Predictive Analytics and Fault Diagnosis of Machines with Machine Learning Techniques

Abstract submission deadline

31 July 2024

Manuscript submission deadline

31 October 2024

Viewed by

4887

Topic Information

Dear Colleagues,

This Topic focuses on cutting-edge topics in the industrial sector, exploring how predictive analytics and machine fault diagnosis can enhance production efficiency and equipment reliability. With the emergence of Industry 4.0, data-driven decision-making and innovative maintenance strategies have become the cornerstone of the industry. This Topic delves into the methods of employing data analysis, predictive modelling, and machine learning techniques to achieve machine health monitoring and early fault diagnosis, ultimately reducing maintenance costs, minimizing production interruptions, and enhancing equipment reliability. We pay particular attention to critical components in rotating machinery, such as bearings, which play a pivotal role in industrial manufacturing. Through state monitoring and fault diagnosis, alongside emerging technologies like deep learning, we accurately diagnose machine conditions and proactively engage in predictive maintenance. This Topic is designed to foster collaboration between industry and academia, driving innovation in methods and applications to meet the demands of modern industrial production. We eagerly anticipate research findings in this critical field, which will provide the industry with more efficient and reliable production methods.

Prof. Dr. Wentao Mao
Dr. Jie Liu
Topic Editors

Keywords

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Automation automation	-	-	2020	26.3 Days	CHF 1000	Submit
Electronics electronics	2.9	4.7	2012	15.6 Days	CHF 2400	Submit
Energies energies	3.2	5.5	2008	16.1 Days	CHF 2600	Submit
Machines machines	2.6	2.1	2013	15.6 Days	CHF 2400	Submit
Symmetry symmetry	2.7	4.9	2009	16.2 Days	CHF 2400	Submit

MDPI Topics is cooperating with Preprints.org and has built a direct connection between MDPI journals and Preprints.org. Authors are encouraged to enjoy the benefits by posting a preprint at Preprints.org prior to publication:

1. Immediately share your ideas ahead of publication and establish your research priority;
2. Protect your idea from being stolen with this time-stamped preprint article;
3. Enhance the exposure and impact of your research;
4. Receive feedback from your peers in advance;
5. Have it indexed in Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (6 papers)

Order results

Content type Publication Date

Result details

Normal Extended Compact

Journals

All Automation Electronics Energies Machines Symmetry

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

Error

Oops... you haven't selected anything for export.

Ok

clear

25 pages, 12847 KiB  

Open AccessArticle

Machine Fault Diagnosis through Vibration Analysis: Time Series Conversion to Grayscale and RGB Images for Recognition via Convolutional Neural Networks

by Dominik Łuczak

Energies 2024, 17(9), 1998; https://doi.org/10.3390/en17091998 - 23 Apr 2024

Viewed by 225

Abstract

Accurate and timely fault detection is crucial for ensuring the smooth operation and longevity of rotating machinery. This study explores the effectiveness of image-based approaches for machine fault diagnosis using data from a 6DOF IMU (Inertial Measurement Unit) sensor. Three novel methods are [...] Read more.

Accurate and timely fault detection is crucial for ensuring the smooth operation and longevity of rotating machinery. This study explores the effectiveness of image-based approaches for machine fault diagnosis using data from a 6DOF IMU (Inertial Measurement Unit) sensor. Three novel methods are proposed. The IMU6DoF-Time2GrayscaleGrid-CNN method converts the time series sensor data into a single grayscale image, leveraging the efficiency of a grayscale representation and the power of convolutional neural networks (CNNs) for feature extraction. The IMU6DoF-Time2RGBbyType-CNN method utilizes RGB images. The IMU6DoF-Time2RGBbyAxis-CNN method employs an RGB image where each channel corresponds to a specific axis (X, Y, Z) of the sensor data. This axis-aligned representation potentially allows the CNN to learn the relationships between movements along different axes. The performance of all three methods is evaluated through extensive training and testing on a dataset containing various operational states (idle, normal, fault). All methods achieve high accuracy in classifying these states. While the grayscale method offers the fastest training convergence, the RGB-based methods might provide additional insights. The interpretability of the models is also explored using Grad-CAM visualizations. This research demonstrates the potential of image-based approaches with CNNs for robust and interpretable machine fault diagnosis using sensor data. Full article

(This article belongs to the Topic Predictive Analytics and Fault Diagnosis of Machines with Machine Learning Techniques)

►▼ Show Figures

Figure 1

16 pages, 3077 KiB  

Open AccessArticle

Active Distribution Network Fault Diagnosis Based on Improved Northern Goshawk Search Algorithm

by Zhongqi Guo, Xiu Ji, Hui Wang and Xiao Yang

Electronics 2024, 13(7), 1202; https://doi.org/10.3390/electronics13071202 - 25 Mar 2024

Viewed by 431

Abstract

Timely and accurate fault location in active distribution networks is of vital importance to ensure the reliability of power grid operation. However, existing intelligent algorithms applied in fault location of active distribution networks possess slow convergence speed and low accuracy, hindering the construction [...] Read more.

Timely and accurate fault location in active distribution networks is of vital importance to ensure the reliability of power grid operation. However, existing intelligent algorithms applied in fault location of active distribution networks possess slow convergence speed and low accuracy, hindering the construction of new power systems. In this paper, a new regional fault localization method based on an improved northern goshawk search algorithm is proposed. The population quality of the samples was improved by using the chaotic initialization strategy. Meanwhile, the positive cosine strategy and adaptive Gaussian–Cauchy hybrid variational perturbation strategy were introduced to the northern goshawk search algorithm, which adopted the perturbation operation to interfere with the individuals to increase the diversity of the population, contributing to jumping out of the local optimum to strengthen the ability of local escape. Finally, simulation verification was carried out in a multi-branch distribution network containing distributed power sources. Compared with the traditional regional localization models, the new method proposed possesses faster convergence speed and higher location accuracy under different fault locations and different distortion points. Full article

(This article belongs to the Topic Predictive Analytics and Fault Diagnosis of Machines with Machine Learning Techniques)

►▼ Show Figures

Figure 1

28 pages, 12037 KiB  

Open AccessArticle

Improved Generative Adversarial Network for Bearing Fault Diagnosis with a Small Number of Data and Unbalanced Data

by Zhaohui Qin, Faguo Huang, Jiafang Pan, Junlin Niu and Haihua Qin

Symmetry 2024, 16(3), 358; https://doi.org/10.3390/sym16030358 - 15 Mar 2024

Viewed by 730

Abstract

Fault data under real operating conditions are often difficult to collect, making the number of trained fault data small and out of proportion to normal data. Thus, fault diagnosis symmetry (balance) is compromised. This will result in less effective fault diagnosis methods for [...] Read more.

Fault data under real operating conditions are often difficult to collect, making the number of trained fault data small and out of proportion to normal data. Thus, fault diagnosis symmetry (balance) is compromised. This will result in less effective fault diagnosis methods for cases with a small number of data and data imbalances (S&I). We present an innovative solution to overcome this problem, which is composed of two components: data augmentation and fault diagnosis. In the data augmentation section, the S&I dataset is supplemented with a deep convolutional generative adversarial network based on a gradient penalty and Wasserstein distance (WDCGAN-GP), which solve the problems of the generative adversarial network (GAN) being prone to model collapse and the gradient vanishing during the training time. The addition of self-attention allows for a better identification and generation of sample features. Finally, the addition of spectral normalization can stabilize the training of the model. In the fault diagnosis section, fault diagnosis is performed through a convolutional neural network with coordinate attention (CNN-CA). Our experiments conducted on two bearing fault datasets for comparison demonstrate that the proposed method surpasses other comparative approaches in terms of the quality of data augmentation and the accuracy of fault diagnosis. It effectively addresses S&I fault diagnosis challenges. Full article

(This article belongs to the Topic Predictive Analytics and Fault Diagnosis of Machines with Machine Learning Techniques)

►▼ Show Figures

Figure 1

11 pages, 4219 KiB  

Open AccessProject Report

Tool Wear Monitoring System Using Seq2Seq

by Wang-Su Jeon and Sang-Yong Rhee

Machines 2024, 12(3), 169; https://doi.org/10.3390/machines12030169 - 01 Mar 2024

Viewed by 879

Abstract

The advancement of smart factories has brought about small quantity batch production. In multi-variety production, both materials and processing methods change constantly, resulting in irregular changes in the progression of tool wear, which is often affected by processing methods. This leads to changes [...] Read more.

The advancement of smart factories has brought about small quantity batch production. In multi-variety production, both materials and processing methods change constantly, resulting in irregular changes in the progression of tool wear, which is often affected by processing methods. This leads to changes in the timing of tool replacement, and failure to correctly determine this timing may result in substantial damage and financial loss. In this study, we sought to address the issue of incorrect timing for tool replacement by using a Seq2Seq model to predict tool wear. We also trained LSTM and GRU models to compare performance by using ${\mathrm{R}}^2$, mean absolute error (MAE), and mean squared error (MSE). The Seq2Seq model outperformed LSTM and GRU with an ${\mathrm{R}}^2$ of approximately 0.03~0.037 in step drill data, 0.540.57 in top metal data, and 0.16~0.45 in low metal data. Confirming that Seq2Seq exhibited the best performance, we established a real-time monitoring system to verify the prediction results obtained using the Seq2Seq model. It is anticipated that this monitoring system will help prevent accidents in advance. Full article

(This article belongs to the Topic Predictive Analytics and Fault Diagnosis of Machines with Machine Learning Techniques)

►▼ Show Figures

Figure 1

16 pages, 11415 KiB  

Open AccessArticle

Multi-Branch Line Fault Arc Detection Method Based on the Improved Northern Goshawk Optimization Adaptive Base Class LogitBoost Algorithm

by Xue Wang and Yu Zhao

Energies 2024, 17(4), 954; https://doi.org/10.3390/en17040954 - 19 Feb 2024

Viewed by 486

Abstract

In low-voltage AC distribution systems, when a series arc fault occurs in a branch with multiple loads operating in parallel, it will be significantly more difficult to identify. Existing arc fault detection methods make it difficult to effectively detect faults occurring in the [...] Read more.

In low-voltage AC distribution systems, when a series arc fault occurs in a branch with multiple loads operating in parallel, it will be significantly more difficult to identify. Existing arc fault detection methods make it difficult to effectively detect faults occurring in the lower-level branch. This study introduces a novel series arc fault detection approach based on the improved northern goshawk optimization adaptive base class LogitBoost (INGO-ABCLogitBoost) algorithm. Considering the zero-rest, intermittent, and random fluctuation and high-frequency features of the arc current, the zero-rest coefficient, discrete coefficient, harmonic amplitude, and wavelet entropy are proposed to establish the high-dimensional feature matrix of the arc current. The ReliefF feature selection algorithm is used to optimize feature quality and decrease feature dimensionality. Subsequently, the ABCLogitBoost fault detection model is proposed, with the INGO algorithm applied to optimize the model parameters, thus enhancing the model’s diagnostic capabilities. The efficacy of the proposed diagnostic model is validated through the construction of a multi-load arc simulation system. The simulation results show that the overall fault diagnosis accuracy of the proposed method reaches 99.01% and can effectively identify the fault load types, which helps to locate the fault location. Full article

(This article belongs to the Topic Predictive Analytics and Fault Diagnosis of Machines with Machine Learning Techniques)

►▼ Show Figures

Figure 1

16 pages, 7362 KiB  

Open AccessArticle

A Multi-Input Convolutional Neural Network Model for Electric Motor Mechanical Fault Classification Using Multiple Image Transformation and Merging Methods

by Insu Bae and Suan Lee

Machines 2024, 12(2), 105; https://doi.org/10.3390/machines12020105 - 02 Feb 2024

Viewed by 1105

Abstract

This paper addresses the critical issue of fault detection and prediction in electric motor machinery, a prevalent challenge in industrial applications. Faults in these machines, stemming from mechanical or electrical issues, often lead to performance degradation or malfunctions, manifesting as abnormal signals in [...] Read more.

This paper addresses the critical issue of fault detection and prediction in electric motor machinery, a prevalent challenge in industrial applications. Faults in these machines, stemming from mechanical or electrical issues, often lead to performance degradation or malfunctions, manifesting as abnormal signals in vibrations or currents. Our research focuses on enhancing the accuracy of fault classification in electric motor facilities, employing innovative image transformation methods—recurrence plots (RPs), the Gramian angular summation field (GASF), and the Gramian angular difference field (GADF)—in conjunction with a multi-input convolutional neural network (CNN) model. We conducted comprehensive experiments using datasets encompassing four types of machinery components: bearings, belts, shafts, and rotors. The results reveal that our multi-input CNN model exhibits exceptional performance in fault classification across all machinery types, significantly outperforming traditional single-input models. This study not only demonstrates the efficacy of advanced image transformation techniques in fault detection but also underscores the potential of multi-input CNN models in industrial fault diagnosis, paving the way for more reliable and efficient monitoring of electric motor machinery. Full article

(This article belongs to the Topic Predictive Analytics and Fault Diagnosis of Machines with Machine Learning Techniques)

►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

 

Error

Oops... you haven't selected anything for export.

Ok

clear

Displaying articles 1-6