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 601–700 of 1,003
Xiong, J., Liu, X., Zhu, X., Zhu, H., Li, H., & Zhang, Q. (2020) · IEEE Access · doi:10.1109/access.2020.3021720 · Cited by 34
“diagnosis for predicting rolling bearing failures is of particular significance [2], [3].”
BackgroundOCR-RCNN: An Accurate and Efficient Framework for Elevator Button Recognition
Zhu, D., Fang, Y., Min, Z., Ho, D., & Meng, M. Q. ‐. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3050357 · Cited by 35
“Before the wide application of deep learning [15], [16], the performance of button recognition is very limited due to the”
BackgroundZhang, K., Huang, W. K., Hou, X., Xu, J., Su, R., & Xu, H. (2021) · Applied Sciences · doi:10.3390/app11031251 · Cited by 35
“The deep-learning–based fault diagnosis model requires a large number of labeled training data for full training before accurate fault identification can be completed [31,36].”
BackgroundAn Efficient Incremental Learning of Bearing Fault Imbalanced Data Set via Filter StyleGAN
Wang, Y., Zeng, L., Wang, L., Shao, Y., Zhang, Y., & Ding, X. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3073436 · Cited by 34
Self-citationIoT-Based Monitoring in Carbon Capture and Storage Systems
Chawla, A., Arellano, Y., Johansson, M. V., Darvishi, H., Shaneen, K., Vitali, M., Finotti, F., & Rossi, P. S. (2022) · IEEE Internet of Things Magazine · doi:10.1109/iotm.001.2200175 · Cited by 34
“Some of these approaches are based on artificial neural networks, convolution neural networks [6] and deep learning [7].”
BackgroundZhao, Y., Hao, H., Chen, Y., & Zhang, Y. (2023) · Electronics · doi:10.3390/electronics12132826 · Cited by 39
Self-citationKrzysztofiak, M., Skowron, M., & Orlowska-Kowalska, T. (2020) · Energies · doi:10.3390/en14010153 · Cited by 33
Mu, L., Bi, S., Yu, S., Liu, X., & Ding, X. (2021) · Drying Technology · doi:10.1080/07373937.2021.1876722 · Cited by 38
“Wen et al. [28] presented a new CNN based on LeNet-5 for fault diagnosis, which performed feature extraction through converting the time-domain signals into two-dimensional images.”
MethodInfluentialA Rotating Machinery Fault Diagnosis Method Based on Multi-Sensor Fusion and ECA-CNN
Wang, H., Zhu, H., & Li, H. (2023) · IEEE Access · doi:10.1109/access.2023.3320065 · Cited by 34
“, 2017) [31] is a classical CNN model for fault diagnosis.”
BackgroundZhao, C., Du, T., Ge, B., Xi, Z., Qian, Z., Wang, Y., Wang, J., Dong, F., Shen, D., Zhan, Z., et al. (2023) · Small · doi:10.1002/smll.202307680 · Cited by 45
Zhang, H., Che, W., Cao, Y., Guan, Z., & Zhu, C. (2024) · Iranian Journal of Science and Technology Transactions of Mechanical Engineering · doi:10.1007/s40997-024-00783-w · Cited by 36
“CNN, Recurrent neural networks (RNN), auto-encoding networks (AE), long-short-term memory networks (LSTM), and others are the major components of deep learning (DL) (Wen et al. 2018; Qin et al. 2020; Liu et al. 2021b, a).”
Ayankoso, S. A., Dutta, A., He, Y., Gu, F., Ball, A. D., & Pal, S. K. (2024) · Structural Health Monitoring · doi:10.1177/14759217241289874 · Cited by 51
“5,7 Performing intelligent fault diagnosis often involves extracting features from preprocessed signals using techniques such as fast Fourier transform (FFT) and wavelet transform (WT).”
Liu, P. J., Zhao, S., Kang, L., & Yin, Y. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104871 · Cited by 35
A Model-Based Method for Leakage Detection of Piston Pump Under Variable Load Condition
Tang, H., Yang, W., & Wang, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2930816 · Cited by 33
Advancement of Mechanical Engineering in Extreme Environments
Qin, Z., Wu, Y.-T., Eizad, A., Lyu, S.-K., & Lee, C.-M. (2021) · International Journal of Precision Engineering and Manufacturing-Green Technology · doi:10.1007/s40684-020-00295-3 · Cited by 33
Xiong, S., Zhou, H., He, S., Zhang, L., & Shi, T. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/abe448 · Cited by 33
Karnavas, Y. L., Plakias, S., & Chasiotis, I. D. (2021) · IET Electric Power Applications · doi:10.1049/elp2.12063 · Cited by 33
“In [22], the raw vibration sensor signals are transformed into two‐dimensional images and, in the sequel, a CNN model based on LeNet‐5 architecture is used to detect and classify faults.”
MethodLi, F., Chen, J., He, S., & Zhou, Z. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3097408 · Cited by 38
Inspection of Defects in Weld Using Differential Array ECT Probe and Deep Learning Algorithm
Tao, X., Peng, L., Tao, Y., & Ye, C. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3099566 · Cited by 38
Tang, H., Gao, S., Wang, L., Li, X., Li, B., & Pang, S. (2021) · Sensors · doi:10.3390/s21206754 · Cited by 35
“proposed a LeNet-5-based CNN for fault diagnosis [38].”
Self-citationWu, H., Gan, D., Xu, C., Liu, Y., Liu, X., Song, Y., & Rao, Y. (2022) · Journal of Lightwave Technology · doi:10.1109/jlt.2022.3144147 · Cited by 33
Jia, X., Qin, N., Huang, D., Zhang, Y., & Du, J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.05.056 · Cited by 35
Self-citationHou, Z., Wang, H., Lv, S., Xiong, M., & Peng, K. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/aca044 · Cited by 32
“Experimental data 1: Bearing fault data of Case In this paper, the signal–picture conversion method proposed in [43] is adopted, and the specific mathematical description is as follows: where P ( m , n ) is the value of row m and column n in the 2D image; N represents that the size of the converted…”
Prior Knowledge-Augmented Meta-Learning for Fine-Grained Fault Diagnosis
Zhou, Y., Zhang, Q., Huang, T., & Cai, Z. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3367029 · Cited by 32
Liu, D., Cheng, W., & Wen, W. (2019) · IEEE Systems Journal · doi:10.1109/jsyst.2019.2929617 · Cited by 32
“[8] proposed a convolutional neural network-based method, which removes the effect of handcrafted features.”
MethodHu, T., Tang, T., & Chen, M. (2019) · IEEE Access · doi:10.1109/access.2019.2937838 · Cited by 35
Reliability‐based fault analysis models with industrial applications: A systematic literature review
Ahmed, Q., Raza, S. A., & Al-Anazi, D. M. (2020) · Quality and Reliability Engineering International · doi:10.1002/qre.2797 · Cited by 41
Du, B., He, Y., & Zhang, C. (2021) · IET Power Electronics · doi:10.1049/pel2.12094 · Cited by 36
“Data-driven approaches [23, 24] mainly involve four parts: Data acquisition, feature extraction, feature selection, and fault diagnosis.”
MethodEdge-cloud cooperation driven self-adaptive exception control method for the smart factory
Wang, W., Hu, T., & Gu, J. (2021) · Advanced Engineering Informatics · doi:10.1016/j.aei.2021.101493 · Cited by 33
Hou, S.-Z., Guo, W., Wang, Z., & Liu, Y.-T. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3133352 · Cited by 35
Liu, Y., Chen, Z., Wei, L., Wang, X., & Li, L. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3231287 · Cited by 32
Zhong, Y., Hao, J., Lliu, Q., Li, Y., Li, X., Liao, R., & Jiang, X. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3242805 · Cited by 31
“machine learning algorithms based on shallow models and manual feature screening [11].”
MethodSelf-citationEstimation of wheat biomass based on phenological identification and spectral response
Liu, T., Yang, T., Zhu, S., Mou, N., Zhang, W., Wu, W., Zhao, Y., Yao, Z., Sun, J., Chen, C., et al. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109076 · Cited by 31
He, Z., Cheng, J., Li, J., & Yang, Y. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.02.024 · Cited by 31
Wang, B., Shen, C., Xu, K., & Zheng, T. (2019) · IET Electric Power Applications · doi:10.1049/iet-epa.2019.0101 · Cited by 31
Intelligent Diagnostics for Bearing Faults Based on Integrated Interaction of Nonlinear Features
Bo, L., Liu, X., & Xu, G. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2943507 · Cited by 31
“To realize the automatic identification of production system states, some AI technologies including artificial neural networks [13], support vector machine (SVM) [2], convolutional neural network [14], hidden semi-Markov model [15], etc.”
MethodA Deep-Learning-Based Bearing Fault Diagnosis Using Defect Signature Wavelet Image Visualization
Duong, B. P., Kim, J. Y., Jeong, I.-K., Im, K., Kim, C. H., & Kim, J. M. (2020) · Applied Sciences · doi:10.3390/app10248800 · Cited by 32
“In addition, Do et al. [10] and Wen et al. [11] suggested a method to e ffi ciently extract features of the faults in a bearing with the vibration image.”
MethodPang, C., Duan, D., Zhou, Z., Han, S., Yao, L., Zheng, C., Yang, J. G., & Gao, X. (2022) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2022.01.062 · Cited by 33
Transfer Learning-Based Condition Monitoring of Single Point Cutting Tool
Venkatesh, S. N., Balaji, P. A., Elangovan, M., Annamalai, K., Indira, V., Sugumaran, V., & Mahamuni, V. S. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/3205960 · Cited by 30
“Roller bearing [33] CNN [27] Deep belief network and sparse autoencoder [34] Recurrent neural network [35] Stacked autoencoder Gear box [36] Generative adversarial network [37] CNN Centrifugal pump [38] Deep learning”
A State-Observer-Based Protection Scheme for AC Microgrids with Recurrent Neural Network Assistance
Mumtaz, F., Khan, H. H., Zafar, A., Ali, M. U., & Imran, K. (2022) · Energies · doi:10.3390/en15228512 · Cited by 31
Biswas, S., Panigrahi, B. K., Nayak, P. K., Pradhan, G., & Padmanaban, S. (2023) · IEEE Journal of Emerging and Selected Topics in Industrial Electronics · doi:10.1109/jestie.2023.3345791 · Cited by 31
Wan, L., Li, H., Chen, Y., & Li, C. (2020) · Energies · doi:10.3390/en13051094 · Cited by 33
“To further evaluate the effectiveness of the proposed method, the comparisons with the other four different fault classifiers based on deep learning are conducted, including VI-CNN [11], AlexNet [12], VGG-19 [13], and ResNet-50 [14].”
MethodInfluentialZhang, Q., Qi, Z., Cui, P., Xie, M., & Din, J. (2023) · Electric Power Systems Research · doi:10.1016/j.epsr.2023.109501 · Cited by 36
Dai, Y., Zhang, L., Xu, D., Chen, Q., & Li, J. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3342858 · Cited by 34
“In particular, once multiple types of faults occur simultaneously, the coupling between the different faults makes it extremely difficult to realize accurate fault diagnosis and classification tasks [6], [7].”
BackgroundAfshar, M., Heydarzadeh, M., & Akin, B. (2024) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2024.3462921 · Cited by 30
Lee, S.-B., Kim, H., Kim, Y.-T., Zeiler, F. A., Smielewski, P. S., Czosnyka, M., & Kim, D. (2019) · Journal of neurosurgery · doi:10.3171/2019.2.jns182260 · Cited by 35
Zhang, C., Feng, J., Hu, C., Liu, Z., Cheng, L., & Zhou, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2981289 · Cited by 31
Kumar, A., Ridha, S., Ganet, T., Vasant, P., & Ilyas, S. U. (2020) · Applied Sciences · doi:10.3390/app10072588 · Cited by 30
“[54] used deep convolutional neural network for diagnosing fault.”
MethodSparse stacked autoencoder network for complex system monitoring with industrial applications
Deng, Z., Li, Y., Zhu, H., Huang, K., Tang, Z., & Wang, Z. (2020) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2020.109838 · Cited by 30
Yu, J., & Liu, G. (2020) · Computers in Industry · doi:10.1016/j.compind.2020.103262 · Cited by 30
RetractedZhou, J., Shan, Y., Liu, J., Xu, Y., & Zheng, Y. (2020) · Sensors · doi:10.3390/s20154277 · Cited by 32
“This section consists of four parts: (1) analyze the monitoring data and construct the health model; (2) generate IDI series of degradation tendency using EW theory and PDIs; (3) construct the CNN-LSTM predict model; and (4) illustrate the general procedure of the proposed model.”
MethodIntelligent fault diagnosis of rolling bearings using a semi-supervised convolutional neural network
Wu, Y., Zhao, R., Jin, W., He, T., Ma, S., & Shi, M. (2020) · Applied Intelligence · doi:10.1007/s10489-020-02006-6 · Cited by 32
Riaz, N., Shah, S. I. A., Rehman, F., & Khan, M. J. (2021) · IEEE Access · doi:10.1109/access.2021.3062496 · Cited by 33
“These include LeNet [47], Adaptive deepCNN [56] by converting 1D signal to 2-D images and implementing adaptive deep CNN structure, RBF-SVM [21] by training time domain signal data feature parameters and our proposed hybrid scheme replacing Mc-SVM with Softmax [48].”
MethodAn Explainable Neural Network for Fault Diagnosis With a Frequency Activation Map
Kim, M. S., Yun, J. P., & Park, P. (2021) · IEEE Access · doi:10.1109/access.2021.3095565 · Cited by 32
Model-Based Deep Transfer Learning Method to Fault Detection and Diagnosis in Nuclear Power Plants
Yao, Y., Ge, D., Yu, J., & Xie, M. (2022) · Frontiers in Energy Research · doi:10.3389/fenrg.2022.823395 · Cited by 36
“…et al., 2015; Seabra et al., 2016), deep learning – based fault diagnosis methods such as the automatic deep encoder – decoder (Wang and Zhang, 2018), deep belief networks (DBNs) (Tang et al., 2018), and deep convolutional neural networks (CNNs) (Wen et al., 2017) are gradually coming into view.”
BackgroundSynthesizing Rolling Bearing Fault Samples in New Conditions: A Framework Based on a Modified CGAN
Ahang, M., Jalayer, M., Shojaeinasab, A., Ogunfowora, O., Charter, T., & Najjaran, H. (2022) · Sensors · doi:10.3390/s22145413 · Cited by 32
“Convolutional neural networks (CNNs) [5,6], stacked auto Encoders [7,8], and deep belief networks (DBNs)[9] are among the most studied algorithms that could reach very high accuracy.”
BackgroundYao, J., Liang, W., & Xiong, J. (2022) · International Journal of Pressure Vessels and Piping · doi:10.1016/j.ijpvp.2022.104781 · Cited by 31
Kao, S.-X., & Chien, C. (2023) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2023.3243775 · Cited by 39
“In particular, a convolutional neural network (CNN) has been employed to solve fault diagnosis problems in PHM such as diagnosing fault patterns with image data conversed from pump fault signals [20].”
MethodA Jointed Signal Analysis and Convolutional Neural Network Method for Fault Diagnosis
Wen, L., Gao, L., Li, X., Wang, L., & Zhu, J. (2018) · Procedia CIRP · doi:10.1016/j.procir.2018.03.117 · Cited by 32
Self-citationTang, T., Hu, T., Chen, M., Lin, R., & Chen, G. (2020) · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · doi:10.1177/0954406220902181 · Cited by 32
“31 TICNN directly uses one-dimensional raw signals in time domain for diagnosis, which can be considered as a state-of-art method.”
BackgroundZhou, P., Gao, B., Zhao, C., & Chai, T. (2023) · Control Engineering Practice · doi:10.1016/j.conengprac.2023.105479 · Cited by 31
Moysidis, D. A., Karatzinis, G. D., Boutalis, Y. S., & Karnavas, Y. L. (2023) · Machines · doi:10.3390/machines11111029 · Cited by 35
Wang, Z., Lu, H., Shi, Y., & Wang, X. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3336435 · Cited by 30
“4) Axial Piston Hydraulic Pump (APHP) dataset [34] consists of three datasets.”
BackgroundKnowledge-based Clustering Federated Learning for fault diagnosis in robotic assembly
Xiao, P., Wang, C., Lin, Z., Hao, Y., Chen, G., & Xie, L. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111792 · Cited by 33
Attention activation network for bearing fault diagnosis under various noise environments
Zhang, Y., Lin, L., Wang, J., Zhāng, W., Gao, S., & Zhang, Z. (2025) · Scientific Reports · doi:10.1038/s41598-025-85275-w · Cited by 32
Self-citationUnsupervised fault diagnosis method based on iterative multi‐manifold spectral clustering
Song, W., Wen, L., Gao, L., & Li, X. (2019) · IET Collaborative Intelligent Manufacturing · doi:10.1049/iet-cim.2019.0003 · Cited by 30
Self-citationGuo, Y., Zeng, Y., Fu, L., & Chen, X. (2019) · Sensors · doi:10.3390/s19092159 · Cited by 34
“The data-driven method requires a large amount of historical data to establish a fault diagnosis model without prior knowledge, and is suitable for systems that are difficult to establish an explicit model [4].”
MethodResearch on deep feature learning and condition recognition method for bearing vibration
Zhu, X., Luo, X., Zhao, J., Hou, D., Han, Z., & Wang, Y. (2020) · Applied Acoustics · doi:10.1016/j.apacoust.2020.107435 · Cited by 31
Wu, P., Nie, X., & Xie, G. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/abc6e3 · Cited by 31
“In reference [22], a new model based on LeNet5 is proposed for fault diagnosis.”
MethodLee, S., Yu, H., Yang, H., Song, I., Choi, J., Yang, J., Lim, G.-M., Kim, K., Choi, B.-K., & Kwon, J.-W. (2021) · Applied Sciences · doi:10.3390/app11041564 · Cited by 31
Li, Y., & Yang, C. (2021) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104197 · Cited by 33
Wang, G., & Zhang, F. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3117082 · Cited by 42
Zhou, X., Zhou, H., Wen, G., Huang, X., Lei, Z., Zhang, Z., & Chen, X. (2021) · Measurement · doi:10.1016/j.measurement.2021.110633 · Cited by 29
An adversarial model for electromechanical actuator fault diagnosis under nonideal data conditions
Wang, C., Tao, L., Ding, Y., Lü, C., & Ma, J. (2022) · Neural Computing and Applications · doi:10.1007/s00521-021-06732-x · Cited by 31
“In contrast, data-driven methods are good at establishing fault modes without any prior explicit models [7].”
MethodWang, H., & Li, Y. (2022) · IEEE Transactions on Reliability · doi:10.1109/tr.2022.3190942 · Cited by 32
“7 shows the validation accuracy curves of GRU, LSTM, WDCNN, and WenCNN under three noise conditions.”
BackgroundInfluentialProjected Gradient Descent Adversarial Attack and Its Defense on a Fault Diagnosis System
Ayas, M. Ş., Ayas, S., & Djouadi, S. M. (2022) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp55681.2022.9851334 · Cited by 38
“A convolutional neural network (CNN) based technique inspired by LeNet-5 was proposed for fault diagnosis in [9], where vibration signals of a motor bearing taken from a public dataset were converted into 2D gray-level images.”
MethodSun, S., Sun, L., Wang, J., & Gao, H. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3225189 · Cited by 31
“Wen et al. [13] transformed 1-”
Shao, Z., Li, W., Xiang, H., Yang, S., & Weng, Z. (2023) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-022-00844-x · Cited by 31
“Wen et al. [29] proposed a fault diagnosis method based on LeNet-5 model, and combined with a data enhancement method of signal-to-image conversion, the one-dimensional original signal is converted into two-dimensional images by the enhancement method.”
Yin, W., Xia, H., Wang, Z., Yang, B., Zhang, J., Jiang, Y., & Miyombo, M. E. (2022) · Annals of Nuclear Energy · doi:10.1016/j.anucene.2023.109700 · Cited by 28
Early and Intelligent Bearing Fault Detection Using Adaptive Superlets
Mitra, S. K., & Koley, C. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3245186 · Cited by 30
“First, time-series vibration signals were converted to gray-pixel images; then, the famous CNN model LeNet 5 was applied in [23] and [24].”
MethodA comprehensive review of mechanical fault diagnosis methods based on convolutional neural network
Hou, J., Lu, X., Zhong, Y., He, W., Zhao, D., & Zhou, F. (2023) · Journal of Vibroengineering · doi:10.21595/jve.2023.23391 · Cited by 36
“…find out the deep fault of feature representation relationship behind the data, through data mining, the deep fault feature representation relationship behind the data is found, and the mapping relationship between the data and the fault is established to detect and identify the fault source [11].”
BackgroundContinuous Wavelet Transform and CNN for Fault Detection in a Helical Gearbox
Lupea, I., & Lupea, M. (2025) · Applied Sciences · doi:10.3390/app15020950 · Cited by 28
“In Wen et al. [16], the time-domain raw signals fill the pixels (in the interval [0, 255]) of a 2D square-shaped gray image, which then feeds the modified LeNet-5 (a pre-trained CNN model) to solve the image classification task in fault diagnosis of rotating machinery.”
Modeling and diagnosis of industrial system using hybrid deep residual shrinkage network and XGBoost
Zhang, R., Li, Z., & Gao, F. (2025) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2025.107438 · Cited by 30
Research on bearing fault diagnosis based on machine learning and SHAP interpretability analysis
Wang, L., & Wu, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-25083-4 · Cited by 49
Thermal Error Modeling of Rotary Axis Based on Convolutional Neural Network
Wu, C., Xiang, S., & Wansheng, X. (2021) · Journal of Manufacturing Science and Engineering · doi:10.1115/1.4049494 · Cited by 28
Light-Weight CNN Enabled Edge-Based Framework for Machine Health Diagnosis
Mukherjee, I., & Tallur, S. G. (2021) · IEEE Access · doi:10.1109/access.2021.3088237 · Cited by 32
“The model sizes reported in literature vary from 17 kB [31] to as large as 50 317 kB [35] with as high as 1.”
BackgroundYang, S., Wang, Y., & Li, C. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac0741 · Cited by 29
“Several DL algorithms have already been introduced in the fault diagnosis field, such as convolutional neural network (CNN) [20], deep Boltzmann machine (DBM) [21], deep brief network (DBN) [22], and autoencoder (AE) [23, 24] et al. The deep representation of the original signals learned by DL…”
Application of Rotating Machinery Fault Diagnosis Based on Deep Learning
Cui, W., Meng, G., Wang, A., Zhang, X., & Ding, J. (2021) · Shock and Vibration · doi:10.1155/2021/3083190 · Cited by 35
“Some other researchers used gray image [100], wavelet packet energy diagram [101], infrared thermal image [102–104], root mean square diagram [105], feature statistics diagram [106], and other images as the input of CNN for fault diagnosis of rotating machinery.”
A novel method for quantitative fault diagnosis of photovoltaic systems based on data-driven
Guo, H., Hu, S., Wang, F., & Zhang, L. (2022) · Electric Power Systems Research · doi:10.1016/j.epsr.2022.108121 · Cited by 30
Transfer learning with inception ResNet-based model for rolling bearing fault diagnosis
Liu, Y., Li, J., Qijie, L. I., & Wang, Q. (2022) · Journal of Advanced Mechanical Design Systems and Manufacturing · doi:10.1299/jamdsm.2022jamdsm0023 · Cited by 28
A Multichannel MN-GCN for Wheelset-Bearing System Fault Diagnosis
Yuan, Z., Ma, Z., Li, X., & Li, J. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3227035 · Cited by 27
“With the development of the Internet of Things in the industry, diagnosing bearing health conditions has become the leading research direction [7].”
BackgroundSelf-citationLi, F., Dai, Z., Jiang, L., Chanfei, S., Zhong, C., & Chen, Y. (2024) · Sensors · doi:10.3390/s24216906 · Cited by 30
“For instance, Wen et al. proposed a CNN model based on LeNet-5 for fault diagnosis [25], which extracts features using a method that converts signals into 2D images, thereby eliminating the need for manual feature engineering.”
MethodDong, X., Zhang, C., Liu, H., Wang, D., Chen, Y., & Wang, T. (2025) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2025.01.037 · Cited by 29
Wen, L., Gao, L., Dong, Y., & Zhu, Z. D. (2019) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2019165 · Cited by 29
“Wen et al [43] studied a new time domain signal to gray image method.”
Self-citationLi, J., Wang, Y., Zi, Y., & Jiang, S. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2986853 · Cited by 29
Supervised Health Stage Prediction Using Convolutional Neural Networks for Bearing Wear
Suh, S., Jang, J., Won, S., Jha, M., & Lee, Y. O. (2020) · Sensors · doi:10.3390/s20205846 · Cited by 30
“The data-driven method can be further categorized into supervised [18] and unsupervised methods [19] in which supervised methods require training sets that are labeled.”
MethodA New Hydrogen Sensor Fault Diagnosis Method Based on Transfer Learning With LeNet-5
Sun, Y., Liu, S., Zhao, T., Zou, Z., Shen, B., Yu, Y., Zhang, S., & Zhang, H. (2021) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2021.664135 · Cited by 27
“Compared with Alenet, GoogLenet, VGG16, and other CNN algorithms, LeNet-5 method has simple structure and high accuracy (Wen et al., 2018; Lu et al., 2019), and has achieved good results in hydrogen sensor fault diagnosis (Sun et al., 2020).”
BackgroundMethodZhang, K., Liu, Y., Gu, Y., Ruan, X., & Wang, J. (2021) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2021.3087503 · Cited by 28
“Wen [23] proposed a signal-to-image conversion method for converting the raw signals into two-dimensional images that are more suitable for CNN processing.”
MethodTransfer learning-based deep CNN model for multiple faults detection in SCIM
Kumar, P., & Hati, A. S. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06205-1 · Cited by 34
Review of machine learning technologies and artificial intelligence in modern manufacturing systems
Nassehi, A., Zhong, R. Y., Li, X., & Epureanu, B. I. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-823657-4.00002-6 · Cited by 43
Self-citation
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.