Submit to Special Issue Submit Abstract to Special Issue Review for Electronics Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Fault Detection Technology Based on Deep Learning

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 15 April 2025 | Viewed by 12290

Share This Special Issue

Special Issue Editors

Dr. Séjir Khojet El Khil

E-Mail Website
Guest Editor

Laboratoire des Systèmes Electriques (LR11ES15), Université de Tunis El Manar, Ecole Nationale d’Ingénieurs de Tunis, Tunis 1002, Tunisia
Interests: fault diagnosis; closed loop systems; electric current control; invertors; maximum power point trackers; permanent magnet generators; photovoltaic power systems; power grids; predictive control; synchronous generators; DC-DC power convertors; control engineering

Dr. Chiara Boccaletti

E-Mail Website
Guest Editor

Department of Astronautics, Electrical and Energetic Engineering, Sapienza University of Rome, Rome, Italy
Interests: cover power plants based on renewable sources; cogeneration and trigeneration
Special Issues, Collections and Topics in MDPI journals

Dr. Monia Ben Khader Bouzid

E-Mail Website
Guest Editor

Laboratoire des Systèmes Electriques (LR11ES15), Université de Tunis El Manar, Ecole Nationale d’Ingénieurs de Tunis, Tunis 1002, Tunisia
Interests: modeling and fault diagnosis of electrical machines, renewable energy systems, and power quality

Special Issue Information

Dear Colleagues,

In recent years, there has been increasing interest in and investment on electrical-based systems in various applications, such as Industry 4.0, electric vehicles, renewables, micro- and smart grids, and so on. Such systems should have high performance, reliability, and availability. Indeed, they are exposed to several types of failures due to external and internal sources. Failures may affect energy sources, actuators, sensors, or controllers. Consequently, predictive maintenance based on accurate fault diagnosis approaches and fault-tolerant control strategies is of upmost importance.

State-of-the-art reviews have shown that fault diagnosis methods are mainly classified in model-based approaches and signal-based approaches. However, with the increase in data acquisition and processing algorithms, artificial intelligence (AI) tools have become more attractive for fault diagnosis and fault classification issues. Indeed, AI approaches are only based on recorded data obtained from measured quantities instead of specific complex mathematical models.

The main purpose of this Special Issue is to share high-quality original research articles and reviews in the area of fault diagnosis based on deep learning and its applications.

The topics of interest of this Special Issue include but are not limited to:

Fault detection and fault diagnosis based on deep learning;
Fault-tolerant control strategies based on deep learning algorithms;
Predictive maintenance with deep learning;
Implementation of deep-learning-based algorithms and architectures for diagnosis.

Dr. Séjir Khojet El Khil
Dr. Chiara Boccaletti
Dr. Monia Ben Khader Bouzid
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. Electronics 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 2400 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

fault diagnosis
fault detection
condition monitoring
predictive maintenance
deep learning
machine learning

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (11 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

17 pages, 3663 KiB

Open AccessArticle

A Novel Multi-Task Self-Supervised Transfer Learning Framework for Cross-Machine Rolling Bearing Fault Diagnosis

by Lujia Zhao, Yuling He, Derui Dai, Xiaolong Wang, Honghua Bai and Weiling Huang

Electronics 2024, 13(23), 4622; https://doi.org/10.3390/electronics13234622 - 23 Nov 2024

Viewed by 303

Abstract

In recent years, intelligent methods based on transfer learning have achieved significant research results in the field of rolling bearing fault diagnosis. However, most studies focus on the transfer diagnosis scenario under different working conditions of the same machine. The transfer fault diagnosis methods used for different machines have problems such as low recognition accuracy and unstable performance. Therefore, a novel multi-task self-supervised transfer learning framework (MTSTLF) is proposed for cross-machine rolling bearing fault diagnosis. The proposed method is trained using a multi-task learning paradigm, which includes three self-supervised learning tasks and one fault diagnosis task. First, three different scales of masking methods are designed to generate masked vibration data based on the periodicity and intrinsic information of the rolling bearing vibration signals. Through self-supervised learning, the attention to the intrinsic features of data in different health conditions is enhanced, thereby improving the model’s feature expression capability. Secondly, a multi-perspective feature transfer method is proposed for completing cross-machine fault diagnosis tasks. By integrating two types of metrics, probability distribution and geometric similarity, the method focuses on transferable fault diagnosis knowledge from different perspectives, thereby enhancing the transfer learning ability and accomplishing cross-machine fault diagnosis of rolling bearings. Two experimental cases are carried out to evaluate the effectiveness of the proposed method. Results suggest that the proposed method is effective for cross-machine rolling bearing fault diagnosis. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Figure 1

29 pages, 2424 KiB

Open AccessArticle

Hybrid-DC: A Hybrid Framework Using ResNet-50 and Vision Transformer for Steel Surface Defect Classification in the Rolling Process

by Minjun Jeong, Minyeol Yang and Jongpil Jeong

Electronics 2024, 13(22), 4467; https://doi.org/10.3390/electronics13224467 - 14 Nov 2024

Viewed by 425

Abstract

This study introduces Hybrid-DC, a hybrid deep-learning model integrating ResNet-50 and Vision Transformer (ViT) for high-accuracy steel surface defect classification. Hybrid-DC leverages ResNet-50 for efficient feature extraction at both low and high levels and utilizes ViT’s global context learning to enhance classification precision. A unique hybrid attention layer and an attention fusion mechanism enable Hybrid-DC to adapt to the complex, variable patterns typical of steel surface defects. Experimental evaluations demonstrate that Hybrid-DC achieves substantial accuracy improvements and significantly reduced loss compared to traditional models like MobileNetV2 and ResNet, with a validation accuracy reaching 0.9944. The results suggest that this model, characterized by rapid convergence and stable learning, can be applied for real-time quality control in steel manufacturing and other high-precision industries, enhancing automated defect detection efficiency. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Figure 1

16 pages, 3506 KiB

Open AccessArticle

HADNet: A Novel Lightweight Approach for Abnormal Sound Detection on Highway Based on 1D Convolutional Neural Network and Multi-Head Self-Attention Mechanism

by Cong Liang, Qian Chen, Qiran Li, Qingnan Wang, Kang Zhao, Jihui Tu and Ammar Jafaripournimchahi

Electronics 2024, 13(21), 4229; https://doi.org/10.3390/electronics13214229 - 28 Oct 2024

Viewed by 545

Abstract

Video surveillance is an effective tool for traffic management and safety, but it may face challenges in extreme weather, low visibility, areas outside the monitoring field of view, or during nighttime conditions. Therefore, abnormal sound detection is used in traffic management and safety as an auxiliary tool to complement video surveillance. In this paper, a novel lightweight method for abnormal sound detection based on 1D CNN and Multi-Head Self-Attention Mechanism on the embedded system is proposed, which is named HADNet. First, 1D CNN is employed for local feature extraction, which minimizes information loss from the audio signal during time-frequency conversion and reduces computational complexity. Second, the proposed block based on Multi-Head Self-Attention Mechanism not only effectively mitigates the issue of disappearing gradients, but also enhances detection accuracy. Finally, the joint loss function is employed to detect abnormal audio. This choice helps address issues related to unbalanced training data and class overlap, thereby improving model performance on imbalanced datasets. The proposed HADNet method was evaluated on the MIVIA Road Events and UrbanSound8K datasets. The results demonstrate that the proposed method for abnormal audio detection on embedded systems achieves high accuracy of 99.6% and an efficient detection time of 0.06 s. This approach proves to be robust and suitable for practical applications in traffic management and safety. By addressing the challenges posed by traditional video surveillance methods, HADNet offers a valuable and complementary solution for enhancing safety measures in diverse traffic conditions. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Figure 1

22 pages, 7018 KiB

Open AccessArticle

PAN: Improved PointNet++ for Pavement Crack Information Extraction

by Jiakai Fan, Weidong Song, Jinhe Zhang, Shangyu Sun, Guohui Jia and Guang Jin

Electronics 2024, 13(16), 3340; https://doi.org/10.3390/electronics13163340 - 22 Aug 2024

Viewed by 696

Abstract

Maintenance and repair of expressways are becoming increasingly important due to the growing frequency of their use. Accurate pavement crack information extraction helps with routine maintenance and reduces the risk of traffic accidents. The traditional 2D crack image detection method has limitations and cannot effectively obtain depth information. Three-dimensional crack extraction from 3D point cloud has become a new solution that can capture pavement crack information more comprehensively and accurately. However, the existing algorithms are not effective in the feature extraction of cracks due to the different and irregular shapes and sizes of pavement cracks and interference from the external environment. To solve this, a new method for detecting pavement cracks in point clouds, namely point attention net (PAN), is herein proposed. It uses a two-branch attention fusion module to focus on space and feature information in the cloud and capture features of crack points at different scales. It also uses the Poly Loss function to solve the imbalance of foreground and background points in pavement point cloud data. Experiments on the LNTU-RDD-LiDAR dataset were carried out to verify the effectiveness of the proposed method. Compared with the traditional method and the latest point cloud segmentation technology, the performance indexes of mIoU, Acc, F1, and Rec achieved significant improvement, reaching 75.4%, 91.5%, 75.4%, and 67.1%, respectively. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Figure 1

21 pages, 1644 KiB

Open AccessArticle

Helicopter Turboshaft Engine Residual Life Determination by Neural Network Method

by Serhii Vladov, Viacheslav Kovtun, Valerii Sokurenko, Oleksandr Muzychuk and Victoria Vysotska

Electronics 2024, 13(15), 2952; https://doi.org/10.3390/electronics13152952 - 26 Jul 2024

Viewed by 673

Abstract

A neural network method has been developed for helicopter turboshaft engine residual life determination, the basis of which is a hierarchical system, which is represented in neural network model form, consisting of four layers, which determines the numerical value of the residual life. To implement a hierarchical system, a justified multilayer perceptron is used. A multilayer perceptron training algorithm has been developed, which, by introducing an initial parameter to the output layer, yields a prediction accuracy of up to 99.3%, and the adaptive Adam training rate ensures an accuracy of up to 99.4% in helicopter turboshaft engine residual life determination. A method for constructing a degradation curve has been developed that takes into account both the parameter predictions and similarities with past patterns, allowing you to determine the range of possible values of the residual life estimate, with a probability of up to 95%. The article considers an example of solving the task of determining the thermally stressed state of helicopter turboshaft engine compressor turbine blades and assessing their residual life. A computational experiment was carried out to determine the residual life of helicopter turboshaft engine compressor turbine blades, and the results, with 160 training epochs, recorded an accuracy of 99.3%, with a reduction in losses from 2.5% to 0.5% thanks to training process optimization by applying an adaptive training rate. The comparative analysis results showed that use of the multilayer perceptron as a hierarchical system gives better results than the classical RBF network and the least squares method. The first and second types of error were reduced by 2.23 times compared to the RBF network and by 4.74 times compared to the least squares method. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Figure 1

24 pages, 7120 KiB

Open AccessArticle

Remaining Useful Life Prediction of Aero-Engine Based on KSFA-GMM-BID-Improved Autoformer

by Jiashun Wei, Zhiqiang Li, Yang Li and Ying Zhang

Electronics 2024, 13(14), 2741; https://doi.org/10.3390/electronics13142741 - 12 Jul 2024

Viewed by 720

Abstract

Addressing the limitation of traditional deep learning models in capturing the spatio-temporal characteristics of flight data and the constrained prediction accuracy due to sequence length in aero-engine life prediction, this study proposes an aero-engine remaining life prediction approach integrating a kernel slow feature analysis, a Gaussian mixture model, and an improved Autoformer model. Initially, the slow degradation features of gas path performance parameters over time are extracted through kernel slow feature analysis, followed by the establishment of a Gaussian mixture model to create a health state representation using Bayesian inferred distances for quantifying the aero-engine’s health status. Moreover, a spatial attention mechanism is introduced alongside the autocorrelation mechanism of the Autoformer model to augment the global feature extraction capacity. Additionally, a multilayer perceptron is employed to further elucidate the degradation trends, which enhances the model’s learning and predictive capabilities for extended sequences. Subsequently, experiments are conducted using authentic aero-engine operational data, comparing the proposed method with the standard Autoformer and Transformer models. The results demonstrate that the proposed method outperforms both models in swiftly and accurately predicting the remaining life of aero-engines with robustness and high prediction accuracy. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Figure 1

20 pages, 6916 KiB

Open AccessArticle

An Improved YOLOv5 Algorithm for Tyre Defect Detection

by Mujun Xie, Heyu Bian, Changhong Jiang, Zhong Zheng and Wei Wang

Electronics 2024, 13(11), 2207; https://doi.org/10.3390/electronics13112207 - 5 Jun 2024

Cited by 1 | Viewed by 1103

Abstract

In this study, a tyre defect detection model is improved and optimized under the YOLOv5 framework, aiming at radial tyre defects with characteristics such as an elongated shape and various target sizes and defect types. The DySneakConv module is introduced to replace the first BotteneckCSP in the Backbone network. The deformation offset of the DySneakConv module is used to make the convolutional energy freely adapt to the structure to improve the recognition rate of tyre defects with elongated features; the AIFI module is introduced to replace the fourth BotteneckCSP, and the self-attention mechanism and the processing of large-scale features are used to improve the recognition rate of tyre defects with elongated features using the AIFI module. This latter module has a self-attention mechanism and the ability to handle large-scale features to solve the problems of diverse tyre defects and different sizes. Secondly, the CARAFE up-sampling operator is introduced to replace the up-sampling operator in the Neck network. The up-sampling kernel prediction module in the CARAFE operator is used to increase the receptive field and allow the feature reorganization module to capture more semantic information to overcome the information loss problem of the up-sampling operator. Finally, based on the improved YOLOv5 detection algorithm, the Channel-wise Knowledge Distillation algorithm lightens the model, reducing its computational requirements and size while ensuring detection accuracy. Experimental studies were conducted on a dataset containing four types of tyre defects. Experimental results for the training set show that the improved algorithm improves the mAP0.5 by 4.6 pp, reduces the model size by 25.6 MB, reduces the computational complexity of the model by 31.3 GFLOPs, and reduces the number of parameters by 12.7 × 10⁶ compared to the original YOLOv5m algorithm. Experimental results for the test set show that the improved algorithm improves the mAP0.5 by 2.6 pp compared to the original YOLOv5m algorithm. This suggests that the improved algorithm is more suitable for tyre defect detection than the original YOLOv5. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Figure 1

22 pages, 11780 KiB

Open AccessArticle

Rolling Bearing Residual Useful Life Prediction Model Based on the Particle Swarm Optimization-Optimized Fusion of Convolutional Neural Network and Bidirectional Long–Short-Term Memory–Multihead Self-Attention

by Jianzhong Yang, Xinggang Zhang, Song Liu, Ximing Yang and Shangfang Li

Electronics 2024, 13(11), 2120; https://doi.org/10.3390/electronics13112120 - 29 May 2024

Cited by 1 | Viewed by 747

Abstract

In the context of predicting the remaining useful life (RUL) of rolling bearings, many models often encounter challenges in identifying the starting point of the degradation stage, and the accuracy of predictions is not high. Accordingly, this paper proposes a technique that utilizes particle swarm optimization (PSO) in combination with the fusing of a one-dimensional convolutional neural network (CNN) and a multihead self-attention (MHSA) bidirectional long short-term memory (BiLSTM) network called PSO-CNN-BiLSTM-MHSA. Initially, the original signals undergo correlation signal processing to calculate the features, such as standard deviation, variance, and kurtosis, to help identify the beginning location of the rolling bearing degradation stage. A new dataset is constructed with similar degradation trend features. Subsequently, the particle swarm optimization (PSO) algorithm is employed to find the optimal values of important hyperparameters in the model. Then, a convolutional neural network (CNN) is utilized to extract the deterioration features of rolling bearings in order to predict their remaining lifespan. The degradation features are inputted into the BiLSTM-MHSA network to facilitate the learning process and estimate the remaining lifespan of rolling bearings. Finally, the degradation features are converted to the remaining usable life (RUL) via the fully connected layer. The XJTU-SY rolling bearing accelerated life experimental dataset was used to verify the effectiveness of the proposed method by k-fold cross-validation. After comparing our model to the CNN-LSTM network model and other models, we found that our model can achieve reductions in mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) of 9.27%, 6.76%, and 2.35%, respectively. Therefore, the experimental results demonstrate the model’s accuracy in forecasting remaining lifetime and support its ability to forecast breakdowns. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Figure 1

18 pages, 6030 KiB

Open AccessArticle

Real-Time Defect Detection in Electronic Components during Assembly through Deep Learning

by Eyal Weiss, Shir Caplan, Kobi Horn and Moshe Sharabi

Electronics 2024, 13(8), 1551; https://doi.org/10.3390/electronics13081551 - 19 Apr 2024

Cited by 3 | Viewed by 2027

Abstract

This paper introduces a pioneering method for real-time image processing in electronic component assembly, revolutionizing quality control in manufacturing. By promptly capturing images from pick-and-place machines during the interval between component pick-up and mounting, defects are identified and promptly addressed in line. This proactive approach ensures that defective components are rejected before mounting, effectively preventing issues from ever occurring, thus significantly enhancing efficiency and reliability. Leveraging rapid network protocols such as gRPC and orchestration via Kubernetes, in conjunction with C++ programming and TensorFlow, this approach achieves an impressive average turnaround time of less than 5 milli-seconds. Rigorously tested on 20 operational production machines, it not only ensures adherence to IPC-A-610 and IPC-STD-J-001 standards but also optimizes production efficiency and reliability. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Figure 1

16 pages, 5994 KiB

Open AccessArticle

Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision Transformer

by Fengyun Xie, Gan Wang, Haiyan Zhu, Enguang Sun, Qiuyang Fan and Yang Wang

Electronics 2023, 12(16), 3515; https://doi.org/10.3390/electronics12163515 - 19 Aug 2023

Cited by 7 | Viewed by 1484

Abstract

Aiming at rolling bearing fault diagnosis, the collected vibration signal contains complex noise interference, and one-dimensional information cannot be used to fully mine the data features of the problem. This paper proposes a rolling bearing fault diagnosis method based on SVD-GST combined with the Vision Transformer. Firstly, the one-dimensional vibration signal is preprocessed to reduce noise using singular value decomposition (SVD) to obtain a more accurate and useful signal. Then, the generalized S-transform (GST) is used to convert the processed one-dimensional vibration signal into a two-dimensional time–frequency image and make full use of the advantages of deep learning in image classification with higher recognition accuracy. In order to avoid the problem of limited sensory fields in CNN and the need for an RNN to compute step by step over time when processing sequence data, the use of a Vision Transformer model for pattern recognition classification is proposed. Finally, an experimental platform for the fault diagnosis of rolling bearings is built. The model is experimentally validated, achieving an average accuracy of 98.52% over multiple tests. Additionally, compared with the SVD-GST-2DCNN, STFT-CNN-LSTM, SVD-GST-LSTM, and GST-ViT fault diagnosis models, the proposed method has higher diagnostic accuracy and stability, providing a new method for rolling bearing fault diagnosis. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Figure 1

17 pages, 6677 KiB

Open AccessArticle

Gearbox Fault Diagnosis Based on Gramian Angular Field and CSKD-ResNeXt

by Yanlin Liu, Shuihai Dou, Yanping Du and Zhaohua Wang

Electronics 2023, 12(11), 2475; https://doi.org/10.3390/electronics12112475 - 31 May 2023

Cited by 9 | Viewed by 2216

Abstract

For most rotating mechanical transmission systems, condition monitoring and fault diagnosis of the gearbox are of great significance to avoid accidents and maintain stability in operation. To strengthen the comprehensiveness of feature extraction and improve the utilization rate of fault signals to accurately identify the different operating states of a gearbox, a gearbox fault diagnosis model combining Gramian angular field (GAF) and CSKD-ResNeXt (channel shuffle and kernel decomposed ResNeXt) was proposed. The original one-dimensional vibration signal of the gearbox was converted into a two-dimensional image by GAF transformation, and the image was used as the input of the subsequent diagnosis network. To solve the problem of channel independence and incomplete information caused by group convolution, the idea of channel shuffle is introduced to enable the branches of the group convolution part to establish information exchange. In addition, to improve the semantic expression ability of the model, the convolutional kernel of the network backbone is split and replaced. The model is verified under the different working conditions of the gearbox and compared with other methods. The experimental results show that the diagnostic accuracy of the model is up to 99.75%, and the precise identification of gearbox faults is realized. Full article

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)

► Show Figures

Journal Menu

Journal Browser

Fault Detection Technology Based on Deep Learning

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (11 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI