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
Beyond 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
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 201–300 of 1,003
Yang, Y., Yin, J., Zheng, H., Li, Y., Xu, M., & Chen, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2994310 · Cited by 105
Fault diagnosis of various rotating equipment using machine learning approaches – A review
Manikandan, S., & Duraivelu, K. (2020) · Proceedings of the Institution of Mechanical Engineers Part E Journal of Process Mechanical Engineering · doi:10.1177/0954408920971976 · Cited by 107
Knowledge and data dual-driven transfer network for industrial robot fault diagnosis
Yin, T., Lü, N., Guo, G., Lei, Y., Wang, S., & Guan, X. (2022) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2022.109597 · Cited by 101
Machine Learning in Manufacturing towards Industry 4.0: From ‘For Now’ to ‘Four-Know’
Chen, T., Sampath, V., May, M. C., Shan, S., Jorg, O. J., Martín, J. J. A., Stamer, F., Fantoni, G., Tosello, G., & Calaon, M. (2023) · Applied Sciences · doi:10.3390/app13031903 · Cited by 130
“In addition, by converting time series data from sensors to 2D images [114], CNNs can be used to detect and diagnosis machine failure as well.”
MethodPan, T., Chen, J., Zhou, Z., Wang, C., & He, S. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2896665 · Cited by 100
“Nowadays, the popular deep learning models include convolutional neural network (CNN), deep belief network (DBN), autoencoders (AE), and the recurrent neural network [13]–[15].”
BackgroundYu, W., Liu, Y., Dillon, T. S., Rahayu, W. J., & Mostafa, F. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3096637 · Cited by 109
A new method for intelligent fault diagnosis of machines based on unsupervised domain adaptation
Lu, N., Xiao, H., Sun, Y., Han, M., & Wang, Y. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.10.039 · Cited by 97
Sun, S., Zhang, T., Qin, L., Wang, J., Zhang, W., Wen, Z., & Tang, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3045798 · Cited by 105
“Wen et al. [17] used the transfer CNN (TCNN) for fault diagnosis and converted the time-domain signal into images as the input of TCNN. Xu et al. [18] used the short-time Fourier transform (STFT) of the extracted rolling bearing vibration signal to obtain the time–frequency image as the input of…”
MethodMultireceptive Field Denoising Residual Convolutional Networks for Fault Diagnosis
Xu, Y., Yan, X., Sun, B., Zhai, J., & Liu, Z. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3125666 · Cited by 99
Rolling Bearing Fault Diagnosis Based on Markov Transition Field and Residual Network
Yan, J., Kan, J., & Luo, H. (2022) · Sensors · doi:10.3390/s22103936 · Cited by 106
“In some scenarios, raw one-dimensional signals are converted into two-dimensional gray images with pixels fulfilled by data stacking [25,26].”
BackgroundWen, G., Gao, Z., Cai, Q., Wang, Y., & Mei, S. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3007292 · Cited by 99
“However, these traditional vision methods are unable to generate discriminative features [6] of input image and are always combined with other approaches to specific issues [19]–[21].”
BackgroundMethodInfluentialChen, P., Li, Y., Wang, K., Zuo, M. J., Heyns, P. S., & Baggerohr, S. (2020) · Measurement · doi:10.1016/j.measurement.2020.108234 · Cited by 98
“Conversely, for data-driven approaches like machine learning techniques, they are not only having the capability of generalization but also have been proven to be effective in various applications of fault diagnosis and HCM [2,14–16].”
Industrial Image Anomaly Localization Based on Gaussian Clustering of Pretrained Feature
Wan, Q., Gao, L., Li, X., & Wen, L. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3094452 · Cited by 94
“W ITH the development of the smart manufacturing system, automatic methods have been developed in various fields, such as quality inspection [1]–[4], fault diagnosis [5]–[7],”
MethodSelf-citationBattery health prognosis using improved temporal convolutional network modeling
Zhou, D., & Wang, B. (2022) · Journal of Energy Storage · doi:10.1016/j.est.2022.104480 · Cited by 101
Fault detection and diagnosis of marine diesel engines: A systematic review
Lv, Y., Yang, X., Li, Y., Liu, J., & Li, S. (2024) · Ocean Engineering · doi:10.1016/j.oceaneng.2024.116798 · Cited by 105
Hang, J., Qiu, G., Hao, M., & Ding, S. (2024) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2024.3432163 · Cited by 107
Prognostics and Health Management of Industrial Assets: Current Progress and Road Ahead
Biggio, L., & Kastanis, I. (2020) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2020.578613 · Cited by 126
“An additional strategy is proposed in Wen et al. (2018), where the following mapping is applied to convert time-series data into twodimensional images: P(j, k) round{L((j − 1) ×M + k) −Min(L) Max(L) −Min(L) × 255}, (9) 6We use the notation “(1D)2D-CNN” to indicate a CNN architecture with (one)…”
MethodCaiazzo, B., Nardo, M. D., Murino, T., Petrillo, A., Piccirillo, G., & Santini, S. (2021) · Computers in Industry · doi:10.1016/j.compind.2021.103548 · Cited by 112
A new subset based deep feature learning method for intelligent fault diagnosis of bearing
Zhang, Y., Li, X., Gao, L., & Li, P. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.05.032 · Cited by 92
Self-citationWu, H., Yang, M., Yang, S., Lu, H., Wang, C., & Rao, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3004207 · Cited by 92
“Then along with rapid development of the deep learning algorithms and their successful applications in image processing [28], [29], speech recognition [30] and fault diagnosis [31] and etc.”
BackgroundA New Fault Diagnosis of Rolling Bearing Based on Markov Transition Field and CNN
Wang, M., Wang, W., Zhang, X., & Iu, H. H. (2022) · Entropy · doi:10.3390/e24060751 · Cited by 92
“realized fault diagnosis on multiple platforms such as rolling bearings by converting original vibration signals into figures and combining with CNN [28].”
MethodState-of-the-Art Technologies in Fault Diagnosis of Electric Vehicles: A Component-Based Review
Choudhary, A., Fatima, S., & Panigrahi, B. K. (2022) · IEEE Transactions on Transportation Electrification · doi:10.1109/tte.2022.3209166 · Cited by 112
“and DL algorithms have made significant progress [272].”
BackgroundSun, M., Wang, H., Liu, P., Huang, S., Wang, P., & Meng, J. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3066933 · Cited by 93
Li, Y., Zou, W., & Jiang, L. (2022) · Measurement · doi:10.1016/j.measurement.2022.110826 · Cited by 103
Xue, Y., Wen, C., Wang, Z., Liu, W., & Chen, G. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.111205 · Cited by 96
Luo, X., Wang, H., Han, T., & Zhang, Y. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3381688 · Cited by 91
Self-citationAugmented Multidimensional Convolutional Neural Network for Industrial Soft Sensing
Jiang, X., & Ge, Z. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3075515 · Cited by 98
“Wen et al. [18] proposed a CNN-based fault diagnosis method for rotating machinery to eliminate the influence of manual features.”
MethodResearch on bearing fault diagnosis method based on transformer neural network
Yang, Z., Cen, J., Liu, X., Xiong, J., & Chen, H. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac66c4 · Cited by 103
“The proposed SiT-32 is compared with the following existing methods: the combination of feature enhancement and probabilistic neural network (SURF + PNN) [34], CNN [35], deep transfer convolutional neural network (TCNN) [36] and CLFormer [25].”
Remaining Useful Life Prediction Based on Deep Learning: A Survey
Wu, F., Wu, Q., Tan, Y., & Xu, X. (2024) · Sensors · doi:10.3390/s24113454 · Cited by 154
“The structure of a CNN is a key factor that affects the accuracy of the generated health indicator [53].”
BackgroundA survey on fault diagnosis of rotating machinery based on machine learning
Wang, Q., Huang, R., Xiong, J., Yang, J., Dong, X., Wu, Y., Wu, Y., & Lu, T. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad6203 · Cited by 107
“CNN has demonstrated excellent performance in several fields, including image processing [126, 127] and sound recognition [128, 129] However, in the field of rotating machinery fault diagnosis, it still faces a number of challenges, such as model generalization, overfitting phenomena, real-time…”
Ma, S., Liu, W., Cai, W., Shang, Z., & Liu, G. (2019) · IEEE Access · doi:10.1109/access.2019.2912072 · Cited by 96
“[22] transformed a raw signal into a square matrix through nonoverlapping cutting and normalized the value to 0-255, which was regarded as an image directly using”
BackgroundFault Diagnosis for Energy Internet Using Correlation Processing-Based Convolutional Neural Networks
Yang, D., Pang, Y., Zhou, B., & Li, K. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2919940 · Cited by 94
“Wen et al. [28] presented a conversion method converting signals into 2-”
MethodMulti-label fault diagnosis of rolling bearing based on meta-learning
Yu, C., Ning, Y., Qin, Y., Su, W., & Zhao, X. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05345-0 · Cited by 95
“Wen et al. [14] transformed the vibration signals into two-dimensional images and adopted a convolutional neural network (CNN) through the study of LeNet-5 to diagnose failures occurring in rolling bearing.”
MethodFault Knowledge Transfer Assisted Ensemble Method for Remaining Useful Life Prediction
Xia, P., Huang, Y., Li, P., Liu, C., & Shi, L. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3081595 · Cited by 95
Yu, S., Wang, M., Pang, S., Song, L., & Qiao, S. (2022) · Measurement · doi:10.1016/j.measurement.2022.111228 · Cited by 90
A Deep Learning Method for Bearing Fault Diagnosis through Stacked Residual Dilated Convolutions
Zhuang, Z., Lv, H., Xu, J., Huang, Z., & Wei, Q. (2019) · Applied Sciences · doi:10.3390/app9091823 · Cited by 93
“Wen et al. [20] developed an e ff ective data preprocessing method to convert the time-domain raw signals into images, and built a new CNN based on LeNet-5 to make full use of the experience related to CNN from image processing.”
MethodDeep Learning Algorithms for Bearing Fault Diagnostics - A Review
Zhang, S., Zhang, S., Wang, B., & Habetler, T. G. (2019) · IEEE International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives (SDEMPED) · doi:10.1109/demped.2019.8864915 · Cited by 96
“Some other variations of CNN are also employed to tackle the bearing fault diagnosis challenge [25], [26] on the CWRU dataset to obtain more desirable characteristics compared to the conventional CNN.”
BackgroundMethodSingh, J., Azamfar, M., Li, F., & Lee, J. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/ab8df9 · Cited by 104
Yu, J., & Liu, J. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.3013492 · Cited by 94
“In recent years, deep learning is becoming a hot topic in the area of machine learning, leading a series of breakthroughs in both academia and industry [16]–[19].”
BackgroundHan, H., Wang, H., Liu, Z., & Wang, J. (2021) · ISA Transactions · doi:10.1016/j.isatra.2021.04.022 · Cited by 90
Lyu, P., Zhang, K., Yu, W., Wang, B., & Liu, C. (2022) · Advanced Engineering Informatics · doi:10.1016/j.aei.2022.101564 · Cited by 92
Wu, J., Tang, T., Chen, M., Wang, Y., & Wang, K. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113710 · Cited by 94
Liang, P., Deng, C., Wu, J., Yang, Z., Zhu, J., & Zhang, Z. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.105895 · Cited by 86
Valtierra‐Rodriguez, M., Rivera‐Guillen, J. R., Basurto-Hurtado, J. A., De-Santiago-Perez, J. J., Granados‐Lieberman, D., & Amézquita-Sánchez, J. P. (2020) · Sensors · doi:10.3390/s20133721 · Cited by 84
Deep convolutional neural network based on adaptive gradient optimizer for fault detection in SCIM
Kumar, P., & Hati, A. S. (2020) · ISA Transactions · doi:10.1016/j.isatra.2020.10.052 · Cited by 96
Deep prototypical networks based domain adaptation for fault diagnosis
Wang, H., Bai, X., Tan, J., & Yang, J. (2020) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-020-01709-4 · Cited by 91
Santolamazza, A., Dadi, D., & Introna, V. (2021) · Energies · doi:10.3390/en14071845 · Cited by 82
“…Zhao, 2018 Gearbox, generator Deep auto-encodernetwork Yes SCADA data [72] Yang et al., 2018 Wind turbine Multivariate EWMA 6 Yes SCADA data [73] Wen et al., 2018 Variouscomponents CNN 7 No SCADA data [49] Wang et al., 2018 Gearbox, generator PCA 5, ANN Yes SCADA data [74] Zhang e Lang, 2018…”
BackgroundPham, M. T., Kim, J.-M., & Kim, C. H. (2022) · IEEE Access · doi:10.1109/access.2022.3193244 · Cited by 84
Ma, R., Han, T., & Lei, W. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110175 · Cited by 88
Liao, J.-X., Dong, H., Sun, Z., Sun, J., Zhang, S., & Fan, F. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3259031 · Cited by 106
“[8] first folded 1-D time-domain signals into 2-D images, and then used LeNet-5 as a backbone to classify these images.”
BackgroundMethodKeshun, Y., Qiu, G., & Gu, Y. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/acd5ef · Cited by 84
“…learning (DL) algorithms, which also was widely applied to the rolling bearing fault diagnosis [18], such as adaptive CNN [19], LeNet-5 based CNN [20], deep fully convolutional neural network [21], multi-scale CNN (MS-DCNN) [22], full graph dynamic autoencoder [23], adaptive overlapping CNN…”
A Novel Local Binary Temporal Convolutional Neural Network for Bearing Fault Diagnosis
Xue, Y., Yang, R., Chen, X., Tian, Z., & Wang, Z. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3298653 · Cited by 88
“Additionally, for the CNN-based lightweight models [46], [47], [48], [49], the limited network depth and width of lightweight model may cause difficulty in extracting latent variables and in-depth features, leading to limited model performance and representation ability, thus ultimately affecting…”
BackgroundMethodFault Diagnosis for Power Converters Based on Optimized Temporal Convolutional Network
Gao, Y., Wang, W., Lin, Q., Cai, F., & Chai, Q. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3021110 · Cited by 86
“In [14], a CNN model with four alternating convolutional and pooling layers and two fully connected (FC) layers was built and successfully performed in diagnosing the motor bearing faults, self-priming centrifugal pump faults, and axial piston hydraulic pump faults.”
MethodA General Transfer Framework Based on Industrial Process Fault Diagnosis Under Small Samples
Liu, J., & Ren, Y. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3036159 · Cited by 85
“High-precision fault diagnosis model establishment requires sufficient training of fault samples in the industrial process [2].”
BackgroundEom, Y. H., Chung, Y., Park, M., Hong, S. B., & Kim, M. S. (2021) · Energy · doi:10.1016/j.energy.2021.120542 · Cited by 81
Yang, C., Wang, Y., Lan, S., Wang, L., Shen, W., & Huang, G. Q. (2022) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2022.102351 · Cited by 99
A zero-shot learning method for fault diagnosis under unknown working loads
Gao, Y., Gao, L., Li, X., & Zheng, Y. (2019) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-019-01485-w · Cited by 80
Self-citationDe Silva, D., Sierla, S., Alahakoon, D., Osipov, E., Yu, X., & Vyatkin, V. (2020) · IEEE Industrial Electronics Magazine · doi:10.1109/mie.2019.2952165 · Cited by 80
Zhang, W., Yang, D., Xu, Y., Huang, X., Zhang, J., & Gidlund, M. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3029551 · Cited by 87
“[15] deployed an end-to-end learning model using the convolutional neural network (CNN) to extract hidden”
MethodKolar, D., Lisjak, D., Pająk, M., & Gudlin, M. (2021) · Sensors · doi:10.3390/s21072411 · Cited by 88
“Researchers using 2D architecture additionally explored either signal processing methods [17–20], manually constructed signal matrix [21,22] to enable CNN or used health state image like infrared thermal image [23] or grey scale image [24].”
MethodA new ensemble residual convolutional neural network for remaining useful life estimation
Wen, L., Dong, Y., & Gao, L. (2019) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2019040 · Cited by 86
Self-citationA Fast Anomaly Diagnosis Approach Based on Modified CNN and Multisensor Data Fusion
Gong, W., Wang, Y., Zhang, M., Mihankhah, E., Chen, H., & Wang, D. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3135520 · Cited by 79
Rolling Bearing Fault Diagnosis Using Hybrid Neural Network with Principal Component Analysis
Keshun, Y., Qiu, G., & Gu, Y. (2022) · Sensors · doi:10.3390/s22228906 · Cited by 90
“Examples include Adaptive CNN (ADCNN) [42], LeNet-5 based CNN [43], Deep Fully Convolutional Neural Network (DFCNN) [44], Multiscale CNN (MS-DCNN) [45], Pythagorean Spatial Pyramidal Pooling (PSPP) CNN [46], and Adaptive Overlapping CNN (AOCNN) [47].”
InfluentialXiao, B., & Yin, S. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.3026272 · Cited by 78
“3) Although the proposed approach and the FDD presented in [30], [31], and [35] are developed by converting the input signals into a 2-”
BackgroundMethodSurrogate Modeling of Electrical Machine Torque Using Artificial Neural Networks
Tahkola, M., Keränen, J., Sedov, D., Far, M. F., & Kortelainen, J. (2020) · IEEE Access · doi:10.1109/access.2020.3042834 · Cited by 86
“[57] propose a CNN-based approach to convert time-domain measurement signals into two-dimensional images, from which relevant features are then extracted.”
BackgroundA novel feature adaptive extraction method based on deep learning for bearing fault diagnosis
Zhang, T., Liu, S., Wei, Y., & Zhang, H. (2021) · Measurement · doi:10.1016/j.measurement.2021.110030 · Cited by 82
A review on convolutional neural network in rolling bearing fault diagnosis
Li, X., Ma, Z., Yuan, Z., Mu, T., Du, G., Liang, Y., & Liu, J. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad356e · Cited by 92
“With the development of CNN, many classic models have also emerged, such as LeNet [19, 20], ResNet [21–23], AlexNet [24, 25], DenseNet [26–28], Vgg [29, 30], GoogleNet [31–33], etc.”
Self-citationRolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network
Wan, L., Chen, Y., Li, H., & Li, C. (2020) · Sensors · doi:10.3390/s20061693 · Cited by 88
“As shown in Figure 13 and Table 9, the difference of diagnosis accuracy of AlexNet, VGG-19, ResNet-50 and the proposed improved 2D LeNet-5 network is very small, but the training time of AlexNet, VGG-19 and ResNet-50 are 1.67 times, 2.39 times and 4.24 times as long as that of improved 2D LeNet-5 network respectively.”
MethodInfluentialDistributed-ensemble stacked autoencoder model for non-linear process monitoring
Li, Z., Tian, L., Jiang, Q., & Yan, X. (2020) · Information Sciences · doi:10.1016/j.ins.2020.06.062 · Cited by 85
A Pipeline Leak Detection and Localization Approach Based on Ensemble TL1DCNN
Zhou, M., Yang, Y., Xu, Y., Hu, Y., Cai, Y., Lin, J., & Pan, H. (2021) · IEEE Access · doi:10.1109/access.2021.3068292 · Cited by 81
“convolutional neural network (2DCNN) for fault diagnosis in the early stage [18]–[21].”
BackgroundXiong, J., Li, C., Wang, C., Cen, J., Wang, Q., & Wang, S. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3073755 · Cited by 81
Shahid, S. M., Ko, S.-H., & Kwon, S. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.116233 · Cited by 80
A Dual-Stage-Recognition Network for Distributed Optical Fiber Sensing Perimeter Security System
He, T., Sun, Q., Zhang, S.-X., Li, H., Yan, B., Fan, C., Yan, Z., & Liu, D. (2022) · Journal of Lightwave Technology · doi:10.1109/jlt.2022.3222472 · Cited by 77
“optic DAS system for accurate identification of intrusion events [14], [15], [16], [17], [18], [19].”
BackgroundAlShorman, O., Irfan, M., Abdelrahman, R. B., Masadeh, M., Alshorman, A. M., Sheikh, M. A., Saad, N. B., & Rahman, S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107724 · Cited by 89
A deep domain adaption model with multi-task networks for planetary gearbox fault diagnosis
Cao, X., Chen, B., & Zeng, N. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.05.064 · Cited by 78
Yu, J., Zhang, C., & Wang, S. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05171-4 · Cited by 80
Ullah, Z., Lodhi, B. A., & Hur, J. (2020) · Energies · doi:10.3390/en13153834 · Cited by 82
Peng, T., Shen, C., Sun, S., & Wang, D. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3111567 · Cited by 76
A Survey of Intelligent Tires for Tire-Road Interaction Recognition Toward Autonomous Vehicles
Yang, S., Chen, Y., Shi, R., Wang, R., Cao, Y., & Lu, J. (2022) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3163588 · Cited by 81
Wang, C., Yang, J., & Zhang, B. (2024) · Measurement · doi:10.1016/j.measurement.2024.114171 · Cited by 80
Deep transfer network for rotating machine fault analysis
Qian, W., Li, S., & Jiang, X. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.106993 · Cited by 76
NOSCNN: A robust method for fault diagnosis of RV reducer
Peng, P., & Wang, J. (2019) · Measurement · doi:10.1016/j.measurement.2019.02.080 · Cited by 79
Yan, X., Liu, Y., & Jia, M. (2019) · Structural Health Monitoring · doi:10.1177/1475921719893594 · Cited by 75
Liu, T., Xu, H. G., Ragulskis, M., Cao, M., & Ostachowicz, W. M. (2020) · Sensors · doi:10.3390/s20041059 · Cited by 81
Li, T., Zhao, Z., Sun, C., Yan, R., & Chen, X. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2980596 · Cited by 77
A New Interpretable Learning Method for Fault Diagnosis of Rolling Bearings
Zhang, D., Chen, Y., Guo, F., Karimi, H. R., Dong, H. F., & Xuan, Q. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3043873 · Cited by 75
“Various DL architectures, such as convolutional neural network (CNN) [3], deep belief network (DBN) [4], sparse autoencoder [5], and recurrent neural network [6], are widely used in the field of fault diagnosis of mechanical equipment.”
BackgroundA New Semi-Supervised Fault Diagnosis Method via Deep CORAL and Transfer Component Analysis
Li, X., Zhang, Z., Gao, L., & Wen, L. (2021) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2021.3115666 · Cited by 77
Self-citationA model fusion strategy for identifying aircraft risk using CNN and Att-BiLSTM
Zhou, D., Zhuang, X. D., Zuo, H., Cai, J., Zhao, X., & Xiang, J. (2022) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2022.108750 · Cited by 75
Learning Deep Correlated Representations for Nonlinear Process Monitoring
Jiang, Q., & Yan, X. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2886048 · Cited by 79
“Currently, the most widely used DNNs in fault diagnosis include deep belief networks (DBNs) [1], convolutional neural networks [26]–[28], and stacked au-”
MethodA Novel Deep Learning Framework for Industrial Multiphase Flow Characterization
Dang, W., Gao, Z., Hou, L., Lv, D., Qiu, S., & Chen, G. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2908211 · Cited by 79
“Many CNN architectures have been introduced in the literature [27], [39].”
BackgroundHe, Y., Zhao, Y., Hu, X., Yan, X., Zhu, Q., & Xu, Y. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.103631 · Cited by 74
Intelligent fault diagnosis of bearings under small samples: A mechanism-data fusion approach
Xu, K., Kong, X., Wang, Q., Han, B., & Sun, L. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107063 · Cited by 76
Multi-Resolution LSTM-Based Prediction Model for Remaining Useful Life of Aero-Engine
Xu, T., Han, G., Zhu, H., Taleb, T., & Peng, J. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3319377 · Cited by 85
“As a result, research into deep learning-based RUL prediction methods is becoming increasingly active, with an emphasis on improving prediction accuracies, such as the merging of deep learning models with current models, structure, and parameter optimization [13], [14].”
BackgroundLong short-term memory models of water quality in inland water environments
Pyo, J., Pachepsky, Y. A., Kim, S., Abbas, A., Kim, M., Kwon, Y. S., Ligaray, M. V., & Cho, K. H. (2023) · Water Research X · doi:10.1016/j.wroa.2023.100207 · Cited by 125
“One of the successful methods of feature extraction is implemented in convolutional neural networks (CNNs) (Wen et al., 2017).”
BackgroundMethodIn Situ Motor Fault Diagnosis Using Enhanced Convolutional Neural Network in an Embedded System
Lu, S., Qian, G., He, Q., Liu, F., Liu, Y., & Wang, Q. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2911299 · Cited by 79
“A vibration signal was transformed to a 2D matrix and then inputted to the CNN in [33].”
MethodLiao, Y., Qing, X., Wang, Y., & Zhang, F. (2023) · Composite Structures · doi:10.1016/j.compstruct.2023.116871 · Cited by 73
A three-dimensional geometric features-based SCA algorithm for compound faults diagnosis
Hao, Y., Song, L., Cui, L., & Wang, H. (2018) · Measurement · doi:10.1016/j.measurement.2018.10.098 · Cited by 73
Convolutional Neural Network‐Based Intelligent Protection Strategy for Microgrids
Bukhari, S. B. A., Kim, C., Mehmood, K. K., Haider, R., & Zaman, M. S. U. (2020) · IET Generation Transmission & Distribution · doi:10.1049/iet-gtd.2018.7049 · Cited by 73
Liu, W., Zhu, C. G., & Zheng, M. (2020) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc45564.2020.9148044 · Cited by 91
“[24] proposed an approach to transfer the features of the raw data from datasets to two-dimensional images, and utilized a classical release of CNN named LeNet-5 to do fault diagnosis.”
MethodLi, J., Zhang, X., Zhou, Q., Chan, F. T. S., & Hu, Z. Y. (2022) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2022.10.050 · Cited by 77
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.