presents a systematical taxonomy of diverse sewer inspection algorithms, which are sorted into three categories that include defect classification, defect detection, and defect segmentation. After reviewing the related sewer defect inspection studies for the past 22 years, the main research trends are organized and discussed in detail according to the proposed technical taxonomy. In addition, different datasets and the evaluation metrics used in the cited literature are described and explained. Furthermore, the performances of the state-of-the-art methods are reported from the aspects of processing accuracy and speed. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

22 pages, 3619 KiB

Open AccessArticle

Multi-Stream Convolutional Neural Networks for Rotating Machinery Fault Diagnosis under Noise and Trend Items

by Han Dong, Jiping Lu and Yafeng Han

Sensors 2022, 22(7), 2720; https://doi.org/10.3390/s22072720 - 01 Apr 2022

Cited by 4 | Viewed by 1892

Abstract

In recent years, rotating machinery fault diagnosis methods based on convolutional neural network have achieved much success. However, in real industrial environments, interfering signals are unavoidable, which may reduce the accuracy of fault diagnosis seriously. Most of the current fault diagnosis methods are [...] Read more.

In recent years, rotating machinery fault diagnosis methods based on convolutional neural network have achieved much success. However, in real industrial environments, interfering signals are unavoidable, which may reduce the accuracy of fault diagnosis seriously. Most of the current fault diagnosis methods are of single input type, which may lead to the information contained in the vibration signal not being fully utilized. In this study, theoretical analysis and comprehensive comparative experiments are completed to investigate the time domain input, frequency domain input, and two types of time–frequency domain input. Based on this, a new fault diagnosis model, named multi-stream convolutional neural network, is developed. The model takes the time domain, frequency domain, and time–frequency domain images as input, and it automatically fuses the information contained in different inputs. The proposed model is tested based on three public datasets. The experimental results suggested that the model achieved pretty high accuracy under noise and trend items without the help of signal separation algorithms. In addition, the positive implications of multiple inputs and information fusion are analyzed through the visualization of learned features. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

13 pages, 259 KiB

Open AccessReview

Casting Process Improvement by the Application of Artificial Intelligence

by Nedeljko Dučić, Srećko Manasijević, Aleksandar Jovičić, Žarko Ćojbašić and Radomir Radiša

Appl. Sci. 2022, 12(7), 3264; https://doi.org/10.3390/app12073264 - 23 Mar 2022

Cited by 3 | Viewed by 4064

Abstract

On the way to building smart factories as the vision of Industry 4.0, the casting process stands out as a specific manufacturing process due to its diversity and complexity. One of the segments of smart foundry design is the application of artificial intelligence [...] Read more.

On the way to building smart factories as the vision of Industry 4.0, the casting process stands out as a specific manufacturing process due to its diversity and complexity. One of the segments of smart foundry design is the application of artificial intelligence in the improvement of the casting process. This paper presents an overview of the conducted research studies, which deal with the application of artificial intelligence in the improvement of the casting process. In the review, 37 studies were analyzed over the last 15 years, with a clear indication of the type of casting process, the field of application of artificial intelligence techniques, and the benefits that artificial intelligence brought. The goals of this paper are to bring to attention the great possibilities of the application of artificial intelligence for the improvement of manufacturing processes in foundries, and to encourage new ideas among researchers and engineers. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

10 pages, 1060 KiB

Open AccessCommunication

Detection of Highway Pavement Damage Based on a CNN Using Grayscale and HOG Features

by Guo-Hong Chen, Jie Ni, Zhuo Chen, Hao Huang, Yun-Lei Sun, Wai Hung Ip and Kai Leung Yung

Sensors 2022, 22(7), 2455; https://doi.org/10.3390/s22072455 - 23 Mar 2022

Cited by 10 | Viewed by 1909

Abstract

Aiming at the demand for rapid detection of highway pavement damage, many deep learning methods based on convolutional neural networks (CNNs) have been developed. However, CNN methods with raw image data require a high-performance hardware configuration and cost machine time. To reduce machine [...] Read more.

Aiming at the demand for rapid detection of highway pavement damage, many deep learning methods based on convolutional neural networks (CNNs) have been developed. However, CNN methods with raw image data require a high-performance hardware configuration and cost machine time. To reduce machine time and to apply the detection methods in common scenarios, the CNN structure with preprocessed image data needs to be simplified. In this work, a detection method based on a CNN and the combination of the grayscale and histogram of oriented gradients (HOG) features is proposed. First, the Gamma correction was employed to highlight the grayscale distribution of the damage area, which compresses the space of normal pavement. The preprocessed image was then divided into several unit cells, whose grayscale and HOG were calculated, respectively. The grayscale and HOG of each unit cell were combined to construct the grayscale-weighted HOG (GHOG) feature patterns. These feature patterns were input to the CNN with a specific structure and parameters. The trained indices suggested that the performance of the GHOG-based method was significantly improved, compared with the traditional HOG-based method. Furthermore, the GHOG-feature-based CNN technique exhibited flexibility and effectiveness under the same accuracy, in comparison to those deep learning techniques that directly deal with raw data. Since the grayscale has a definite physical meaning, the present detection method possesses a potential application for the further detection of damage details in the future. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

17 pages, 6422 KiB

Open AccessArticle

On-Machine Detection of Sub-Microscale Defects in Diamond Tool Grinding during the Manufacturing Process Based on DToolnet

by Wen Xue, Chenyang Zhao, Wenpeng Fu, Jianjun Du and Yingxue Yao

Sensors 2022, 22(7), 2426; https://doi.org/10.3390/s22072426 - 22 Mar 2022

Cited by 1 | Viewed by 2150

Abstract

Nowadays, tool condition monitoring (TCM), which can prevent the waste of resources and improve efficiency in the process of machining parts, has developed many mature methods. However, TCM during the production of cutting tools is less studied and has different properties. The scale [...] Read more.

Nowadays, tool condition monitoring (TCM), which can prevent the waste of resources and improve efficiency in the process of machining parts, has developed many mature methods. However, TCM during the production of cutting tools is less studied and has different properties. The scale of the defects in the tool production process is tiny, generally between 10 μm and 100 μm for diamond tools. There are also very few samples with defects produced by the diamond tool grinding process, with only about 600 pictures. Among the many TCM methods, the direct inspection method using machine vision has the advantage of obtaining diamond tool information on-machine at a low cost and with high efficiency, and the method is accurate enough to meet the requirements of this task. Considering the specific, above problems, to analyze the images acquired by the vision system, a neural network model that is suitable for defect detection in diamond tool grinding is proposed, which is named DToolnet. DToolnet is developed by extracting and learning from the small-sample diamond tool features to intuitively and quickly detect defects in their production. The improvement of the feature extraction network, the optimization of the target recognition network, and the adjustment of the parameters during the network training process are performed in DToolnet. The imaging system and related mechanical structures for TCM are also constructed. A series of validation experiments is carried out and the experiment results show that DToolnet can achieve an 89.3 average precision (AP) for the detection of diamond tool defects, which significantly outperforms other classical network models. Lastly, the DToolnet parameters are optimized, improving the accuracy by 4.7%. This research work offers a very feasible and valuable way to achieve TCM in the manufacturing process. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

23 pages, 5193 KiB

Open AccessArticle

A Novel Analytical Modeling Approach for Quality Propagation of Transient Analysis of Serial Production Systems

by Shihong Liu, Shichang Du, Lifeng Xi, Yiping Shao and Delin Huang

Sensors 2022, 22(6), 2409; https://doi.org/10.3390/s22062409 - 21 Mar 2022

Cited by 1 | Viewed by 1660

Abstract

Production system modeling (PSM) for quality propagation involves mapping the principles between components and systems. While most existing studies focus on the steady-state analysis, the transient quality analysis remains largely unexplored. It is of significance to fully understand quality propagation, especially during transients, [...] Read more.

Production system modeling (PSM) for quality propagation involves mapping the principles between components and systems. While most existing studies focus on the steady-state analysis, the transient quality analysis remains largely unexplored. It is of significance to fully understand quality propagation, especially during transients, to shorten product changeover time, decrease quality loss, and improve quality. In this paper, a novel analytical PSM approach is established based on the Markov model, to explore product quality propagation for transient analysis of serial multi-stage production systems. The cascade property for quality propagation among correlated sequential stages was investigated, taking into account both the status of the current stage and the quality of the outputs from upstream stages. Closed-form formulae to evaluate transient quality performances of multi-stage systems were formulated, including the dynamics of system quality, settling time, and quality loss. An iterative procedure utilizing the aggregation technique is presented to approximate transient quality performance with computational efficiency and high accuracy. Moreover, system theoretic properties of quality measures were analyzed and the quality bottleneck identification method was investigated. In the case study, the modeling error was 0.36% and the calculation could clearly track system dynamics; quality bottleneck was identified to decrease the quality loss and facilitate continuous improvement. The experimental results illustrate the applicability of the proposed PSM approach. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

25 pages, 5830 KiB

Open AccessArticle

Optimisation of Operator Support Systems through Artificial Intelligence for the Cast Steel Industry: A Case for Optimisation of the Oxygen Blowing Process Based on Machine Learning Algorithms

by Álvaro Ojeda Roldán, Gert Gassner, Martin Schlautmann, Luis Enrique Acevedo Galicia, Doru Stefan Andreiana, Mikko Heiskanen, Carlos Leyva Guerrero, Fernando Dorado Navas and Alejandro del Real Torres

J. Manuf. Mater. Process. 2022, 6(2), 34; https://doi.org/10.3390/jmmp6020034 - 12 Mar 2022

Cited by 3 | Viewed by 2825

Abstract

The processes involved in the metallurgical industry consume significant amounts of energy and materials, so improving their control would result in considerable improvements in the efficient use of these resources. This study is part of the MORSE H2020 Project, and it aims to [...] Read more.

The processes involved in the metallurgical industry consume significant amounts of energy and materials, so improving their control would result in considerable improvements in the efficient use of these resources. This study is part of the MORSE H2020 Project, and it aims to implement an operator support system that improves the efficiency of the oxygen blowing process of a real cast steel foundry. For this purpose, a machine learning agent is developed according to a reinforcement learning method suitable for the dynamics of the oxygen blowing process in the cast steel factory. This reinforcement learning agent is trained with both historical data provided by the company and data generated by an external model. The trained agent will be the basis of the operator support system that will be integrated into the factory, allowing the agent to continue improving with new and real experience. The results show that the suggestions of the agent improve as it gains experience, and consequently the efficiency of the process also improves. As a result, the success rate of the process increases by 12%. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

26 pages, 4849 KiB

Open AccessArticle

A Novel Integrated Control Method for an Aero-Derivative Gas Turbine of Power Generation

by Senchuang Guo, Ai He, Bo Xiao, Peijun Liu and Zinan Wang

Machines 2022, 10(3), 179; https://doi.org/10.3390/machines10030179 - 28 Feb 2022

Cited by 1 | Viewed by 2207

Abstract

On account of the complexity of aero-derivative gas turbines and the much higher control requirements, it is significant and meaningful to design advanced controllers for obtaining the ideal control effect. In this paper, to improve the performance of the original controller of an [...] Read more.

On account of the complexity of aero-derivative gas turbines and the much higher control requirements, it is significant and meaningful to design advanced controllers for obtaining the ideal control effect. In this paper, to improve the performance of the original controller of an aero-derivative gas turbine, a novel integrated control method is proposed by combining the original controller with a new neural network controller. It realizes the speed control by switching the two controllers during the operation process of the aero-derivative gas turbine. A tracking test and robustness test are conducted to assess the superiority of the novel integrated control method. The results show that in comparison with the original controller and the new neural network controller, the novel integrated control method has a much better speed tracking performance during the four tracking tests. When the model of the aero-derivative gas turbine changes with the ambient temperature and compressor performance degradation, the robustness of the novel integrated control method is also better than the other two controllers. Hence, the superiority of the novel integrated control method is validated. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

14 pages, 5436 KiB

Open AccessTechnical Note

Prediction-Interval-Based Credibility Criteria of Prognostics Results for Practical Use

by Dawn An

Processes 2022, 10(3), 473; https://doi.org/10.3390/pr10030473 - 26 Feb 2022

Cited by 1 | Viewed by 1314

Abstract

Prognostics is an AI-based technique for predicting the degrading/damaging behavior and remaining useful life (RUL) of a system, which facilitates a cost-effective and smart maintenance process. Many prognostics methods have been developed for various applications, such as bearings, aircraft engines, batteries, and fuel [...] Read more.

Prognostics is an AI-based technique for predicting the degrading/damaging behavior and remaining useful life (RUL) of a system, which facilitates a cost-effective and smart maintenance process. Many prognostics methods have been developed for various applications, such as bearings, aircraft engines, batteries, and fuel cell stacks. Once a new prognostics method is developed, it is evaluated using several metrics based on the true value of the RUL. However, these typical evaluation metrics are not applicable in real-world applications, as the true RUL cannot be known before the actual failure of a system. There are no ways to determine the reliability of prognostics results in practice. Therefore, this article presents the credibility criteria of prognostics results based on prediction intervals (PI), which are known values, unlike the true RUL. The PI-based credibility criteria for prognostics results are explained with two simple examples under different levels of noise to help with the decision making on prognostics results in the industrial field. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

17 pages, 7895 KiB

Open AccessArticle

Smart System to Detect Painting Defects in Shipyards: Vision AI and a Deep-Learning Approach

by Hanseok Ma and Sunggeun Lee

Appl. Sci. 2022, 12(5), 2412; https://doi.org/10.3390/app12052412 - 25 Feb 2022

Cited by 9 | Viewed by 2910

Abstract

The shipbuilding industry has recently had to address several problems, such as improving productivity and overcoming the limitations of existing worker-dependent defect-inspection systems for painting on large steel plates while meeting the demands for information and smart-factory systems for quality management. The target [...] Read more.

The shipbuilding industry has recently had to address several problems, such as improving productivity and overcoming the limitations of existing worker-dependent defect-inspection systems for painting on large steel plates while meeting the demands for information and smart-factory systems for quality management. The target shipyard previously used human visual inspection and there was no system to manage defect frequency, type, or history. This is challenging because these defects can have different sizes, shapes, and locations. In addition, the shipyard environment is variable and limits the options for camera placements. To solve these problems, we developed a new Vision AI deep-learning system for detecting painting defects in an actual shipyard production line and conducted experiments to optimize and evaluate the performance. We then configured and installed the Vision AI system to control the actual shipyard production line through a programmable logic controller interface. The installed system analyzes images in real-time and is expected to improve productivity by 11% and reduce quality incidents by 2%. This is the first practical application of AI operating in conjunction with the control unit of the actual shipyard production line. The lessons learned here can be applied to other industrial systems. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

14 pages, 9984 KiB

Open AccessArticle

Compressed Deep Learning to Classify Arrhythmia in an Embedded Wearable Device

by Kwang-Sig Lee, Hyun-Joon Park, Ji Eon Kim, Hee Jung Kim, Sangil Chon, Sangkyu Kim, Jaesung Jang, Jin-Kook Kim, Seongbin Jang, Yeongjoon Gil and Ho Sung Son

Sensors 2022, 22(5), 1776; https://doi.org/10.3390/s22051776 - 24 Feb 2022

Cited by 14 | Viewed by 2726

Abstract

The importance of an embedded wearable device with automatic detection and alarming cannot be overstated, given that 15–30% of patients with atrial fibrillation are reported to be asymptomatic. These asymptomatic patients do not seek medical care, hence traditional diagnostic tools including Holter are [...] Read more.

The importance of an embedded wearable device with automatic detection and alarming cannot be overstated, given that 15–30% of patients with atrial fibrillation are reported to be asymptomatic. These asymptomatic patients do not seek medical care, hence traditional diagnostic tools including Holter are not effective for the further prevention of associated stroke or heart failure. This is likely to be more so in the era of COVID-19, in which patients become more reluctant on hospitalization and checkups. However, little literature is available on this important topic. For this reason, this study developed efficient deep learning with model compression, which is designed to use ECG data and classify arrhythmia in an embedded wearable device. ECG-signal data came from Korea University Anam Hospital in Seoul, Korea, with 28,308 unique patients (15,412 normal and 12,896 arrhythmia). Resnets and Mobilenets with model compression (TensorFlow Lite) were applied and compared for the diagnosis of arrhythmia in an embedded wearable device. The weight size of the compressed model registered a remarkable decrease from 743 MB to 76 KB (1/10000), whereas its performance was almost the same as its original counterpart. Resnet and Mobilenet were similar in terms of accuracy, i.e., Resnet-50 Hz (97.3) vs. Mo-bilenet-50 Hz (97.2), Resnet-100 Hz (98.2) vs. Mobilenet-100 Hz (97.9). Here, 50 Hz/100 Hz denotes the down-sampling rate. However, Resnets took more flash memory and longer inference time than did Mobilenets. In conclusion, Mobilenet would be a more efficient model than Resnet to classify arrhythmia in an embedded wearable device. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

29 pages, 10773 KiB

Open AccessArticle

Denoising and Feature Extraction for Space Infrared Dim Target Recognition Utilizing Optimal VMD and Dual-Band Thermometry

by Hao Zhang, Peng Rao, Xin Chen, Hui Xia and Shenghao Zhang

Machines 2022, 10(3), 168; https://doi.org/10.3390/machines10030168 - 23 Feb 2022

Cited by 6 | Viewed by 1939

Abstract

Space target feature extraction and space infrared target recognition are important components of space situational awareness (SSA). However, owing to far imaging distance between the space target and infrared detector, the infrared signal of the target received by the detector is dim and [...] Read more.

Space target feature extraction and space infrared target recognition are important components of space situational awareness (SSA). However, owing to far imaging distance between the space target and infrared detector, the infrared signal of the target received by the detector is dim and easily contaminated by noise. To effectively improve the accuracy of feature extraction and recognition, it is essential to suppress the noise of the infrared signal. Hence, a novel denoising and extracting feature method combinating optimal variational mode decomposition (VMD) and dual-band thermometry (DBT) is proposed. It takes the mean weighted fuzzy-distribution entropy (FuzzDistEn) of the band-limited intrinsic mode functions (BLIMFs) as the optimization index of dragonfly algorithm (DA) to obtain the optimal parameters (K, α) of VMD. Then the VMD is utilized to decompose the noisy signal to obtain a series of BLIMFs and the Pearson correlation coefficient (PCC) is proposed to determine the effective modes to reconstructe the denoising signal. Finally, based on the denoising signal, the feature of temperature and emissivity-area product are calculated using the DBT. The simulation and experiment results show that the proposed method has better noise reduction performance compared with the other denoising methods, and the accuracy of feature extraction is improved at different noise equivalent irradiance. This provides more accurate feature of temerpature and emissivity-area product for space infrared dim target recognition. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

14 pages, 1107 KiB

Open AccessArticle

Temperature Control for Automated Tape Laying with Infrared Heaters Based on Reinforcement Learning

by Martin Römer, Johannes Bergers, Felix Gabriel and Klaus Dröder

Machines 2022, 10(3), 164; https://doi.org/10.3390/machines10030164 - 22 Feb 2022

Cited by 6 | Viewed by 2756

Abstract

The use of fiber-reinforced lightweight materials in the field of electromobility offers great opportunities to increase the range of electric vehicles and also enhance the functionality of the components themselves. In order to meet the demand for a high number of variants, flexible [...] Read more.

The use of fiber-reinforced lightweight materials in the field of electromobility offers great opportunities to increase the range of electric vehicles and also enhance the functionality of the components themselves. In order to meet the demand for a high number of variants, flexible production technologies are required which can quickly adapt to different component variants and thereby avoid long setup times of the required production equipment. By applying the formflexible process of automated tape laying (ATL), it is possible to build lightweight components in a variant-flexible way. Unidirectional (UD) tapes are often used to build up lightweight structures according to a predefined load path. However, the UD tape which is used to build the components is particularly sensitive to temperature fluctuations due to its low thickness. Temperature fluctuations within the production sites as well as the warming of the tape layer and the deposit surface over longer process times have an impact on the heat flow which is infused to the tape and make an adaptive control of the tape heating indispensable. At present, several model-based control strategies are available. However, these strategies require a comprehensive understanding of the ATL system and its environment and are therefore difficult to design. With the possibility of model-free reinforcement learning, it is possible to build a temperature control system that learns the common dependencies of both the process being used and its operating environment, without the need to rely on a complete understanding of the physical interrelationships. In this paper, a reinforcement learning approach based on the deep deterministic policy gradient (DDPG) algorithm is presented, with the aim to control the temperature of an ATL endeffector based on infrared emitters. The algorithm was adapted to the thermal inertia of the system and trained in a real process environment. With only a small amount of training data, the trained DDPG agent was able to reliably maintain the ATL process temperatures within a specified tolerance range. By applying this technique, UD tape can be deposited at a consistent process temperature over longer process times without the need for a cooling system. Reducing process complexity can help to increase the prevalence of lightweight components and thus contribute to lower energy consumption of electric vehicles. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

19 pages, 7711 KiB

Open AccessArticle

CTIMS: Automated Defect Detection Framework Using Computed Tomography

by Hossam A. Gabbar, Abderrazak Chahid, Md. Jamiul Alam Khan, Oluwabukola Grace Adegboro and Matthew Immanuel Samson

Appl. Sci. 2022, 12(4), 2175; https://doi.org/10.3390/app12042175 - 19 Feb 2022

Cited by 7 | Viewed by 2722

Abstract

Non-Destructive Testing (NDT) is one of the inspection techniques used in industrial tool inspection for quality and safety control. It is performed mainly using X-ray Computed Tomography (CT) to scan the internal structure of the tools and detect the potential defects. In this [...] Read more.

Non-Destructive Testing (NDT) is one of the inspection techniques used in industrial tool inspection for quality and safety control. It is performed mainly using X-ray Computed Tomography (CT) to scan the internal structure of the tools and detect the potential defects. In this paper, we propose a new toolbox called the CT-Based Integrity Monitoring System (CTIMS-Toolbox) for automated inspection of CT images and volumes. It contains three main modules: first, the database management module, which handles the database and reads/writes queries to retrieve or save the CT data; second, the pre-processing module for registration and background subtraction; third, the defect inspection module to detect all the potential defects (missing parts, damaged screws, etc.) based on a hybrid system composed of computer vision and deep learning techniques. This paper explores the different features of the CTIMS-Toolbox, exposes the performance of its modules, compares its features to some existing CT inspection toolboxes, and provides some examples of the obtained results. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

19 pages, 5180 KiB

Open AccessArticle

Modification and Noise Reduction Design of Gear Transmission System of EMU Based on Generalized Regression Neural Network

by Zhaoping Tang, Manyu Wang, Min Zhao and Jianping Sun

Machines 2022, 10(2), 157; https://doi.org/10.3390/machines10020157 - 18 Feb 2022

Cited by 5 | Viewed by 2362

Abstract

In view of traction gear vibration and noise affecting the performance of the transmission system and the comfort of passengers when the electric multiple units (EMU) is running at high speed, taking the traction gear transmission system of an EMU as the research [...] Read more.

In view of traction gear vibration and noise affecting the performance of the transmission system and the comfort of passengers when the electric multiple units (EMU) is running at high speed, taking the traction gear transmission system of an EMU as the research object by using Romax software to construct the parametric modification model of the gear transmission system based on gear modification theory. Combined with multibody dynamics, the vibration response characteristics of the transmission system are simulated and analyzed. A radiated noise prediction model is established using the acoustic boundary element method, based on the generalized regression neural network (GRNN). To further explore the influence of gear modification methods and parameters on vibration and noise characteristics and minimize gear transmission’s radiation noise. A particle swarm optimization (PSO) algorithm is designed to solve the optimal modification parameters. The simulation results reveal that after the optimization and modification, the gear transmission error is significantly reduced, the contact status is considerably improved, and the root mean square value of the acoustic power level is reduced by 13.10 dB, which is a reduction of 14%. It shows that the design can effectively reduce the radiation noise of EMU gear trans-mission system. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

15 pages, 2484 KiB

Open AccessEditor’s ChoiceArticle

Predicting the Electrical Impedance of Rolling Bearings Using Machine Learning Methods

by Eckhard Kirchner, Christoph Bienefeld, Tobias Schirra and Alexander Moltschanov

Machines 2022, 10(2), 156; https://doi.org/10.3390/machines10020156 - 18 Feb 2022

Cited by 4 | Viewed by 1749

Abstract

The present paper describes a measurement setup and a related prediction of the electrical impedance of rolling bearings using machine learning algorithms. The impedance of the rolling bearing is expected to be key in determining the state of health of the bearing, which [...] Read more.

The present paper describes a measurement setup and a related prediction of the electrical impedance of rolling bearings using machine learning algorithms. The impedance of the rolling bearing is expected to be key in determining the state of health of the bearing, which is an essential component in almost all machines. In previous publications, the determination of the impedance of rolling bearings has already been advanced using analytical methods. Despite the improvements in accuracy achieved within the calculations, there are still discrepancies between the calculated and the measured impedance, leading to an approximately constant off-set value. This discrepancy motivates the machine learning approach introduced in this paper. It is shown that with the help of the data-driven methods the difference between analytical prediction and measurement is reduced to the order of up to 2% across the operational range analyzed so far. To introduce the context of the research shown, first the underlying physics of bearing impedance is presented. Subsequently different machine learning approaches are highlighted and compared with each other in terms of their prediction quality in the results part of this paper. As a further aspect, in addition to the prediction of the bearing impedance, it is investigated whether the rotational speed present at the bearing can be predicted from the frequency spectrum of the impedance using order analysis methods which is independent from the force prediction accuracy. The background to this is that, if the prediction quality is sufficiently high, the additional use of speed sensors could be omitted in future investigations. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Graphical abstract

19 pages, 23366 KiB

Open AccessArticle

Improved Wafer Map Inspection Using Attention Mechanism and Cosine Normalization

by Qiao Xu, Naigong Yu and Firdaous Essaf

Machines 2022, 10(2), 146; https://doi.org/10.3390/machines10020146 - 17 Feb 2022

Cited by 9 | Viewed by 6124

Abstract

Wafer map inspection is essential for semiconductor manufacturing quality control and analysis. The deep convolutional neural network (DCNN) is the most effective algorithm in wafer defect pattern analysis. Traditional DCNNs rely heavily on high quality datasets for training. However, obtaining balanced and sufficient [...] Read more.

Wafer map inspection is essential for semiconductor manufacturing quality control and analysis. The deep convolutional neural network (DCNN) is the most effective algorithm in wafer defect pattern analysis. Traditional DCNNs rely heavily on high quality datasets for training. However, obtaining balanced and sufficient labeled data is difficult in practice. This paper reconsiders the causes of the imbalance and proposes a deep learning method that can learn robust knowledge from an imbalanced dataset using the attention mechanism and cosine normalization. We interpret the dataset imbalance as both a feature and a quantity distribution imbalance. To compensate for feature distribution imbalance, we add an improved convolutional attention module to the DCNN to enhance representation. In particular, a feature-map-specific direction mapping module is developed to amplify the positional information of defect clusters. For quantity distribution imbalance, the cosine normalization algorithm is proposed to replace the fully connected layer, and classifier fine-tuning is realized through a small amount of iterative training, which decreases the sensitivity to the quantitative distribution. The experimental results on real-world datasets demonstrate that the proposed method significantly improves the robustness of wafer map inspection and outperforms existing algorithms when trained on imbalanced datasets. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

16 pages, 4748 KiB

Open AccessArticle

Correlation Stability Problem in Selecting Temperature-Sensitive Points of CNC Machine Tools

by Hui Liu, Enming Miao, Liyin Zhang, Dafeng Tang and Yinlong Hou

Machines 2022, 10(2), 132; https://doi.org/10.3390/machines10020132 - 12 Feb 2022

Cited by 2 | Viewed by 2413

Abstract

In the thermal-error compensation of CNC machine tools, temperature-sensitive points (TSPs) are used for predicting thermal error and need to have a high correlation with the thermal error. The stability of the correlation between TSPs and the thermal error is the key to [...] Read more.

In the thermal-error compensation of CNC machine tools, temperature-sensitive points (TSPs) are used for predicting thermal error and need to have a high correlation with the thermal error. The stability of the correlation between TSPs and the thermal error is the key to long-term prediction accuracy. In this paper, the uncertainty-calculation method of the correlation coefficient is proposed to measure the stability of the correlation, and the reasons that affect the stability of the correlation of TSPs are analyzed. Then, the uncertainty-correlation coefficient is proposed, which can comprehensively evaluate the correlation and the stability of the correlation between TSPs and the thermal error. Through long-term experimental verifications, compared with the current TSP selection algorithm, the uncertainty-correlation coefficient can help to select a more stable TSP and improve the long-term prediction accuracy of the thermal error. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

19 pages, 4758 KiB

Open AccessArticle

Dynamic System Modeling of a Hybrid Neural Network with Phase Space Reconstruction and a Stability Identification Strategy

by Mingming Zhang, Jia Zhang, Anping Hou, Aiguo Xia and Wei Tuo

Machines 2022, 10(2), 122; https://doi.org/10.3390/machines10020122 - 09 Feb 2022

Cited by 4 | Viewed by 1462

Abstract

Focusing on the identification of dynamic system stability, a hybrid neural network model is proposed in this research for the rotating stall phenomenon in an axial compressor. Based on the data fusion of the amplitude of the spatial mode, the nonlinear property is [...] Read more.

Focusing on the identification of dynamic system stability, a hybrid neural network model is proposed in this research for the rotating stall phenomenon in an axial compressor. Based on the data fusion of the amplitude of the spatial mode, the nonlinear property is well characterized in the feature extraction of the rotating stall. This method of data processing can effectively avoid the inaccurate recognition of single or multiple measuring sensors only depending on pressure. With the analysis on the spatial mode, a chaotic characteristic was shown in the development of the amplitude with the first-order spatial mode. With the prerequisite of revealing the essence of this dynamic system, a hybrid radial basis function (RBF) neural network was adopted to represent the properties of the system by artificial intelligence learning. Combining the advantages of the methods of K-means and Gradient Descent (GD), the Chaos–K-means–GD–RBF fusion model was established based on the phase space reconstruction of the chaotic sequence. Compared with the two methods mentioned above, the calculation accuracy was significantly improved in the hybrid neural network model. By taking the strategy of global sample entropy and difference quotient criterion identification, a warning of inception can be suggested in advance of 12.3 revolutions (296 ms) with a multi-step prediction before the stall arrival. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

18 pages, 7500 KiB

Open AccessArticle

A Novel Approach for Real-Time Quality Monitoring in Machining of Aerospace Alloy through Acoustic Emission Signal Transformation for DNN

by David Adeniji, Kyle Oligee and Julius Schoop

J. Manuf. Mater. Process. 2022, 6(1), 18; https://doi.org/10.3390/jmmp6010018 - 25 Jan 2022

Cited by 11 | Viewed by 3196

Abstract

Gamma titanium aluminide (γ-TiAl) is considered a high-performance, low-density replacement for nickel-based superalloys in the aerospace industry due to its high specific strength, which is retained at temperatures above 800 °C. However, low damage tolerance, i.e., brittle material behavior with a propensity to [...] Read more.

Gamma titanium aluminide (γ-TiAl) is considered a high-performance, low-density replacement for nickel-based superalloys in the aerospace industry due to its high specific strength, which is retained at temperatures above 800 °C. However, low damage tolerance, i.e., brittle material behavior with a propensity to rapid crack propagation, has limited the application of γ-TiAl. Any cracks introduced during manufacturing would dramatically lower the useful (fatigue) life of γ-TiAl components, making the workpiece surface’s quality from finish machining a critical component to product quality and performance. To address this issue and enable more widespread use of γ-TiAl, this research aims to develop a real-time non-destructive evaluation (NDE) quality monitoring technique based on acoustic emission (AE) signals, wavelet transform, and deep neural networks (DNN). Previous efforts have opted for traditional approaches to AE signal analysis, using statistical feature extraction and classification, which face challenges such as the extraction of good/relevant features and low classification accuracy. Hence, this work proposes a novel AI-enabled method that uses a convolutional neural network (CNN) to extract rich and relevant features from a two-dimensional image representation of 1D time-domain AE signals (known as scalograms), subsequently classifying the AE signature based on pedigreed experimental data and finally predicting the process-induced surface quality. The results of the present work show good classification accuracy of 80.83% using scalogram images, in-situ experimental data, and a VGG-19 pre-trained neural network, establishing the significant potential for real-time quality monitoring in manufacturing processes. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

15 pages, 6005 KiB

Open AccessArticle

Laser Curve Extraction of Wheelset Based on Deep Learning Skeleton Extraction Network

by Shuai Luo, Kai Yang, Lijuan Yang, Yong Wang, Xiaorong Gao, Tianci Jiang and Chunjiang Li

Sensors 2022, 22(3), 859; https://doi.org/10.3390/s22030859 - 23 Jan 2022

Cited by 1 | Viewed by 2443

Abstract

In this paper, a new algorithm for extracting the laser fringe center is proposed. Based on a deep learning skeleton extraction network, the laser stripe center can be extracted quickly and accurately. Skeleton extraction is the process of reducing the shape image to [...] Read more.

In this paper, a new algorithm for extracting the laser fringe center is proposed. Based on a deep learning skeleton extraction network, the laser stripe center can be extracted quickly and accurately. Skeleton extraction is the process of reducing the shape image to its approximate central axis representation while maintaining the image’s topological and geometric shape. Skeleton extraction is an important step in topological and geometric shape analysis. According to the characteristics of the wheelset laser curve dataset, a new skeleton extraction network, a hierarchical skeleton network (LuoNet), is proposed. The proposed architecture has three levels of the encoder–decoder network, and YE Module interconnection is designed between each level of the encoder and decoder network. In the wheelset laser curve dataset, the F1_score can reach 0.714. Compared with the traditional laser curve center extraction algorithm, the proposed LuoNet algorithm has the advantages of short running time, high accuracy, and stable extraction results. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

15 pages, 4147 KiB

Open AccessArticle

Online Detection of Surface Defects Based on Improved YOLOV3

by Xuechun Chen, Jun Lv, Yulun Fang and Shichang Du

Sensors 2022, 22(3), 817; https://doi.org/10.3390/s22030817 - 21 Jan 2022

Cited by 29 | Viewed by 4200

Abstract

Aiming at the problems of low efficiency and poor accuracy in the product surface defect detection. In this paper, an online surface defects detection method based on YOLOV3 is proposed. Firstly, using lightweight network MobileNetV2 to replace the original backbone as the feature [...] Read more.

Aiming at the problems of low efficiency and poor accuracy in the product surface defect detection. In this paper, an online surface defects detection method based on YOLOV3 is proposed. Firstly, using lightweight network MobileNetV2 to replace the original backbone as the feature extractor to improve network speed. Then, we propose an extended feature pyramid network (EFPN) to extend the detection layer for multi-size object detection and design a novel feature fusing module (FFM) embedded in the extend layer to super-resolve features and capture more regional details. In addition, we add an IoU loss function to solve the mismatch between classification and bounding box regression. The proposed method is used to train and test on the hot rolled steel open dataset NEU-DET, which contains six typical defects of a steel surface, namely rolled-in scale, patches, crazing, pitted surface, inclusion and scratches. The experimental results show that our method achieves a satisfactory balance between performance and consumption and reaches 86.96% mAP with a speed of 80.96 FPS, which is more accurate and faster than many other algorithms and can realize real-time and high-precision inspection of product surface defects. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

9 pages, 1643 KiB

Open AccessCommunication

A Study on 3D Deep Learning-Based Automatic Diagnosis of Nasal Fractures

by Yu Jin Seol, Young Jae Kim, Yoon Sang Kim, Young Woo Cheon and Kwang Gi Kim

Sensors 2022, 22(2), 506; https://doi.org/10.3390/s22020506 - 10 Jan 2022

Cited by 16 | Viewed by 2581

Abstract

This paper reported a study on the 3-dimensional deep-learning-based automatic diagnosis of nasal fractures. (1) Background: The nasal bone is the most protuberant feature of the face; therefore, it is highly vulnerable to facial trauma and its fractures are known as the most [...] Read more.

This paper reported a study on the 3-dimensional deep-learning-based automatic diagnosis of nasal fractures. (1) Background: The nasal bone is the most protuberant feature of the face; therefore, it is highly vulnerable to facial trauma and its fractures are known as the most common facial fractures worldwide. In addition, its adhesion causes rapid deformation, so a clear diagnosis is needed early after fracture onset. (2) Methods: The collected computed tomography images were reconstructed to isotropic voxel data including the whole region of the nasal bone, which are represented in a fixed cubic volume. The configured 3-dimensional input data were then automatically classified by the deep learning of residual neural networks (3D-ResNet34 and ResNet50) with the spatial context information using a single network, whose performance was evaluated by 5-fold cross-validation. (3) Results: The classification of nasal fractures with simple 3D-ResNet34 and ResNet50 networks achieved areas under the receiver operating characteristic curve of 94.5% and 93.4% for binary classification, respectively, both indicating unprecedented high performance in the task. (4) Conclusions: In this paper, it is presented the possibility of automatic nasal bone fracture diagnosis using a 3-dimensional Resnet-based single classification network and it will improve the diagnostic environment with future research. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

18 pages, 20682 KiB

Open AccessArticle

Autonomous Incident Detection on Spectrometers Using Deep Convolutional Models

by Xuelin Zhang, Donghao Zhang, Alexander Leye, Adrian Scott, Luke Visser, Zongyuan Ge and Paul Bonnington

Sensors 2022, 22(1), 160; https://doi.org/10.3390/s22010160 - 27 Dec 2021

Cited by 1 | Viewed by 2339

Abstract

This paper focuses on improving the performance of scientific instrumentation that uses glass spray chambers for sample introduction, such as spectrometers, which are widely used in analytical chemistry, by detecting incidents using deep convolutional models. The performance of these instruments can be affected [...] Read more.

This paper focuses on improving the performance of scientific instrumentation that uses glass spray chambers for sample introduction, such as spectrometers, which are widely used in analytical chemistry, by detecting incidents using deep convolutional models. The performance of these instruments can be affected by the quality of the introduction of the sample into the spray chamber. Among the indicators of poor quality sample introduction are two primary incidents: The formation of liquid beads on the surface of the spray chamber, and flooding at the bottom of the spray chamber. Detecting such events autonomously as they occur can assist with improving the overall operational accuracy and efficacy of the chemical analysis, and avoid severe incidents such as malfunction and instrument damage. In contrast to objects commonly seen in the real world, beading and flooding detection are more challenging since they are of significantly small size and transparent. Furthermore, the non-rigid property increases the difficulty of the detection of these incidents, as such that existing deep-learning-based object detection frameworks are prone to fail for this task. There is no former work that uses computer vision to detect these incidents in the chemistry industry. In this work, we propose two frameworks for the detection task of these two incidents, which not only leverage the modern deep learning architectures but also integrate with expert knowledge of the problems. Specifically, the proposed networks first localize the regions of interest where the incidents are most likely generated and then refine these incident outputs. The use of data augmentation and synthesis, and choice of negative sampling in training, allows for a large increase in accuracy while remaining a real-time system for inference. In the data collected from our laboratory, our method surpasses widely used object detection baselines and can correctly detect 95% of the beads and 98% of the flooding. At the same time, out method can process four frames per second and is able to be implemented in real time. Full article

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)

► Show Figures

Figure 1

Topic Menu

Topic Editors

Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing

Topic Information

Keywords

Participating Journals

Published Papers (77 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI