A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method
The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Fault diagnosis is vital in manufacturing system, since early detections on the emerging problem can save invaluable time and cost. With the development of smart manufacturing, the data-driven fault diagnosis becomes a hot topic. However, the traditional data-driven fault diagnosis methods rely on the features extracted by experts. The feature extraction process is an exhausted work and greatly impacts the final result. Deep learning (DL) provides an effective way to extract the features of raw data automatically. Convolutional neural network (CNN) is an effective DL method. In this study, a new CNN based on LeNet-5 is proposed for fault diagnosis. Through a conversion method converting signals into two-dimensional (2-D) images, the proposed method can extract the features of the converted 2-D images and eliminate the effect of handcrafted features. The proposed method which is tested on three famous datasets, including motor bearing dataset, self-priming centrifugal pump dataset, and axial piston hydraulic pump dataset, has achieved prediction accuracy of 99.79%, 99.481%, and 100%, respectively. The results have been compared with other DL and traditional methods, including adaptive deep CNN, sparse filter, deep belief network, and support vector machine. The comparisons show that the proposed CNN-based data-driven fault diagnosis method has achieved significant improvements.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
Olshausen, B. A., & Field, D. J. (1996) · Nature · doi:10.1038/381607a0 · Cited by 5,694 · cited 1×
“This was inspired by the concept of simple and complex cells in visual cortex in brain [34], and the”
MethodBeyond the hype: Big data concepts, methods, and analytics
Gandomi, A., & Haider, M. (2015) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2014.10.007 · Cited by 4,226
Gao, Z., Cecati, C., & Ding, S. X. (2015) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2015.2417501 · Cited by 3,135 · cited 1×
“2774777 methods [3].”
Deep learning and its applications to machine health monitoring
Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., & Gao, R. X. (2019) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.05.050 · Cited by 2,894
Research works printed but not linked: 3
- henley, 0, Application of expert systems to fault diagnosis, Proc AIChE Annu Meeting
- aydmj, 1999, Pump failure determination using support vector data description, Advances in Intelligent Data Analysis, 415
- 10.1109/TIE.2015.2417501 · DOI · Paper page
Cited by
Items 701–800 of 1,003
A Concurrent Fault Diagnosis Model via the Evidential Reasoning Rule
Ning, P., Zhou, Z., Cao, Y., Tang, S., & Wang, J. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3135317 · Cited by 28
“Second, the quantitative information-based FD method requires a large number of historic data about fault features when lacking enough prior knowledge, such as SVM and neural network-based approaches [22]–[24].”
MethodDeep subdomain generalisation network for health monitoring of high-speed train brake pads
Hu, R., Zhang, M., Meng, X., & Kang, Z. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.104896 · Cited by 30
SKND-TSACNN: A novel time-scale adaptive CNN framework for fault diagnosis of rotating machinery
Yu, Z., Zhang, C., Liu, J., & Deng, C. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110682 · Cited by 31
A Novel Data Augmentation and Composite Multiscale Network for Mechanical Fault Diagnosis
Wei, Y., Xiao, Z., Liu, S., Schröder, K., Peng, H., Sarr, A. M., & Gu, X. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3301902 · Cited by 28
“[18] put forward a mechanical fault diagnosis method based on the 2-D representation of vibration signals and LeNet-5 convolutional neural network (LeNet-5).”
Men, J., & Zhao, C. M. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121159 · Cited by 30
The study of hydraulic machinery condition monitoring based on anomaly detection and fault diagnosis
Liu, Y., Zhang, R., He, Z., Huang, Q., Zhu, R., Li, H., & Fu, Q. (2024) · Measurement · doi:10.1016/j.measurement.2024.114518 · Cited by 27
A Novel Interpretable Model via Algorithm Unrolling for Intelligent Fault Diagnosis of Machinery
Rao, F., Zeng, M., & Cheng, Y. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3332755 · Cited by 29
“Widely used deep learning models include convolutional neural networks (CNNs), recurrent neural networks (RNN), and residual neural networks (ResNet) [2], [3], [4], [5], [6], [7], [8], [9].”
Shen, H., Tang, X. Z., Luo, Y., Xie, F., & Shi, Z. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3348886 · Cited by 31
“The convolutional neural network (CNN) is widely used in the existing research on data-driven fault diagnosis meth-ods [16], [17].”
MethodLuo, J., Zhang, Y., Yang, F., & Jing, X. (2024) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-024-0104-2 · Cited by 30
“Most of the current fault diagnosis networks are composed of CNNs, mainly because of their strong feature extraction ability and high accuracy of classification [31, 32].”
Self-citationWu, K., Xu, W., Shu, Q., Zhang, W., Cui, X., & Wu, J. (2024) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02395-2 · Cited by 26
“CNN (Wen et al., 2018): CNN is a classical deep learning method that assumes the same distribution of train and test data.”
InfluentialExplainable fault diagnosis method based on statistical features for gearboxes
Tang, H., Wang, H., & Li, C. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110503 · Cited by 36
He, J., Ouyang, M., Chen, Y., Chen, D., Guo, J., & Zhou, Y. (2020) · Sensors · doi:10.3390/s20061774 · Cited by 27
“As an emerging research field, deep learning has a powerful ability to extract the representative features from the collected signals, which makes it has the potential to overcome the shortcomings of the traditional intelligent diagnosis methods [22,23].”
BackgroundGao, T., Sheng, W., Zhou, M., Fang, B., Luo, F., & Li, J. (2020) · Sensors · doi:10.3390/s20195633 · Cited by 27
“[38] achieved mean FD accuracies of 94.”
BackgroundMethodFault Diagnosis of Sucker Rod Pump Based on Deep-Broad Learning Using Motor Data
Wei, J., & Gao, X. (2020) · IEEE Access · doi:10.1109/access.2020.3036078 · Cited by 27
“, convolutional neural network (CNN), as one of the most effective DLs, has been vastly employed to extract the features of one-dimension (1-D) [21] signal in electrocardiogram (ECG) classification [22], motor fault detection [23] and real-time structural health monitoring [24] fault diagnosis recently.”
BackgroundUsing convolutional neural network for intelligent SAM inspection of flip chips
Wang, W., Lu, X., He, Z., & Shi, T. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac1615 · Cited by 28
“Elements in a confusion matrix include TP, FP, precision, FN, TN, recall and accuracy [31].”
A Survey on Fault Detection and Diagnosis Methods
Okada, K., de Morais, A. S., Oliveira-Lopes, L. C., & Ribeiro, L. (2021) · IEEE International Conference on Industry Applications · doi:10.1109/induscon51756.2021.9529495 · Cited by 32
Wang, S., Zheng, H., Tang, L., Li, Z., Zhao, R., Lu, Y., & Aw, K. C. (2022) · Journal of Civil Structural Health Monitoring · doi:10.1007/s13349-022-00616-x · Cited by 28
“This section introduces the method to convert the raw vibration signals to the pixels of the grayscale image [30].”
MethodZhang, G., Kong, X., Du, J., Wang, J., Yang, S., & Ma, H. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.105847 · Cited by 26
Deep Learning-Based Composite Fault Diagnosis
An, Z., Wu, F., Zhang, C., Ma, J., Sun, B., Tang, B., & Liu, Y. (2023) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2023.3262241 · Cited by 26
“Wen et al.’s classic paper in the field of fault diagnosis [1] based on the LeNet-5 network proposed a method to complete fault diagnosis by converting the time domain waveform signal of the fault into a gray image for image classification, which solved the problem requiring a large amount of a…”
BackgroundMethodInfluentialZhang, Y., Liu, Z., & Huang, Q. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3284044 · Cited by 30
“However, in practice, deep learning algorithms in general are purely data-driven and learn features automatically based on a large number of input data [1], [26], which seldom incorporate any physics of the process into the computation.”
BackgroundSelf-citationTang, G., Yi, C., Liu, L., Du, X., Zhou, Q., Hu, Y., Zhou, P., & Lin, J. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107407 · Cited by 28
Yang, J., Yin, S., Chang, Y., & Gao, T. (2020) · Sensors · doi:10.3390/s20143837 · Cited by 29
“Wen et al. [28] modified the LeNet-5 to perform fault diagnosis for bearings and centrifugal pumps, wherein the raw time-domain signal was transformed into a two-dimensional gray scale image to train the model.”
MethodPhysics-guided, data-refined fault root cause tracing framework for complex electromechanical system
Xu, J., Wang, R., Liang, Z., Liu, P., Gao, J., & Wang, Z. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109293 · Cited by 26
Orthotropic Material Parameters Identification Method of Stator Core and Windings in Electric Motors
Deng, W., Qian, Z., Chen, W., Qian, C., & Wang, Q. (2023) · IEEE Transactions on Energy Conversion · doi:10.1109/tec.2023.3276980 · Cited by 25
Brain-Inspired Meta-Learning for Few-Shot Bearing Fault Diagnosis
Wang, J., Sun, C., Nandi, A. K., Yan, R., & Chen, X. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3503658 · Cited by 25
“W ITH the rapid development of sensing and intelligent computing technology, data-driven methods have attracted more and more attention in bearing fault diagnosis [1], [2], [3], [4], [5].”
Lin, C., Kong, Y., Huang, G., Han, Q., Dong, M., Liu, H., & Chu, F. (2024) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2024.110791 · Cited by 29
Li, J., Zheng, C., Wu, Z., Chen, H., Wang, X., & Yang, Z.-X. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.113623 · Cited by 34
Fault Diagnosis of High-Speed Railway Turnout Based on Convolutional Neural Network
Zhang, P., Zhang, G., Dong, W., Sun, X., & Ji, X. (2018) · International Conference on Automation and Computing (ICAC) · doi:10.23919/iconac.2018.8749078 · Cited by 25
“Motivated by the efficient performance of CNN in image classification and the capability to extract features automatically [13], this paper aims to introduce a new Proceedings of the 24th International Conference on Automation & Computing, Newcastle University, Newcastle upon Tyne, UK, 6-7 September 2018”
MethodKim, T. K., Park, J. K., Lee, B. H., & Seong, S.-H. (2019) · Annals of Nuclear Energy · doi:10.1016/j.anucene.2019.07.022 · Cited by 25
Bearing fault diagnosis based on improved VMD and DCNN
Wang, R., Xu, L., & Liu, F. (2020) · Journal of Vibroengineering · doi:10.21595/jve.2020.21187 · Cited by 26
“For these reasons, CNN has also been applied in machinery fault diagnosis [16, 17].”
MethodChen, L., Hu, H., Zhang, Z., & Wang, X. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3029383 · Cited by 25
“Wen et al. [16] converted fault signals into 2-”
BackgroundA Novel Subpixel Edge Detection Method of Pantograph Slide in Complicated Surroundings
Lu, S., Liu, Z., Chen, Y., & Gao, Y. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3062276 · Cited by 25
Гареев, А. М., Protsenko, V. I., Стадник, Д. М., И., Г. П., Yuzifovich, Y., Minaev, E. Y., Гимадиев, А. Г., & Nikonorov, A. V. (2021) · Sensors · doi:10.3390/s21134410 · Cited by 30
“Vibration data [28,29] and statistical and heuristic feature engineering performed with this data [30,31] is typically used as classifier input, while works [10,32] use additional sensors such as Citation: Gareev, A.”
MethodJiang, L., Li, S., Li, X., Jiale, L., & Dalian, Y. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac471a · Cited by 27
“For example: Long et al [18] proposed through a conversion method to convert signals into 2D images, then to use a new CNN based on LeNet-5 for fault diagnosis.”
MethodSelf-citationYu, Y., Zhang, H., Peng, W., Wang, R., & Li, C. (2022) · Journal of Building Engineering · doi:10.1016/j.jobe.2022.104718 · Cited by 30
Zhai, X., Qiao, F., Ma, Y., & Lu, H. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3177233 · Cited by 32
Zhang, Y., Feng, Z., Shi, S., Dong, Z., Zhao, L., Jing, L., & Tan, J. (2022) · Heliyon · doi:10.1016/j.heliyon.2022.e11623 · Cited by 26
Self-citationDing, X., Wang, H., Cao, Z., Liu, X., Liu, Y., & Huang, Z. (2023) · Electronics · doi:10.3390/electronics12081816 · Cited by 30
Li, Y., Xie, S., Wang, J., Zhang, J., & Yan, H. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3318686 · Cited by 26
Progressive Improved Convolutional Neural Network for Avionics Fault Diagnosis
Chen, S., Ge, H., Li, J., & PECHT, M. G. (2019) · IEEE Access · doi:10.1109/access.2019.2954170 · Cited by 31
“[40] also transformed the 1D data into gray images, and used transform learning of LeNet-5 to diagnose bearing faults.”
MethodSun, G., Gao, Y., Xu, Y. F., & Feng, W. (2020) · IEEE Access · doi:10.1109/access.2020.3006152 · Cited by 26
Bharatheedasan, K., Maity, T., Kumaraswamidhas, L. A., & Durairaj, M. (2023) · Sadhana · doi:10.1007/s12046-023-02169-1 · Cited by 26
“For the detection of faults in inner and outer rings, as well as rotating elements of aviation engine shafts, vibration measurements are included in the dataset [24].”
BackgroundZhang, Z., Li, J., Cai, C., Ren, J., & Xue, Y. (2024) · Applied Sciences · doi:10.3390/app14072706 · Cited by 29
“The mathematical expression of the Morlet wavelet is [35]: For any function f ( t ) ∈ L 2 ( R ) , its CWT is defined as [16], where W f ( a , b ) represents the wavelet transform coefficient, f , ψ a , b ( t ) (cid:11) denotes the inner product of two functions, and ψ ( t ) denotes the complex…”
Chen, D., Wu, F., Wang, Y., & Qin, Y. (2024) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2024.111699 · Cited by 31
Li, H., Wang, X., Cao, P., Li, Y., Yi, B., & Huang, M. (2024) · Computers in Industry · doi:10.1016/j.compind.2024.104180 · Cited by 28
Xu, D., Shang, J., Jiang, C., Shang, X., Qiu, H., & Gao, L. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.103053 · Cited by 24
Self-citationXin, Y., Li, S., Wang, J., An, Z., & We, Z. (2020) · IET Science Measurement & Technology · doi:10.1049/iet-smt.2018.5672 · Cited by 29
Bibliometric Analysis of the Application of Convolutional Neural Network in Computer Vision
Huie, C., & Deng, Z. (2020) · IEEE Access · doi:10.1109/access.2020.3019336 · Cited by 27
“This method can extract the features of the converted 2-D image and eliminate the influence of manual features [41].”
MethodWang, K., Zhao, W., Xu, A., Zeng, P., & Yang, S. (2020) · Sensors · doi:10.3390/s20216039 · Cited by 26
Bearing Fault Diagnosis Using a Grad-CAM-Based Convolutional Neuro-Fuzzy Network
Lin, C., & Jhang, J. (2021) · Mathematics · doi:10.3390/math9131502 · Cited by 31
“[26] adopted LeNet-5 for bearing fault diagnosis.”
Shi, P., Gao, H., Yu, Y., Xu, X., & Han, D. (2022) · Measurement · doi:10.1016/j.measurement.2022.111993 · Cited by 27
Sun, Z., Liu, K., Xu, T., Xu, Y., Fang, W., Xue, K., Huang, Y., Li, S., & Liu, T. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3210603 · Cited by 26
“LeNet-5 is well known for its effective and automatic feature extraction ability in image pattern recognition [35].”
BackgroundMethodWang, B., Baraldi, P., & Zio, E. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3222400 · Cited by 28
“Differently, deep-learning-based algorithms, such as deep belief network (DBN) [4], sparse autoencoder (SAE) [5], and convolutional neural network (CNN) [6], automatically extract degradation features from large-scale raw data, given their capability of mining hierarchical representations and, therefore, of self-adapt…”
BackgroundMethodInfluentialThe Semisupervised Weighted Centroid Prototype Network for Fault Diagnosis of Wind Turbine Gearbox
Su, Z., Zhang, X., Wang, G., Wang, S., Luo, M., & Wang, X. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3312042 · Cited by 27
Nayal, K., Raut, R. D., Kumar, M., Paul, S. K., & Narkhede, B. E. (2024) · Global Journal of Flexible Systems Management · doi:10.1007/s40171-023-00367-8 · Cited by 35
“AI-based AI-based techniques, either rule-based expert systems or self-learning models, help analyze possible correlations of product failures (Wen et al., 2017), thus improving delivery reliability and reducing the number of consumer backorders.”
Wang, J., Zheng, P., Qin, W., Li, T., & Zhang, J. (2018) · Enterprise Information Systems · doi:10.1080/17517575.2018.1526322 · Cited by 24
Wang, Y., Huang, S., Dai, J., & Tang, J. (2020) · Shock and Vibration · doi:10.1155/2020/1850286 · Cited by 26
“In [20], the one-dimensional signal was converted into two-dimensional gray map as the input of 2DCNN, and the input of 2DCNN in [31] was the root mean square (RMS) map of the characteristics of the vibration signal after Fourier transform (FT).”
MethodSu, J., Xuan, J., Duan, J., Lin, J., Tao, H., Xia, Q., Jing, R., Xiong, S., & Shi, T. (2020) · Journal of Vibration and Control · doi:10.1177/1077546320961918 · Cited by 25
“Wen et al. (2018) It is undeniable that the CNN models mentioned above have made a signi fi cant breakthrough for fault diagnosis and health monitoring.”
Yassaie, N., Gargoum, S., & Al-Dabbagh, A. W. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3317978 · Cited by 26
“Another popular architecture is convolutional neural network (CNN), where its use in fault diagnosis has been investigated in several studies [12], [13], [14].”
BackgroundMethodResultInfluentialZhang, S., Jiang, P., Li, X., Yin, C., & Wang, X. V. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102756 · Cited by 26
Self-citationHan, J., Miao, S., Li, Y., Yang, W., & Yin, H. (2020) · Electric Power Systems Research · doi:10.1016/j.epsr.2020.106876 · Cited by 26
Yu, W., Liu, G., Zhu, L. X., & Yu, W. (2020) · Solar Energy · doi:10.1016/j.solener.2020.09.026 · Cited by 26
Han, T., & Chao, Z. (2021) · Journal of the Brazilian Society of Mechanical Sciences and Engineering · doi:10.1007/s40430-021-03152-9 · Cited by 23
Zhang, Y., Luo, L., Ji, X., & Dai, Y. (2021) · Sensors · doi:10.3390/s21206715 · Cited by 24
“…with the popularization of neural networks, scholars have proposed various non-statistical methods; for example, the convolutional neural network (CNN) realizes image recognition and compressed sensor signal processing by automatic feature extraction and deep learning through hidden layers [15–17].”
BackgroundSelf-citationZhang, Z., & Yang, Q. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.108207 · Cited by 25
Song, H., Ma, W., Han, Z., & Zhu, X. (2022) · Measurement · doi:10.1016/j.measurement.2022.111353 · Cited by 25
The Design of the 1D CNN–GRU Network Based on the RCS for Classification of Multiclass Missiles
Kim, A. R., Kim, H. S., Kang, C. H., & Kim, S. Y. (2023) · Remote Sensing · doi:10.3390/rs15030577 · Cited by 24
Leveraging deep learning techniques for ship pipeline valve leak monitoring
Liu, Z., Xiaohui, Y., Wu, M., Weilei, M., & Guijie, L. (2023) · Ocean Engineering · doi:10.1016/j.oceaneng.2023.116167 · Cited by 24
Maggio, L. G. D., Brusa, E. G. M., & Delprete, C. (2023) · Applied Sciences · doi:10.3390/app132212458 · Cited by 30
1DCNN Fault Diagnosis Based on Cubic Spline Interpolation Pooling
Huang, S., Tang, J., Dai, J., Wang, Y., & Dong, J. (2020) · Shock and Vibration · doi:10.1155/2020/1949863 · Cited by 22
“[8] applied the bearing dataset of the Case Western Reserve University (CWRU) on images as inputs to diagnose the bearing fault through the CNN, where the diagnostic accuracy higher than 95% is obtained.”
MethodHu, P., Song, Y., Zhou, H., Xie, J., & Zhang, C. (2022) · Computer-Aided Design · doi:10.1016/j.cad.2022.103273 · Cited by 22
Time-Efficient Neural Architecture Search for Autonomous Underwater Vehicle Fault Diagnosis
Pei, S., Wang, H., & Han, T. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3327477 · Cited by 23
“The fault diagnosis models of artificial neural networks (ANNs) involved in the comparison are multi-ANN, Wen-CNN [32], sequence convolutional neural network (Seq-CNN) [14], spiking recurrent attention network (SRA-SNN) [33], multi-GRU [34], genetic algorithm-supported ensemble learning (GASEL)…”
MethodInfluentialTransparency: The Missing Link to Boosting AI Transformations in Chemical Engineering
Yuan, Y., Chaffart, D., Wu, T., & Zhu, J. (2024) · Engineering · doi:10.1016/j.eng.2023.11.024 · Cited by 25
Li, S., Zhou, B., Shang, J., Chen, X., & Yu, J. (2025) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2025.07.002 · Cited by 29
An Optimized Few-Shot Learning Framework for Fault Diagnosis in Milling Machines
Saleem, F., Umar, M. I., & Kim, J.-M. (2025) · Machines · doi:10.3390/machines13111010 · Cited by 25
A novel knowledge distillation framework for bearing fault diagnosis under imbalanced samples
Cheng, Y., Liu, L., Liao, Z., Chen, B., Yan, J., & Chen, Z. (2026) · Structural Health Monitoring · doi:10.1177/14759217261418304 · Cited by 26
Ray, S., Ganguly, B., & Dey, D. (2020) · Electric Power Components and Systems · doi:10.1080/15325008.2020.1854384 · Cited by 24
Conditional StyleGAN modelling and analysis for a machining digital twin
Зотов, Е. В., Tiwari, A., & Kadirkamanathan, V. (2021) · Integrated Computer-Aided Engineering · doi:10.3233/ica-210662 · Cited by 23
“The proposed applications of ANNs to machining domain problems include chatter prediction [40,41], fault diagnosis [42], surface defect detection [43] and several others [44].”
Power grid fault diagnosis using polar PMU data plots
Zhang, X., Guo, Z., Zheng, Y., Liu, J., Yan, P., & Zheng, L. (2022) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2022.108148 · Cited by 22
Bearing Faulty Prediction Method Based on Federated Transfer Learning and Knowledge Distillation
Yi-qing, Z., Wang, J., & Wang, Z. (2022) · Machines · doi:10.3390/machines10050376 · Cited by 23
Misfire Detection in Spark Ignition Engine Using Transfer Learning
Venkatesh, S. N., Chakrapani, G., Senapti, S. B., Annamalai, K., Elangovan, M., Indira, V., Sugumaran, V., & Mahamuni, V. S. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/7606896 · Cited by 22
“[22] CNN Centrifugal pump Computational Intelligence and Neuroscience 5”
MethodProfile prediction in ECM using machine learning
Wu, M., Arshad, M. H., Saxena, K. K., Qian, J., & Reynaerts, D. (2022) · Procedia CIRP · doi:10.1016/j.procir.2022.09.192 · Cited by 22
An Intelligent Multiscale Spatiotemporal Fusion Network Model for TCM
Quan, Y., Liu, C., Yuan, Z., & Yang, Z. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3244587 · Cited by 22
“Many deep-learning models, including stacked sparse autoencoders (SAEs) [17], [18], [19], deep belief networks (DBNs) [20], [21], [22], long short-term memory (LSTM) [23], [24], [25], and convolutional neural networks (CNNs) [26], [27], [28], have been used for quantitative monitoring of tool wear.”
BackgroundEnhanced Tyre Pressure Monitoring System for Nitrogen Filled Tyres Using Deep Learning
Arun Balaji, M., Sridharan, N. V., Anoop, P. S., & Sugumaran, V. (2023) · Machines · doi:10.3390/machines11040434 · Cited by 22
A comprehensive diagnosis method of valve leakage faults based on bi-sensor information fusion
Liu, Z., Hao, N., Wu, M., Mu, W., & Liu, G. (2023) · Structural Health Monitoring · doi:10.1177/14759217231174369 · Cited by 22
“12 Wang et al. 13 processed the vibration signals into wavelet transform (WT) images and used them as input to a CNN, thus achieving good classification results.”
MethodIntelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory Data
Zhang, X., Hua, X., Zhu, J., & Ma, M. (2023) · Sensors · doi:10.3390/s23125636 · Cited by 22
“used a conversion method that converts signals into two-dimensional (2-D) images to extract the features of the converted 2-D images and eliminate the influence of handcrafted features [14].”
MethodHuang, Z., Li, K., Ke, C., Duan, H., Wang, M., & Bing, S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106829 · Cited by 26
Jiang, D., & Wang, Z. (2023) · Sensors · doi:10.3390/s23156999 · Cited by 25
“CNN is also used for data-driven fault diagnosis [33], etc. Analysis has shown that, although the deep learning method combined with the fusion of information from multiple sources can provide better diagnostic accuracy, the theory and system for fusing information from multiple sensors are not yet…”
MethodWang, Y., Zou, Y., Hu, W., Chen, J., & Xiao, Z. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/ad05a3 · Cited by 25
“…the original time-domain signal is transformed by short-time Fourier transform to generate a two-dimensional time–frequency image and processed into a two-dimensional grayscale image, which is input into the improved LeNet-5 model for fault diagnosis, and a better diagnosis result is achieved [35].”
Wang, H., Luo, W., Liu, Z., Zhang, J., & Zuo, M. J. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3363216 · Cited by 22
“…noise robustness of traditional CNN. 3) Comparing Existing Methods: In this section, the proposed Soft-FFRNet is compared with five existing methods that have good performance in machinery fault diagnosis: 1) MWA-CNN [34]; 2) MA1DCNN [35]; 3) WenCNN [36]; 4) MCSwin-T [37]; and 5) Convformer [38].”
MethodTemporal–Spatial Attention Network: A Novel Axial Piston Pump Coupled Fault Diagnosis Method
Liu, S. B., Zhang, J., Huang, W., Lyu, F., Wang, D., & Bing Hong, X. U. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3398074 · Cited by 22
“…diagnosis problem, the TSAN model is compared to currently reported state-of-the-art methods, including ResNet-20 [35], LeNet-5 [36], VGG + LSTM [7], VGG-16 [37], and Inception-V4 [37], which are demonstrated to obtain satisfactory performance in solving fault diagnosis in previous researches.”
BackgroundMethodApplication of Generative Adversarial Networks for Intelligent Fault Diagnosis
Cao, S., Wen, L., Li, X., & Gao, L. (2018) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2018.8560528 · Cited by 27
“And a designed structure of Generative Adversarial Networks (GAN) modeled by Convolutional Neural Network (CNN) is proposed to make the classification of fault.”
BackgroundMethodInfluentialSelf-citationWang, Q., Wang, K., Li, Q. '., Yang, Z., Jin, G., & Hong, W. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3017686 · Cited by 23
“With the complexity of fault diagnosis of industrial equipment and the development of hardware and software, more and more researchers try to use deeper network structure to solve complex data analysis tasks in industry, such as the fault diagnosis of industrial rotating equipment [1], [2].”
BackgroundA minority oversampling approach for fault detection with heterogeneous imbalanced data
Liu, J. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115492 · Cited by 22
Wang, B., Chen, G., Song, J., Peng, C., Krein, P. T., & Ma, H. (2024) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2024.3362365 · Cited by 22
Liu, K., Zhou, J., Jin, C., Chen, P., & Zhao, J. (2025) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2025.3610190 · Cited by 27
“Data-driven methods refer to analyzing the measured electrical data of power electronic converters and identifying faults by extracting characteristic information contained in the data [25], [26], [27], [28], [29].”
Multi-Scale CNN based on Attention Mechanism for Rolling Bearing Fault Diagnosis
Hao, Y., Wang, H., Liu, Z., & Han, H. (2020) · Asia-Pacific International Symposium on Advanced Reliability and Maintenance Modeling (APARM) · doi:10.1109/aparm49247.2020.9209470 · Cited by 27
“Three alternatives are Wen-CNN [14], WDCNN [15], ResCNN [16].”
MethodBearing condition evaluation based on the shock pulse method and principal resonance analysis
He, Y. D., Hu, M., Feng, K., & Jiang, Z. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3050679 · Cited by 23
“, n, as presented in the following equation [34]: P( j, k) = A( j, k) − min(Xi ) max(Xi) − min(Xi ) × 255 = x(i−1)×p+ j+k−1 − min(Xi) max(Xi ) − min(Xi ) × 255.”
Huang, Y., Jin, W., & Li, L. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3149892 · Cited by 21
Wu, J., Li, L., Shi, F., Zhao, P., & Li, B. (2022) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2022.108372 · Cited by 29
Metadata
- Authors
- Wen, L., Li, X., Gao, L., & Zhang, Y.
- Affiliations
- State Key Laboratory of Digital Manufacturing Equipment and Technology (CN)
- Venue
- IEEE Transactions on Industrial Electronics
- Published
- 2018-07
- Volume
- 65
- Issue
- 7
- Pages
- 5990-5998
- ISSN
- 0278-0046 (ISSN-L)
- 1557-9948
- OpenAlex
- W2768753204
- Cited by
- 2,222
- References
- 40
- Citations by year
- 2026: 200 · 2025: 242 · 2024: 321 · 2023: 353 · 2022: 318 · 2021: 311 · 2020: 279 · 2019: 167 · 2018: 31
- FWCI
- 81.94
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Industrial Electronics (publishedVersion)
- Funders
- Natural Science Foundation of China (NSFC) (51435009, 51775216, 51711530038)
- China Postdoctoral Science Foundation (2017M622414)
- 111 Project (B16019)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Electrical Fault Detection and Protection
- Keywords
- data-driven fault diagnosis, convolutional neural networks, LeNet-5, signal-to-image conversion, automatic feature extraction, smart manufacturing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.