sensors-logo

Journal Browser

Journal Browser

Sensors for Fault Detection and Condition Monitoring

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Fault Diagnosis & Sensors".

Deadline for manuscript submissions: 30 March 2024 | Viewed by 14966

Special Issue Editor

School of Mechanical Engineering (SMEC), Vellore Institute of Technology, Chennai 600127, India
Interests: fault diagnosis; machine learning; condition monitoring; sensors; deep learning

Special Issue Information

Dear Colleagues,

Industrial automation (Industry 4.0), along with recent developments in artificial intelligence, has played a significant role in the enhancement of technological advancements in modern society. Fault detection and diagnosis are essential for the elimination of production losses and safety hazards due to complex automated installations. The early detection of faults in machineries can help in reducing the wear and tear of internal components, thereby enhancing their useful lifetime and reliability. Additionally, the identification of specific fault types can assist service personnel equip for preventive maintenance. Hence, recently, fault diagnosis and detection have gained the attention of several researchers. Additionally, intelligent fault diagnosis techniques that deliver instantaneous results are the need of the hour. Fault detection and diagnostic techniques involve the consumption of high volumes of data from sensors. Several types of sensors, such as piezoelectric, temperature, pressure, force, acoustic, etc., have been adopted, along with machine learning and deep learning techniques utilized to identify the health condition of machinery. However, certain challenges, such as data augmentation (deep learning), multifault diagnosis, machine learning algorithms for small datasets, data and sensor fusion, interpretation of deep learning algorithms and feature representation, still persist.

This Special Issue aims to highlight various sensors and techniques adopted for performing intelligent fault diagnosis and detection in machineries. Furthermore, innovations in fault feature extraction, feature selection strategies and the development of novel machine learning algorithms aiming for higher accuracy and minimal computational efforts are appreciable. Contributors are welcome to submit review/original articles addressing (but not limited to) the topics in the list of keywords found below.

  • sensor vibration/sound/force/AE;
  • machine learning /deep learning;
  • fault detection/fault diagnosis/prognosis;
  • oil analysis using sensors;
  • low-cost sensors for fault diagnosis;
  • wavelets/fractals applied to fault diagnosis;
  • FD of mechanical components, such as bearings, gears, belts, etc.;
  • FD of automobile components, such as engines, brakes, clutches, etc.;
  • FD of energy systems, such as wind turbine, photo voltaic module, etc.

Prof. Dr. Sugumaran Vaithiyanathan
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (10 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

22 pages, 2826 KiB  
Article
State Evaluation of Self-Powered Wireless Sensors Based on a Fuzzy Comprehensive Evaluation Model
by Suqin Xiong, Qiuyang Li, Aichao Yang, Liang Zhu, Peng Li, Kaiwen Xue and Jin Yang
Sensors 2023, 23(22), 9267; https://doi.org/10.3390/s23229267 - 18 Nov 2023
Viewed by 625
Abstract
The energy harvesters used in self-powered wireless sensing technology, which has the potential to completely solve the power supply problem of the sensing nodes from the source, usually require mechanical movement or operate in harsh environments, resulting in a significant reduction in device [...] Read more.
The energy harvesters used in self-powered wireless sensing technology, which has the potential to completely solve the power supply problem of the sensing nodes from the source, usually require mechanical movement or operate in harsh environments, resulting in a significant reduction in device lifespan and reliability. Therefore, the influencing factors and failure mechanisms of the operating status of self-powered wireless sensors were analyzed, and an innovative evaluation index system was proposed, which includes 4 primary indexes and 13 secondary indexes, including energy harvesters, energy management circuits, wireless communication units, and sensors. Next, the weights obtained from the subjective analytic hierarchy process (AHP) and objective CRITIC weight method were fused to obtain the weights of each index. A self-powered sensor evaluation scheme (FE-SPS) based on fuzzy comprehensive evaluation was implemented by constructing a fuzzy evaluation model. The advantage of this scheme is that it can determine the current health status of the system based on its output characteristics. Finally, taking vibration energy as an example, the operational status of the self-powered wireless sensors after 200 h of operation was comprehensively evaluated. The experimental results show that the test self-powered wireless sensor had the highest score of “normal”, which is 0.4847, so the evaluation result was “normal”. In this article, a reliability evaluation strategy for self-powered wireless sensor was constructed to ensure the reliable operation of self-powered wireless sensors. Full article
(This article belongs to the Special Issue Sensors for Fault Detection and Condition Monitoring)
Show Figures

Figure 1

18 pages, 4266 KiB  
Article
Detection of Failures in Metal Oxide Surge Arresters Using Frequency Response Analysis
by Tiago Goncalves Zacarias, Rafael Martins, Carlos Eduardo Xavier, Julio Cezar Oliveira Castioni, Wilson Cesar Sant’Ana, Germano Lambert-Torres, Bruno Reno Gama, Isac Antonio dos Santos Areias, Erik Leandro Bonaldi and Frederico De Oliveira Assuncao
Sensors 2023, 23(12), 5633; https://doi.org/10.3390/s23125633 - 16 Jun 2023
Cited by 2 | Viewed by 990
Abstract
This work presents an innovative application of Frequency Response Analysis (FRA) in order to detect early degradation of Metal Oxide Surge Arresters (MOSAs). This technique has been widely used in power transformers, but has never been applied to MOSAs. It consists in comparisons [...] Read more.
This work presents an innovative application of Frequency Response Analysis (FRA) in order to detect early degradation of Metal Oxide Surge Arresters (MOSAs). This technique has been widely used in power transformers, but has never been applied to MOSAs. It consists in comparisons of spectra, measured at different instants of the lifetime of the arrester. Differences between these spectra are an indicator that some electrical properties of the arrester have changed. An incremental deterioration test has been performed on arrester samples (with controlled circulation of leakage current, which increases the energy dissipation over the device), and the FRA spectra correctly identified the progression of damage. Although preliminary, the FRA results seemed promising, and it is expected that this technology could be used as another diagnostic tool for arresters. Full article
(This article belongs to the Special Issue Sensors for Fault Detection and Condition Monitoring)
Show Figures

Figure 1

24 pages, 5776 KiB  
Article
Intelligent Bearing Fault Diagnosis Based on Feature Fusion of One-Dimensional Dilated CNN and Multi-Domain Signal Processing
by Kaitai Dong and Ashkan Lotfipoor
Sensors 2023, 23(12), 5607; https://doi.org/10.3390/s23125607 - 15 Jun 2023
Cited by 5 | Viewed by 1174
Abstract
Finding relevant features that can represent different types of faults under a noisy environment is the key to practical applications of intelligent fault diagnosis. However, high classification accuracy cannot be achieved with only a few simple empirical features, and advanced feature engineering and [...] Read more.
Finding relevant features that can represent different types of faults under a noisy environment is the key to practical applications of intelligent fault diagnosis. However, high classification accuracy cannot be achieved with only a few simple empirical features, and advanced feature engineering and modelling necessitate extensive specialised knowledge, resulting in restricted widespread use. This paper has proposed a novel and efficient fusion method, named MD-1d-DCNN, that combines statistical features from multiple domains and adaptive features retrieved using a one-dimensional dilated convolutional neural network. Moreover, signal processing techniques are utilised to uncover statistical features and realise the general fault information. To offset the negative influence of noise in signals and achieve high accuracy of fault diagnosis in noisy settings, 1d-DCNN is adopted to extract more dispersed and intrinsic fault-associated features, while also preventing the model from overfitting. In the end, fault classification based on fusion features is accomplished by the usage of fully connected layers. Two bearing datasets containing varying amounts of noise are used to verify the effectiveness and robustness of the suggested approach. The experimental results demonstrate MD-1d-DCNN’s superior anti-noise capability. When compared to other benchmark models, the proposed method performs better at all noise levels. Full article
(This article belongs to the Special Issue Sensors for Fault Detection and Condition Monitoring)
Show Figures

Figure 1

14 pages, 5094 KiB  
Article
Numerical Approach and Verification Method for Improving the Sensitivity of Ferrous Particle Sensors with a Permanent Magnet
by Sung-Ho Hong
Sensors 2023, 23(12), 5381; https://doi.org/10.3390/s23125381 - 06 Jun 2023
Cited by 1 | Viewed by 785
Abstract
This study aimed to improve the sensitivity of ferrous particle sensors used in various mechanical systems such as engines to detect abnormalities by measuring the number of ferrous wear particles generated by metal-to-metal contact. Existing sensors collect ferrous particles using a permanent magnet. [...] Read more.
This study aimed to improve the sensitivity of ferrous particle sensors used in various mechanical systems such as engines to detect abnormalities by measuring the number of ferrous wear particles generated by metal-to-metal contact. Existing sensors collect ferrous particles using a permanent magnet. However, their ability to detect abnormalities is limited because they only measure the number of ferrous particles collected on the top of the sensor. This study provides a design strategy to boost the sensitivity of an existing sensor using a multi-physics analysis method, and a practical numerical method was recommended to assess the sensitivity of the enhanced sensor. The sensor’s maximum magnetic flux density was increased by around 210% compared to the original sensor by changing the core’s form. In addition, in the numerical evaluation of the sensitivity of the sensor, the suggested sensor model has improved sensitivity. This study is important because it offers a numerical model and verification technique that may be used to enhance the functionality of a ferrous particle sensor that uses a permanent magnet. Full article
(This article belongs to the Special Issue Sensors for Fault Detection and Condition Monitoring)
Show Figures

Figure 1

22 pages, 7605 KiB  
Article
Research on Rolling Bearing Fault Diagnosis Based on Digital Twin Data and Improved ConvNext
by Chao Zhang, Feifan Qin, Wentao Zhao, Jianjun Li and Tongtong Liu
Sensors 2023, 23(11), 5334; https://doi.org/10.3390/s23115334 - 05 Jun 2023
Cited by 4 | Viewed by 2010
Abstract
This article introduces a novel framework for diagnosing faults in rolling bearings. The framework combines digital twin data, transfer learning theory, and an enhanced ConvNext deep learning network model. Its purpose is to address the challenges posed by the limited actual fault data [...] Read more.
This article introduces a novel framework for diagnosing faults in rolling bearings. The framework combines digital twin data, transfer learning theory, and an enhanced ConvNext deep learning network model. Its purpose is to address the challenges posed by the limited actual fault data density and inadequate result accuracy in existing research on the detection of rolling bearing faults in rotating mechanical equipment. To begin with, the operational rolling bearing is represented in the digital realm through the utilization of a digital twin model. The simulation data produced by this twin model replace traditional experimental data, effectively creating a substantial volume of well-balanced simulated datasets. Next, improvements are made to the ConvNext network by incorporating an unparameterized attention module called the Similarity Attention Module (SimAM) and an efficient channel attention feature referred to as the Efficient Channel Attention Network (ECA). These enhancements serve to augment the network’s capability for extracting features. Subsequently, the enhanced network model is trained using the source domain dataset. Simultaneously, the trained model is transferred to the target domain bearing using transfer learning techniques. This transfer learning process enables the accurate fault diagnosis of the main bearing to be achieved. Finally, the proposed method’s feasibility is validated, and a comparative analysis is conducted in comparison with similar approaches. The comparative study demonstrates that the proposed method effectively addresses the issue of low mechanical equipment fault data density, leading to improved accuracy in fault detection and classification, along with a certain level of robustness. Full article
(This article belongs to the Special Issue Sensors for Fault Detection and Condition Monitoring)
Show Figures

Figure 1

23 pages, 4011 KiB  
Article
Enhancing Tool Wear Prediction Accuracy Using Walsh–Hadamard Transform, DCGAN and Dragonfly Algorithm-Based Feature Selection
by Milind Shah, Himanshu Borade, Vedant Sanghavi, Anshuman Purohit, Vishal Wankhede and Vinay Vakharia
Sensors 2023, 23(8), 3833; https://doi.org/10.3390/s23083833 - 08 Apr 2023
Cited by 10 | Viewed by 2165
Abstract
Tool wear is an important concern in the manufacturing sector that leads to quality loss, lower productivity, and increased downtime. In recent years, there has been a rise in the popularity of implementing TCM systems using various signal processing methods and machine learning [...] Read more.
Tool wear is an important concern in the manufacturing sector that leads to quality loss, lower productivity, and increased downtime. In recent years, there has been a rise in the popularity of implementing TCM systems using various signal processing methods and machine learning algorithms. In the present paper, the authors propose a TCM system that incorporates the Walsh–Hadamard transform for signal processing, DCGAN aims to circumvent the issue of the availability of limited experimental dataset, and the exploration of three machine learning models: support vector regression, gradient boosting regression, and recurrent neural network for tool wear prediction. The mean absolute error, mean square error and root mean square error are used to assess the prediction errors from three machine learning models. To identify these relevant features, three metaheuristic optimization feature selection algorithms, Dragonfly, Harris hawk, and Genetic algorithms, were explored, and prediction results were compared. The results show that the feature selected through Dragonfly algorithms exhibited the least MSE (0.03), RMSE (0.17), and MAE (0.14) with a recurrent neural network model. By identifying the tool wear patterns and predicting when maintenance is required, the proposed methodology could help manufacturing companies save money on repairs and replacements, as well as reduce overall production costs by minimizing downtime. Full article
(This article belongs to the Special Issue Sensors for Fault Detection and Condition Monitoring)
Show Figures

Figure 1

25 pages, 10127 KiB  
Article
A Condition Evaluation Simplified Method for Traction Converter Power Module Based on Operating Interval Segmentation
by Lei Wang, Mingchao Zhou, Zhonghao Dongye, Yanbei Sha and Jingcao Chen
Sensors 2023, 23(5), 2537; https://doi.org/10.3390/s23052537 - 24 Feb 2023
Viewed by 1346
Abstract
In the actual operation of urban rail vehicles, it is essential to evaluate the condition of the traction converter IGBT modules. Considering the fixed line and the similarity of operation conditions between adjacent stations, this paper proposes an efficient and accurate simplified simulation [...] Read more.
In the actual operation of urban rail vehicles, it is essential to evaluate the condition of the traction converter IGBT modules. Considering the fixed line and the similarity of operation conditions between adjacent stations, this paper proposes an efficient and accurate simplified simulation method to evaluate IGBT conditions based on operating interval segmentation (OIS). Firstly, this paper proposes the framework for a condition evaluation method by segmenting operating intervals based on the similarity of average power loss between neighboring stations. The framework makes it possible to reduce the number of simulations to shorten the simulation time while ensuring the state trend estimation accuracy. Secondly, this paper proposes a basic interval segmentation model that uses the operating conditions as inputs to implement the segmentation of the line and is able to simplify the operation conditions of entire line. Finally, the simulation and analysis of the temperature and stress fields of IGBT modules based on segmented intervals completes the IGBT module condition evaluation and realizes the combination of lifetime calculation with actual operating conditions and internal stresses. The validity of the method is verified by comparing the interval segmentation simulation with actual test results. The results show that the method can effectively characterize the temperature and stress trends of traction converter IGBT modules in the whole line, which could support the fatigue mechanism and lifetime assessment reliability study of IGBT modules. Full article
(This article belongs to the Special Issue Sensors for Fault Detection and Condition Monitoring)
Show Figures

Figure 1

18 pages, 2405 KiB  
Article
Tire Condition Monitoring Using Transfer Learning-Based Deep Neural Network Approach
by Vinod Vasan, Naveen Venkatesh Sridharan, Anoop Prabhakaranpillai Sreelatha and Sugumaran Vaithiyanathan
Sensors 2023, 23(4), 2177; https://doi.org/10.3390/s23042177 - 15 Feb 2023
Cited by 2 | Viewed by 1925
Abstract
Monitoring tire condition plays a deterministic role in the overall safety and economy of an automobile. The tire condition monitoring system (TCMS) alerts the driver of the vehicle if the inflation pressure of a particular tire decreases below a specific value. Owing to [...] Read more.
Monitoring tire condition plays a deterministic role in the overall safety and economy of an automobile. The tire condition monitoring system (TCMS) alerts the driver of the vehicle if the inflation pressure of a particular tire decreases below a specific value. Owing to the high costs involved in realizing this system, most vehicles do not feature this technology as a standard. With highly robust and accurate sensors making their way into an increasing number of applications, obtaining signals of varied types (especially vibration signals) is becoming easier and more modularized. In addition, feature-based machine learning techniques that enable accurate responses to varied input conditions have sought greater scientific attention. However, deep learning is gradually finding greater applications pertaining to condition monitoring. One approach of deep learning is presented in this paper, which instantaneously monitors the vehicle tire condition. For this purpose, vibration signals were obtained through the rotation of the tire under different inflation pressure conditions using a low-cost microelectromechanical system (MEMS) accelerometer. Full article
(This article belongs to the Special Issue Sensors for Fault Detection and Condition Monitoring)
Show Figures

Figure 1

13 pages, 3565 KiB  
Article
Stable and Accurate Estimation of SOC Using eXogenous Kalman Filter for Lithium-Ion Batteries
by Qizhe Lin, Xiaoqi Li, Bicheng Tu, Junwei Cao, Ming Zhang and Jiawei Xiang
Sensors 2023, 23(1), 467; https://doi.org/10.3390/s23010467 - 01 Jan 2023
Cited by 11 | Viewed by 1924
Abstract
The state of charge (SOC) for a lithium-ion battery is a key index closely related to battery performance and safety with respect to the power supply system of electric vehicles. The Kalman filter (KF) or extended KF (EKF) is normally employed to estimate [...] Read more.
The state of charge (SOC) for a lithium-ion battery is a key index closely related to battery performance and safety with respect to the power supply system of electric vehicles. The Kalman filter (KF) or extended KF (EKF) is normally employed to estimate SOC in association with the relatively simple and fast second-order resistor-capacitor (RC) equivalent circuit model for SOC estimations. To improve the stability of SOC estimation, a two-stage method is developed by combining the second-order RC equivalent circuit model and the eXogenous Kalman filter (XKF) to estimate the SOC of a lithium-ion battery. First, approximate SOC estimation values are observed with relatively poor accuracy by a stable observer without considering parameter uncertainty. Second, the poor accuracy SOC results are further fed into XKF to obtain relative stable and accurate SOC estimation values. Experiments demonstrate that the SOC estimation results of the present method are superior to those of the commonly used EKF method. It is expected that the present two-stage XKF method will be useful for the stable and accurate estimation of SOC in the power supply system of electric vehicles. Full article
(This article belongs to the Special Issue Sensors for Fault Detection and Condition Monitoring)
Show Figures

Figure 1

Review

Jump to: Research

26 pages, 2244 KiB  
Review
A Bibliometric and Comprehensive Review on Condition Monitoring of Metal Oxide Surge Arresters
by Tiago Goncalves Zacarias and Wilson Cesar Sant’Ana
Sensors 2024, 24(1), 235; https://doi.org/10.3390/s24010235 - 31 Dec 2023
Viewed by 766
Abstract
This paper presents a literature review on the subject of Condition-Based Maintenance of surge arresters. Both a bibliometric analysis and traditional comprehensive research are presented. The bibliometric analysis is useful for obtaining insights about the literature. It quantitatively highlights relationships between journals, authors [...] Read more.
This paper presents a literature review on the subject of Condition-Based Maintenance of surge arresters. Both a bibliometric analysis and traditional comprehensive research are presented. The bibliometric analysis is useful for obtaining insights about the literature. It quantitatively highlights relationships between journals, authors and keywords (related to the monitoring methods) and reveals future trends for research based on the timeline of the keywords. The traditional comprehensive literature review is also presented. It summarizes the methods, their advantages and disadvantages and also points to some known measurement issues of the methods. Both online (leakage current, harmonic components, temperature, partial discharges, power loss and the counting of discharges) and offline (reference voltage, residual voltage, insulation resistance, polarization/depolarization, return voltage, microscopy, spectrometry, X-ray, RUS and the recent application of FRA) methods have been qualitatively analyzed. Full article
(This article belongs to the Special Issue Sensors for Fault Detection and Condition Monitoring)
Show Figures

Figure 1

Back to TopTop