Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.8
3.9
Journals
Sensors
Special Issues
AI-Assisted Condition Monitoring and Fault Diagnosis
sensors-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

AI-Assisted Condition Monitoring and Fault Diagnosis

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

Deadline for manuscript submissions: 30 June 2024 | Viewed by 19682

Special Issue Editors

Prof. Dr. Pavlos Lazaridis

E-Mail Website
Guest Editor
Department of Engineering and Technology, School of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UK
Interests: partial discharges; condition monitoring; sensors; antennas; propagation; AI-based detection techniques; fault diagnosis
Special Issues, Collections and Topics in MDPI journals
Dr. Euler Cássio Tavares De Macêdo

E-Mail Website
Guest Editor
Department of Electrical Engineering, Federal University of Paraíba, Campus I - Cidade Universitária, Joao Pessoa 58051-970, PB, Brazil
Interests: solar power; partial discharges; condition monitoring; sensors; AI-based detection techniques; Wireless Sensor Networks; Lithium-ion batteries
Dr. Christos Tachtatzis

E-Mail Website
Guest Editor
Department of Electronic and Electrical Engineering, University of Strathclyde, 16 Richmond Street, Glasgow G1 1XQ, UK
Interests: machine learning; partial discharge monitoring; wireless technologies; data analytics
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Condition monitoring is necessary for the health diagnosis of expensive and safety-critical industrial assets, as well as for the correct implementation of preventive maintenance schemes. The assets required to be monitored include power transformers, high-voltage cables, gas-insulated switchgear, coaxial cables, and other power lines, and rotating machines. Recently there has been a rapid development of radio electromagnetic wave sensors for detecting and localizing partial discharges. Based on signals and data derived from sensors and arrays of sensors, condition monitoring technologies provide information regarding the status and future evolution of the health condition of machinery and plants, which is of capital importance for the safety and reliability of industrial equipment. Artificial Intelligence (AI) and Machine Learning (ML) techniques may be used advantageously for the early detection and localization of faults which, if left untreated, could lead to catastrophic failures.

The aim of this Special Issue is to attract high-quality, innovative, and original research works and survey articles related but not restricted to the already mentioned research fields, including the following topics:

  • Sensor technology;
  • Partial discharge detection and monitoring;
  • Condition monitoring systems;
  • Sensor integration for condition monitoring;
  • Artificial intelligence (AI), machine learning (ML), fingerprinting, and pattern recognition techniques;
  • AI-based techniques used in the detection and localization of faults;
  • Electronic measurement systems for industrial environments;
  • Signal processing techniques, signal conditioning, and front-end analog electronics;
  • Artificial intelligence, machine learning, and pattern recognition;
  • Sensor networks and arrays of sensors;

Papers should be of high quality and should not have been submitted or published elsewhere. However, extended versions of conference papers that show significant improvement can be considered for review.

Prof. Dr. Pavlos Lazaridis
Dr. Euler Cássio Tavares De Macêdo
Dr. Christos Tachtatzis
Guest Editors

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.

Keywords

  • sensors
  • condition monitoring
  • fault diagnosis
  • industrial systems
  • partial discharge
  • artificial intelligence
  • machine learning
  • rotating machines
  • power transformers
  • power lines

Published Papers (20 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

20 pages, 5147 KiB  
Article
Anomaly Detection for Asynchronous Multivariate Time Series of Nuclear Power Plants Using a Temporal-Spatial Transformer
by Shuang Yi, Sheng Zheng, Senquan Yang, Guangrong Zhou and Jiajun Cai
Sensors 2024, 24(9), 2845; https://0-doi-org.brum.beds.ac.uk/10.3390/s24092845 - 29 Apr 2024
Abstract
Industrial process monitoring is a critical application of multivariate time-series (MTS) anomaly detection, especially crucial for safety-critical systems such as nuclear power plants (NPPs). However, some current data-driven process monitoring approaches may not fully capitalize on the temporal-spatial correlations inherent in operational MTS [...] Read more.
Industrial process monitoring is a critical application of multivariate time-series (MTS) anomaly detection, especially crucial for safety-critical systems such as nuclear power plants (NPPs). However, some current data-driven process monitoring approaches may not fully capitalize on the temporal-spatial correlations inherent in operational MTS data. Particularly, asynchronous time-lagged correlations may exist among variables in actual NPPs, which further complicates this challenge. In this work, a reconstruction-based MTS anomaly detection approach based on a temporal-spatial transformer is proposed. It employs a two-stage temporal-spatial attention mechanism combined with a multi-scale strategy to learn the dependencies within normal operational data at various scales, thereby facilitating the extraction of temporal-spatial correlations from asynchronous MTS. Experiments on simulated datasets and real NPP datasets demonstrate that the proposed model possesses stronger feature learning capabilities, as evidenced by its improved performance in signal reconstruction and anomaly detection for asynchronous MTS data. Moreover, the proposed TS-Trans model enables earlier detection of anomalous events, which holds significant importance for enhancing operational safety and reducing potential losses in NPPs. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
14 pages, 730 KiB  
Article
Robust Cooperative Fault-Tolerant Control for Uncertain Multi-Agent Systems Subject to Actuator Faults
by Jiantao Shi, Xiang Chen, Shuangqing Xing, Anning Liu and Chuang Chen
Sensors 2024, 24(8), 2651; https://0-doi-org.brum.beds.ac.uk/10.3390/s24082651 - 21 Apr 2024
Viewed by 341
Abstract
This article investigates the robust cooperative fault-tolerant control problem of multi-agent systems subject to mismatched uncertainties and actuator faults. During the design process of the intermediate variable estimator, there is no need to satisfy fault estimation matching conditions, and this overcomes a crucial [...] Read more.
This article investigates the robust cooperative fault-tolerant control problem of multi-agent systems subject to mismatched uncertainties and actuator faults. During the design process of the intermediate variable estimator, there is no need to satisfy fault estimation matching conditions, and this overcomes a crucial constraint of traditional observers and estimators. The feedback term of the designed estimator contains the centralized estimation errors and the distributed estimation errors of the agent, and this further improves the design freedom of the proposed estimator. A novel fault-tolerant control protocol is designed based on the fault estimation information. In this work, the bounds of the fault and its derivatives are unknown, and the considered method is applicable to both directed and undirected multi-agent systems. Furthermore, the parameters of the estimator are determined through the resolution of a linear matrix inequality (LMI), which is decoupled by employing coordinate transformation and Schur decomposition. Lastly, a numerical simulation result is used to demonstrate the effectiveness of the proposed method. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

13 pages, 3834 KiB  
Article
Tool Condition Monitoring Using Machine Tool Spindle Current and Long Short-Term Memory Neural Network Model Analysis
by Niko Turšič and Simon Klančnik
Sensors 2024, 24(8), 2490; https://0-doi-org.brum.beds.ac.uk/10.3390/s24082490 - 12 Apr 2024
Viewed by 322
Abstract
In cutting processes, tool condition affects the quality of the manufactured parts. As such, an essential component to prevent unplanned downtime and to assure machining quality is having information about the state of the cutting tool. The primary function of it is to [...] Read more.
In cutting processes, tool condition affects the quality of the manufactured parts. As such, an essential component to prevent unplanned downtime and to assure machining quality is having information about the state of the cutting tool. The primary function of it is to alert the operator that the tool has reached or is reaching a level of wear beyond which behaviour is unreliable. In this paper, the tool condition is being monitored by analysing the electric current on the main spindle via an artificial intelligence model utilising an LSTM neural network. In the current study, the tool is monitored while working on a cylindrical raw piece made of AA6013 aluminium alloy with a custom polycrystalline diamond tool for the purposes of monitoring the wear of these tools. Spindle current characteristics were obtained using external measuring equipment to not influence the operation of the machine included in a larger production line. As a novel approach, an artificial intelligence model based on an LSTM neural network is utilised for the analysis of the spindle current obtained during a manufacturing cycle and assessing the tool wear range in real time. The neural network was designed and trained to notice significant characteristics of the captured current signal. The conducted research serves as a proof of concept for the use of an LSTM neural network-based model as a method of monitoring the condition of cutting tools. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

16 pages, 8486 KiB  
Article
Convolutional Neural Network with Attention Mechanism and Visual Vibration Signal Analysis for Bearing Fault Diagnosis
by Qing Zhang, Xiaohan Wei, Ye Wang and Chenggang Hou
Sensors 2024, 24(6), 1831; https://0-doi-org.brum.beds.ac.uk/10.3390/s24061831 - 13 Mar 2024
Viewed by 626
Abstract
Bearings, as widely employed supporting components, frequently work in challenging working conditions, leading to diverse fault types. Traditional methods for diagnosing bearing faults primarily center on time–frequency analysis, but this often requires expert experience for accurate fault identification. Conversely, intelligent fault recognition and [...] Read more.
Bearings, as widely employed supporting components, frequently work in challenging working conditions, leading to diverse fault types. Traditional methods for diagnosing bearing faults primarily center on time–frequency analysis, but this often requires expert experience for accurate fault identification. Conversely, intelligent fault recognition and classification methods frequently lack interpretability. To address this challenge, this paper introduces a convolutional neural network with an attention mechanism method, denoted as CBAM-CNN, for bearing fault diagnosis. This approach incorporates an attention mechanism, creating a Convolutional Block Attention Module (CBAM), to enhance the fault feature extraction capability of the network in the time–frequency domain. In addition, the proposed method integrates a weight visualization module known as the Gradient-Weighted Class Activation Map (Grad-CAM), enhancing the interpretability of the convolutional neural network by generating visual heatmaps on fault time–frequency graphs. The experimental results demonstrate that utilizing the dataset employed in this study, the CBAM-CNN achieves an accuracy of 99.81%, outperforming the Base-CNN with enhanced convergence speed. Furthermore, the analysis of attention weights reveals that this method exhibits distinct focus of attention under various fault types and degrees. The interpretability experiments indicate that the CBAM module balances the weight allocation, emphasizing signal frequency distribution rather than amplitude distribution. Consequently, this mitigates the impact of the signal amplitude on the diagnostic model to some extent. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

18 pages, 4372 KiB  
Article
Gas Turbine Anomaly Detection under Time-Varying Operation Conditions Based on Spectra Alignment and Self-Adaptive Normalization
by Dongyan Miao, Kun Feng, Yuan Xiao, Zhouzheng Li and Jinji Gao
Sensors 2024, 24(3), 941; https://0-doi-org.brum.beds.ac.uk/10.3390/s24030941 - 31 Jan 2024
Viewed by 530
Abstract
Gas turbine vibration data may exhibit considerable differences under time-varying conditions, which poses challenges for neural network anomaly detection. We first propose a framework for a gas turbine vibration frequency spectra process under time-varying operation conditions, assisting neural networks’ ability to capture weak [...] Read more.
Gas turbine vibration data may exhibit considerable differences under time-varying conditions, which poses challenges for neural network anomaly detection. We first propose a framework for a gas turbine vibration frequency spectra process under time-varying operation conditions, assisting neural networks’ ability to capture weak information. The framework involves scaling spectra for aligning all frequency components related to rotational speed and normalizing frequency amplitude in a self-adaptive way. Degressive beta variational autoencoder is employed for learning spectra characteristics and anomaly detection, while a multi-category anomaly index is proposed to accommodate various operating conditions. Finally, a dataset of blade Foreign Object Damage (FOD) fault occurring under time-varying operating conditions was used to validate the framework and anomaly detection. The results demonstrate that the proposed method can effectively reduce the spectra differences under time-varying conditions, and also detect FOD fault during operation, which are challenging to identify using conventional methods. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

25 pages, 7722 KiB  
Article
Machine Learning for the Detection and Diagnosis of Anomalies in Applications Driven by Electric Motors
by Fábio Ferraz Júnior, Roseli Aparecida Francelin Romero and Sheng-Jen Hsieh
Sensors 2023, 23(24), 9725; https://0-doi-org.brum.beds.ac.uk/10.3390/s23249725 - 09 Dec 2023
Cited by 1 | Viewed by 939
Abstract
Manufacturing systems are becoming increasingly flexible, necessitating the adoption of new technologies that allow adaptations to a turbulent and complex modern market. Consequently, modern concepts of production systems require horizontal and vertical integration, extending across value networks and within a factory or production [...] Read more.
Manufacturing systems are becoming increasingly flexible, necessitating the adoption of new technologies that allow adaptations to a turbulent and complex modern market. Consequently, modern concepts of production systems require horizontal and vertical integration, extending across value networks and within a factory or production shop. The integration of these environments enables the acquisition of a substantial amount of data containing information pertaining to production, processes, and equipment located on the shop floor. When these data and information are processed and analyzed, they have the potential to reveal valuable insights and knowledge about the manufacturing systems, offering interpretive outcomes for strategic decision making. One of the opportunities presented in this context includes the implementation of predictive maintenance (PdM). However, industrial adoption of PdM is still relatively low. In this paper, the aim is to propose a methodology for selecting the main attributes (variables) to be considered in the instrumentation setup of rotating machines driven by electric motors to decrease the associated costs and the time spent defining them. For this, the most well-known data science and machine learning algorithms are investigated to choose the one most adequate for this task. For the experiments, different testing scenarios were proposed to detect the different possible types of anomalies, such as uncoupled, overloaded, unbalanced, misaligned, and normal. The results obtained show how these algorithms can be effective in classifying the different types of anomalies and that the two models that presented the best accuracy values were k-nearest neighbor and multi-layer perceptron. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

17 pages, 7121 KiB  
Article
Dynamic Condition Adversarial Adaptation for Fault Diagnosis of Wind Turbine Gearbox
by Hongpeng Zhang, Xinran Wang, Cunyou Zhang, Wei Li, Jizhe Wang, Guobin Li and Chenzhao Bai
Sensors 2023, 23(23), 9368; https://0-doi-org.brum.beds.ac.uk/10.3390/s23239368 - 23 Nov 2023
Viewed by 653
Abstract
While deep learning has found widespread utility in gearbox fault diagnosis, its direct application to wind turbine gearboxes encounters significant hurdles. Disparities in data distribution across a spectrum of operating conditions for wind turbines result in a marked decrease in diagnostic accuracy. In [...] Read more.
While deep learning has found widespread utility in gearbox fault diagnosis, its direct application to wind turbine gearboxes encounters significant hurdles. Disparities in data distribution across a spectrum of operating conditions for wind turbines result in a marked decrease in diagnostic accuracy. In response, this study introduces a tailored dynamic conditional adversarial domain adaptation model for fault diagnosis in wind turbine gearboxes amidst cross-condition scenarios. The model adeptly adjusts the importance of aligning marginal and conditional distributions using distance metric factors. Information entropy parameters are also incorporated to assess individual sample transferability, prioritizing highly transferable samples during domain alignment. The amalgamation of these dynamic factors empowers the approach to maintain stability across varied data distributions. Comprehensive experiments on both gear and bearing data validate the method’s efficacy in cross-condition fault diagnosis. Comparative outcomes demonstrate that, when contrasted with four advanced transfer learning techniques, the dynamic conditional adversarial domain adaptation model attains superior accuracy and stability in multi-transfer tasks, making it notably suitable for diagnosing wind turbine gearbox faults. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

20 pages, 1605 KiB  
Article
Time-Frequency Multi-Domain 1D Convolutional Neural Network with Channel-Spatial Attention for Noise-Robust Bearing Fault Diagnosis
by Yejin Kim and Young-Keun Kim
Sensors 2023, 23(23), 9311; https://0-doi-org.brum.beds.ac.uk/10.3390/s23239311 - 21 Nov 2023
Cited by 1 | Viewed by 1261
Abstract
This paper proposes a noise-robust and accurate bearing fault diagnosis model based on time-frequency multi-domain 1D convolutional neural networks (CNNs) with attention modules. The proposed model, referred to as the TF-MDA model, is designed for an accurate bearing fault classification model based on [...] Read more.
This paper proposes a noise-robust and accurate bearing fault diagnosis model based on time-frequency multi-domain 1D convolutional neural networks (CNNs) with attention modules. The proposed model, referred to as the TF-MDA model, is designed for an accurate bearing fault classification model based on vibration sensor signals that can be implemented at industry sites under a high-noise environment. Previous 1D CNN-based bearing diagnosis models are mostly based on either time domain vibration signals or frequency domain spectral signals. In contrast, our model has parallel 1D CNN modules that simultaneously extract features from both the time and frequency domains. These multi-domain features are then fused to capture comprehensive information on bearing fault signals. Additionally, physics-informed preprocessings are incorporated into the frequency-spectral signals to further improve the classification accuracy. Furthermore, a channel and spatial attention module is added to effectively enhance the noise-robustness by focusing more on the fault characteristic features. Experiments were conducted using public bearing datasets, and the results indicated that the proposed model outperformed similar diagnosis models on a range of noise levels ranging from −6 to 6 dB signal-to-noise ratio (SNR). Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

13 pages, 6706 KiB  
Article
The Practical Application of Bio-Inspired PMA for the Detection of Partial Discharges in High Voltage Equipment
by Josiel Cruz, Alexandre Serres, Raimundo Freire, Edson Costa, George Xavier, Adriano Oliveira, Vladimir Souza and Pavlos Lazaridis
Sensors 2023, 23(23), 9307; https://0-doi-org.brum.beds.ac.uk/10.3390/s23239307 - 21 Nov 2023
Viewed by 658
Abstract
In this paper, the practical application of a bio-inspired antenna for partial discharge (PD) detection in high voltage equipment was evaluated in order to validate the efficiency of using this technology for PD monitoring purposes. For this, PD measurements using the bio-inspired antenna [...] Read more.
In this paper, the practical application of a bio-inspired antenna for partial discharge (PD) detection in high voltage equipment was evaluated in order to validate the efficiency of using this technology for PD monitoring purposes. For this, PD measurements using the bio-inspired antenna were performed on operational 69 kV potential transformers (PT) in a real substation. After the field experiment, laboratory measurements using the IEC 60270 standard method and a bio-inspired antenna were performed, simultaneously, over the evaluated PT. The results obtained at the substation indicated suspicious frequencies of partial discharge activity in two out of three evaluated potential transformers, mainly for the frequencies of 461 MHz, 1366 MHz, 1550 MHz and 1960 MHz. During the laboratory tests, the presence of partial discharge activity over the suspicious potential transformers was confirmed with the detection of PD apparent charge levels above 20 pC. Finally, the frequency spectrum obtained from the PD signals detected by the bio-inspired antenna in the laboratory presented similar frequency values to those obtained during the practical application at the substation, making it a promising indicator for future defect classification studies using artificial intelligence. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

13 pages, 4792 KiB  
Article
Detection of Broken Rotor Bars in Cage Induction Motors Using Machine Learning Methods
by Lloyd Prosper Chisedzi and Mbika Muteba
Sensors 2023, 23(22), 9079; https://0-doi-org.brum.beds.ac.uk/10.3390/s23229079 - 09 Nov 2023
Cited by 1 | Viewed by 941
Abstract
In this paper, the performance of machine learning methods for squirrel cage induction motor broken rotor bar (BRB) fault detection is evaluated. Decision tree classification (DTC), artificial neural network (ANN), and deep learning (DL) methods are developed, applied, and studied to compare their [...] Read more.
In this paper, the performance of machine learning methods for squirrel cage induction motor broken rotor bar (BRB) fault detection is evaluated. Decision tree classification (DTC), artificial neural network (ANN), and deep learning (DL) methods are developed, applied, and studied to compare their performance in detecting broken rotor bar faults in squirrel cage induction motors. The training data were collected through experimental measurements. The BRB fault features were extracted from measured line-current signatures through a transformation from the time domain to the frequency domain using discrete Fourier Transform (DFT) of the frequency spectrum of the current signal. Eighty percent of the data were used for training the models, and twenty percent were used for testing. A confusion matrix was used to validate the models’ performance using accuracy, precision, recall, and f1-scores. The results evidence that the DTC is less load-dependent, and it has better accuracy and precision for both unloaded and loaded squirrel cage induction motors when compared with the DL and ANN methods. The DTC method achieved higher accuracy in the detection of the magnitudes of the twice-frequency sideband components induced in stator currents by BRB faults when compared with the DL and ANN methods. Although the detection accuracy and precision are higher for the loaded motor than the unloaded motor, the DTC method managed to also exhibit a high accuracy for the unloaded current when compared with the DL and ANN methods. The DTC is, therefore, a suitable candidate to detect broken rotor bar faults on trained data for lightly or thoroughly loaded squirrel cage induction motors using the characteristics of the measured line-current signature. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

21 pages, 5106 KiB  
Article
Tool Wear State Identification Based on SVM Optimized by the Improved Northern Goshawk Optimization
by Jiaqi Wang, Zhong Xiang, Xiao Cheng, Ji Zhou and Wenqi Li
Sensors 2023, 23(20), 8591; https://0-doi-org.brum.beds.ac.uk/10.3390/s23208591 - 20 Oct 2023
Cited by 4 | Viewed by 832
Abstract
Tool wear condition significantly influences equipment downtime and machining precision, necessitating the exploration of a more accurate tool wear state identification technique. In this paper, the wavelet packet thresholding denoising method is used to process the acquired multi-source signals and extract several signal [...] Read more.
Tool wear condition significantly influences equipment downtime and machining precision, necessitating the exploration of a more accurate tool wear state identification technique. In this paper, the wavelet packet thresholding denoising method is used to process the acquired multi-source signals and extract several signal features. The set of features most relevant to the tool wear state is screened out by the support vector machine recursive feature elimination (SVM-RFE). Utilizing these selected features, we propose a tool wear state identification model, which utilizes an improved northern goshawk optimization (INGO) algorithm to optimize the support vector machine (SVM), hereby referred to as INGO-SVM. The simulation tests reveal that INGO demonstrates superior convergence efficacy and stability. Furthermore, a milling wear experiment confirms that this approach outperforms five other methods in terms of recognition accuracy, achieving a remarkable accuracy rate of 97.9%. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

24 pages, 17540 KiB  
Article
Enhanced Fault Type Detection in Covered Conductors Using a Stacked Ensemble and Novel Algorithm Combination
by Ondřej Kabot, Lukáš Klein, Lukáš Prokop and Wojciech Walendziuk
Sensors 2023, 23(20), 8353; https://0-doi-org.brum.beds.ac.uk/10.3390/s23208353 - 10 Oct 2023
Viewed by 722
Abstract
This study introduces an innovative approach to enhance fault detection in XLPE-covered conductors used for power distribution systems. These covered conductors are widely utilized in forested areas (natural parks) to decrease the buffer zone and increase the reliability of the distribution network. Recognizing [...] Read more.
This study introduces an innovative approach to enhance fault detection in XLPE-covered conductors used for power distribution systems. These covered conductors are widely utilized in forested areas (natural parks) to decrease the buffer zone and increase the reliability of the distribution network. Recognizing the imperative need for precise fault detection in this context, this research employs an antenna-based method to detect a particular type of fault. The present research contains the classification of fault type detection, which was previously accomplished using a very expensive and challenging-to-install galvanic contact method, and only to a limited extent, which did not provide information about the fault type. Additionally, differentiating between types of faults in the contact method is much easier because information for each phase is available. The proposed method uses antennas and a classifier to effectively differentiate between fault types, ranging from single-phase to three-phase faults, as well as among different types of faults. This has never been done before. To bolster the accuracy, a stacking ensemble method involving the logistic regression is implemented. This approach not only advances precise fault detection but also encourages the broader adoption of covered conductors. This promises benefits such as a reduced buffer zone, improved distribution network reliability, and positive environmental outcomes through accident prevention and safe covered conductor utilization. Additionally, it is suggested that the fault type detection could lead to a decrease in false positives. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

20 pages, 3826 KiB  
Article
Industrial Product Quality Analysis Based on Online Machine Learning
by Yiming Yin, Ming Wan, Panfeng Xu, Rui Zhang, Yang Liu and Yan Song
Sensors 2023, 23(19), 8167; https://0-doi-org.brum.beds.ac.uk/10.3390/s23198167 - 29 Sep 2023
Viewed by 814
Abstract
During industrial production activities, industrial products serve as critical resources whose performance is subject to various external factors and usage conditions. To ensure uninterrupted production processes and to guarantee the safety of the production personnel, a real-time analysis of the industrial product quality [...] Read more.
During industrial production activities, industrial products serve as critical resources whose performance is subject to various external factors and usage conditions. To ensure uninterrupted production processes and to guarantee the safety of the production personnel, a real-time analysis of the industrial product quality and subsequent decision making are essential. Conventional detection methods have inherent limitations in meeting the real-time demands of processing large volumes of data and achieving high response speeds. For instance, the regular inspection and maintenance of cars can be time-consuming and labor-intensive if performed manually. Furthermore, monitoring the damage situation of bearings in real time through a manual inspection may lead to delays and may hinder production efficiency. Therefore, this paper presents online machine-learning-based methods to address these two practical problems and simulates them on various datasets to meet the requirements of efficiency and speed. Prior to being fed into the network for training, the data undergo identity parsing to transform them into easily identifiable streaming data. The training process demonstrates that online machine learning ensures timely model updates as small batches of data are sent to the network. The test results indicate that the online learning method exhibits highly stable and effective performance, optimizing the training process. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

13 pages, 3297 KiB  
Article
A New Dual-Input Deep Anomaly Detection Method for Early Faults Warning of Rolling Bearings
by Yuxiang Kang, Guo Chen, Hao Wang, Wenping Pan and Xunkai Wei
Sensors 2023, 23(18), 8013; https://0-doi-org.brum.beds.ac.uk/10.3390/s23188013 - 21 Sep 2023
Viewed by 878
Abstract
To address the problem of low fault diagnosis accuracy caused by insufficient fault samples of rolling bearings, a dual-input deep anomaly detection method with zero fault samples is proposed for early fault warning of rolling bearings. First, the main framework of dual-input feature [...] Read more.
To address the problem of low fault diagnosis accuracy caused by insufficient fault samples of rolling bearings, a dual-input deep anomaly detection method with zero fault samples is proposed for early fault warning of rolling bearings. First, the main framework of dual-input feature extraction based on a convolutional neural network (CNN) is established, and the two outputs of the main frame are subjected to the autoencoder structure. Then, the secondary feature extraction is performed. At the same time, the experience pool structure is introduced to improve the feature learning ability of the network. A new objective loss function is also proposed to learn the network parameters. Then, the vibration acceleration signal is preprocessed by wavelet to obtain multiple signals in different frequency bands, and the two signals in the high-frequency band are two-dimensionally encoded and used as the network input. Finally, the unsupervised learning of the model is completed on five sets of actual full-life rolling bearing fault data sets relying only on some samples in a normal state. The verification results show that the proposed method can realize earlier than the RMS, Kurtosis, and other features. The early fault warning and the accuracy rate of more than 98% show that the method is highly capable of early fault warning and anomaly detection. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

22 pages, 4451 KiB  
Article
A Low Complexity Rolling Bearing Diagnosis Technique Based on Machine Learning and Smart Preprocessing
by Ada Fort, Elia Landi, Marco Mugnaini and Valerio Vignoli
Sensors 2023, 23(17), 7546; https://0-doi-org.brum.beds.ac.uk/10.3390/s23177546 - 30 Aug 2023
Viewed by 828
Abstract
In this work, we present a diagnosis system for rolling bearings that leverages simultaneous measurements of vibrations and machine rotation speed. Our approach combines the robustness of simple time domain methods for fault detection with the potential of machine learning techniques for fault [...] Read more.
In this work, we present a diagnosis system for rolling bearings that leverages simultaneous measurements of vibrations and machine rotation speed. Our approach combines the robustness of simple time domain methods for fault detection with the potential of machine learning techniques for fault location. This research is based on a neural network classifier, which exploits a simple and novel preprocessing algorithm specifically designed for minimizing the dependency of the classifier performance on the machine working conditions, on the bearing model and on the acquisition system set-up. The overall diagnosis system is based on light algorithms with reduced complexity and hardware resource demand and is designed to be deployed in embedded electronics. The fault diagnosis system was trained using emulated data, exploiting an ad-hoc test bench thus avoiding the problem of generating enough data, achieving an overall classifier accuracy larger than 98%. Its noteworthy ability to generalize was proven by using data emulating different working conditions and acquisition set-ups and noise levels, obtaining in all the cases accuracies greater than 97%, thereby proving in this way that the proposed system can be applied in a wide spectrum of different applications. Finally, real data from an on-line database containing vibration signals obtained in a completely different scenario are used to demonstrate the distinctive capability of the proposed system to generalize. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

28 pages, 12244 KiB  
Article
A Convolutional Autoencoder Based Fault Diagnosis Method for a Hydraulic Solenoid Valve Considering Unknown Faults
by Seungjin Yoo, Joon Ha Jung, Jai-Kyung Lee, Sang Woo Shin and Dal Sik Jang
Sensors 2023, 23(16), 7249; https://0-doi-org.brum.beds.ac.uk/10.3390/s23167249 - 18 Aug 2023
Viewed by 1188
Abstract
The hydraulic solenoid valve is an essential electromechanical component used in various industries to control the flow rate, pressure, and direction of hydraulic fluid. However, these valves can fail due to factors like electrical issues, mechanical wear, contamination, seal failure, or improper assembly; [...] Read more.
The hydraulic solenoid valve is an essential electromechanical component used in various industries to control the flow rate, pressure, and direction of hydraulic fluid. However, these valves can fail due to factors like electrical issues, mechanical wear, contamination, seal failure, or improper assembly; these failures can lead to system downtime and safety risks. To address hydraulic solenoid valve failure, and its related impacts, this study aimed to develop a nondestructive diagnostic technology for rapid and accurate diagnosis of valve failures. The proposed approach is based on a data-driven model that uses voltage and current signals measured from normal and faulty valve samples. The algorithm utilizes a convolutional autoencoder and hypersphere-based clustering of the latent variables. This clustering approach helps to identify patterns and categorize the samples into distinct groups, normal and faulty. By clustering the data into groups of hyperspheres, the algorithm identifies the specific fault type, including both known and potentially new fault types. The proposed diagnostic model successfully achieved an accuracy rate of 98% in classifying the measurement data, which were augmented with white noise across seven distinct fault modes. This high accuracy demonstrates the effectiveness of the proposed diagnosis method for accurate and prompt identification of faults present in actual hydraulic solenoid valves. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

27 pages, 1600 KiB  
Article
Evaluating the Performance of Pre-Trained Convolutional Neural Network for Audio Classification on Embedded Systems for Anomaly Detection in Smart Cities
by Mimoun Lamrini, Mohamed Yassin Chkouri and Abdellah Touhafi
Sensors 2023, 23(13), 6227; https://0-doi-org.brum.beds.ac.uk/10.3390/s23136227 - 07 Jul 2023
Cited by 2 | Viewed by 1912
Abstract
Environmental Sound Recognition (ESR) plays a crucial role in smart cities by accurately categorizing audio using well-trained Machine Learning (ML) classifiers. This application is particularly valuable for cities that analyzed environmental sounds to gain insight and data. However, deploying deep learning (DL) models [...] Read more.
Environmental Sound Recognition (ESR) plays a crucial role in smart cities by accurately categorizing audio using well-trained Machine Learning (ML) classifiers. This application is particularly valuable for cities that analyzed environmental sounds to gain insight and data. However, deploying deep learning (DL) models on resource-constrained embedded devices, such as Raspberry Pi (RPi) or Tensor Processing Units (TPUs), poses challenges. In this work, an evaluation of an existing pre-trained model for deployment on Raspberry Pi (RPi) and TPU platforms other than a laptop is proposed. We explored the impact of the retraining parameters and compared the sound classification performance across three datasets: ESC-10, BDLib, and Urban Sound. Our results demonstrate the effectiveness of the pre-trained model for transfer learning in embedded systems. On laptops, the accuracy rates reached 96.6% for ESC-10, 100% for BDLib, and 99% for Urban Sound. On RPi, the accuracy rates were 96.4% for ESC-10, 100% for BDLib, and 95.3% for Urban Sound, while on RPi with Coral TPU, the rates were 95.7% for ESC-10, 100% for BDLib and 95.4% for the Urban Sound. Utilizing pre-trained models reduces the computational requirements, enabling faster inference. Leveraging pre-trained models in embedded systems accelerates the development, deployment, and performance of various real-time applications. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

24 pages, 16030 KiB  
Article
A Self-Attention Integrated Learning Model for Landing Gear Performance Prediction
by Lin Lin, Changsheng Tong, Feng Guo, Song Fu, Yancheng Lv and Wenhui He
Sensors 2023, 23(13), 6219; https://0-doi-org.brum.beds.ac.uk/10.3390/s23136219 - 07 Jul 2023
Cited by 2 | Viewed by 899
Abstract
The landing gear structure suffers from large loads during aircraft takeoff and landing, and an accurate prediction of landing gear performance is beneficial to ensure flight safety. Nevertheless, the landing gear performance prediction method based on machine learning has a strong reliance on [...] Read more.
The landing gear structure suffers from large loads during aircraft takeoff and landing, and an accurate prediction of landing gear performance is beneficial to ensure flight safety. Nevertheless, the landing gear performance prediction method based on machine learning has a strong reliance on the dataset, in which the feature dimension and data distribution will have a great impact on the prediction accuracy. To address these issues, a novel MCA-MLPSA is developed. First, an MCA (multiple correlation analysis) method is proposed to select key features. Second, a heterogeneous multilearner integration framework is proposed, which makes use of different base learners. Third, an MLPSA (multilayer perceptron with self-attention) model is proposed to adaptively capture the data distribution and adjust the weights of each base learner. Finally, the excellent prediction performance of the proposed MCA-MLPSA is validated by a series of experiments on the landing gear data. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

24 pages, 2207 KiB  
Article
Condition Monitoring of Wind Turbine Systems by Explainable Artificial Intelligence Techniques
by Davide Astolfi, Fabrizio De Caro and Alfredo Vaccaro
Sensors 2023, 23(12), 5376; https://0-doi-org.brum.beds.ac.uk/10.3390/s23125376 - 06 Jun 2023
Cited by 8 | Viewed by 1830
Abstract
The performance evaluation of wind turbines operating in real-world environments typically relies on analyzing the power curve, which shows the relationship between wind speed and power output. However, conventional univariate models that consider only wind speed as an input variable often fail to [...] Read more.
The performance evaluation of wind turbines operating in real-world environments typically relies on analyzing the power curve, which shows the relationship between wind speed and power output. However, conventional univariate models that consider only wind speed as an input variable often fail to fully explain the observed performance of wind turbines, as power output depends on multiple variables, including working parameters and ambient conditions. To overcome this limitation, the use of multivariate power curves that consider multiple input variables needs to be explored. Therefore, this study advocates for the application of explainable artificial intelligence (XAI) methods in constructing data-driven power curve models that incorporate multiple input variables for condition monitoring purposes. The proposed workflow aims to establish a reproducible method for identifying the most appropriate input variables from a more comprehensive set than is usually considered in the literature. Initially, a sequential feature selection approach is employed to minimize the root-mean-square error between measurements and model estimates. Subsequently, Shapley coefficients are computed for the selected input variables to estimate their contribution towards explaining the average error. Two real-world data sets, representing wind turbines with different technologies, are discussed to illustrate the application of the proposed method. The experimental results of this study validate the effectiveness of the proposed methodology in detecting hidden anomalies. The methodology successfully identifies a new set of highly explanatory variables linked to the mechanical or electrical control of the rotor and blade pitch, which have not been previously explored in the literature. These findings highlight the novel insights provided by the methodology in uncovering crucial variables that significantly contribute to anomaly detection. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

16 pages, 1316 KiB  
Article
Attention Recurrent Neural Network-Based Severity Estimation Method for Early-Stage Fault Diagnosis in Robot Harness Cable
by Heonkook Kim, Hojin Lee, Seongyun Kim and Sang Woo Kim
Sensors 2023, 23(11), 5299; https://0-doi-org.brum.beds.ac.uk/10.3390/s23115299 - 02 Jun 2023
Cited by 1 | Viewed by 1128
Abstract
Cable is crucial to the control and instrumentation of machines and facilities. Therefore, early diagnosis of cable faults is the most effective approach to prevent system downtime and maximize productivity. We focused on a “soft fault state”, which is a transient state that [...] Read more.
Cable is crucial to the control and instrumentation of machines and facilities. Therefore, early diagnosis of cable faults is the most effective approach to prevent system downtime and maximize productivity. We focused on a “soft fault state”, which is a transient state that eventually becomes a permanent fault —open-circuit and short-circuit. However, the issue of soft fault diagnosis has not been considered enough in previous research, which could not provide crucial information, such as fault severity, to support maintenance. In this study, we focused on solving soft fault problem by estimating fault severity to diagnose early-stage faults. The proposed diagnosis method comprised a novelty detection and severity estimation network. The novelty detection part is specially designed to deal with varying operating conditions of industrial applications. First, an autoencoder calculates anomaly scores to detect faults using three-phase currents. If a fault is detected, a fault severity estimation network, wherein long short-term memory and attention mechanisms are integrated, estimates the fault severity based on the time-dependent information of the input. Accordingly, no additional equipment, such as voltage sensors and signal generators, is required. The conducted experiments demonstrated that the proposed method successfully distinguishes seven different soft fault degrees. Full article
(This article belongs to the Special Issue AI-Assisted Condition Monitoring and Fault Diagnosis)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-20
Back to TopTop