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 301–400 of 1,003
Fault Detection for Motor Drive Control System of Industrial Robots Using CNN-LSTM-based Observers
Wang, T., Zhang, L., & Wang, X. (2023) · CES Transactions on Electrical Machines and Systems · doi:10.30941/cestems.2023.00014 · Cited by 83
Chen, J., Lin, C., Yao, B., Yang, L., & Ge, H. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109343 · Cited by 76
A Novel Sparse Echo Autoencoder Network for Data-Driven Fault Diagnosis of Delta 3-D Printers
Long, J., Sun, Z., Li, C., Hong, Y., Bai, Y., & Zhang, S. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2905752 · Cited by 76
A fault diagnosis method based on one-dimensional data enhancement and convolutional neural network
Long, Y., Zhou, W., & Luo, Y. (2021) · Measurement · doi:10.1016/j.measurement.2021.109532 · Cited by 78
Liu, X., Xia, L., Shi, J., Zhang, L., Bai, L., & Wang, S. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3265409 · Cited by 72
“D vibration grayscale images [15], [16], time–frequency images [17], [18], [19], Gramian angular summation/difference fields and Markov transition fields [20], symmetrized dot pattern [21], [22], and recurrence plot (RP) [23], [24], [25], [26], [27].”
BackgroundBearing fault diagnosis with parallel CNN and LSTM
Fu, G., Wei, Q., & Yang, Y. (2024) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2024105 · Cited by 78
“Wen et al. [46] designed an improved LeNet⁃5 network with high diagnostic accuracy which could convert the original 1D signal into 2D images and then directly extract features from the latter.”
BackgroundA New Convolutional Neural Network With Random Forest Method for Hydrogen Sensor Fault Diagnosis
Sun, Y., Zhang, H., Zhao, T., Zou, Z., Shen, B., & Yang, L. (2020) · IEEE Access · doi:10.1109/access.2020.2992231 · Cited by 78
“used a CNN for fault diagnosis [30]; and Qinyu Jiang et al.”
MethodAn ARMA-Based Digital Twin for MEMS Gyroscope Drift Dynamics Modeling and Real-Time Compensation
Tu, Y.-H., & Peng, C.-C. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3028140 · Cited by 71
“For the complex systems, the ANNs algorithms are quite suitable for constructing the models or signal symptoms in mathematical form [35], [36].”
MethodNovel Analog Implementation of a Hyperbolic Tangent Neuron in Artificial Neural Networks
Shakiba, F. M., & Zhou, M. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.3034856 · Cited by 79
Toma, R. N., Kim, C. H., & Kim, J.-M. (2021) · Electronics · doi:10.3390/electronics10111248 · Cited by 71
“This method has proven to be efficient for fault diagnosis with a vibration signal [49,50].”
MethodA Lighted Deep Convolutional Neural Network Based Fault Diagnosis of Rotating Machinery
Ma, S., Cai, W., Liu, W., Shang, Z., & Liu, G. (2019) · Sensors · doi:10.3390/s19102381 · Cited by 74
“Consequently, there are increasingly higher “small-size, lightweight, and rapidness” requirements for DL algorithms [25,29].”
BackgroundMethodGarcia, G. R., Michau, G., Ducoffe, M., Gupta, J. S., & Fink, O. (2021) · Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability · doi:10.1177/1748006x21994446 · Cited by 82
“Grey scale encoding has been revisited in Wen et al. 26 for the purpose of fault diagnosis in manufacturing systems using convolutional neural networks.”
Ensemble 1-D CNN diagnosis model for VRF system refrigerant charge faults under heating condition
Cheng, H.-D., Chen, H., Li, Z., & Cheng, X. (2020) · Energy and Buildings · doi:10.1016/j.enbuild.2020.110256 · Cited by 69
Xu, D., Qiu, H., Gao, L., Yang, Z., & Wang, D. (2022) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2022.108444 · Cited by 72
Self-citationXiong, S., Zhou, H., He, S., Zhang, L., Xia, Q., Xuan, J., & Shi, T. (2020) · Sensors · doi:10.3390/s20174965 · Cited by 74
“…appropriate 2D-format data VGGNet and 2D - CNN separately fold up the time-series signal into an appropriate 2D-format data matrix as input [47], while 1D - CNN directly receives raw 1D vibration signal as input. matrix as input [47], while 1D-CNN directly receives raw 1D vibration signal as input.”
MethodConvolutional Neural Network-Based Inter-Turn Fault Diagnosis in LSPMSMs
Maraaba, L. S., Milhem, A. S., Nemer, I. A., Al-Duwaish, H., & Abido, M. A. (2020) · IEEE Access · doi:10.1109/access.2020.2991137 · Cited by 72
“These layers comprise a set of neurons with biases, weights, and activation functions [38].”
BackgroundMethodHallaji, S. M., Fang, Y., & Winfrey, B. K. (2021) · Automation in Construction · doi:10.1016/j.autcon.2021.104049 · Cited by 86
Liu, X., Lu, J., & Li, Z. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3298712 · Cited by 70
“The results show that there is a significant difference between MSFACNN and CNN [26], CNN + CBAM [27], SEnet [28], ResNet18 [29], MSACNN [30], DRSN [18], and TICNN [31] as the P-values are all less than 0.05 whether under two datasets or from the overall perspective.”
BackgroundInfluentialBearing fault diagnosis based on CNN-BiLSTM and residual module
Fu, G., Wei, Q., Yang, Y., & Li, C. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/acf598 · Cited by 79
“…et al [16] transformed the WT vibration signals into time– frequency images as inputs and accomplished fault identification through CNN. Wen et al [39] improved upon the LeNet-5 network by converting the raw vibration signals into two-dimensional images before entering the model, then by…”
Deep Self-Organizing Maps for Unsupervised Image Classification
Wickramasinghe, C. S., Amarasinghe, K., & Manic, M. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2906083 · Cited by 71
“Successful mining of these images (classification, clustering) can lead to several advantages including process optimization, fault diagnosis, and improved cyber security [1], [3]–[7].”
BackgroundKolar, D., Lisjak, D., Pająk, M., & Pavković, D. (2020) · Sensors · doi:10.3390/s20144017 · Cited by 75
“Similarly, Wen et al. in [27] signal-to-2D image conversion as a step to extracting They also defined the process of converting a signal to a 2D grayscale image as a way of preprocessing. features based on the LeNet Further on, Shaheryar et al. [28] explored CNN in fault identification with…”
MethodYin, H., Li, Z., Zuo, J., Liu, H., Yang, K., & Li, F. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/2604191 · Cited by 70
“In order to achieve a better balance between training speed and accuracy, adaptive CNN (ADCNN) was applied to the CWRU dataset to change the learning rate dynamically in [26].”
MethodMachine fault detection methods based on machine learning algorithms: A review
Ciaburro, G. (2022) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2022534 · Cited by 90
“[110] applied CNNs to develop a method of diagnosing mechanical component failures.”
MethodEfficient federated learning for fault diagnosis in industrial cloud-edge computing
Wang, Q., Li, Q., Wang, K., Wang, H., & Zeng, P. (2021) · Computing · doi:10.1007/s00607-021-00970-6 · Cited by 81
Gundewar, S. K., & Kane, P. V. (2022) · Measurement · doi:10.1016/j.measurement.2022.111855 · Cited by 71
Zheng, H., Wang, R., Yin, J., Li, Y., Lu, H., & Xu, M. (2019) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2019.106344 · Cited by 68
Fault diagnosis of the bushing infrared images based on mask R‐CNN and improved PCNN joint algorithm
Jiang, J., Bie, Y., Li, J., Yang, X., Ma, G., Lu, Y., & Zhang, C. (2020) · High Voltage · doi:10.1049/hve.2019.0249 · Cited by 69
Park, C. H., Kim, H., Suh, C., Chae, M., Yoon, H., & Youn, B. D. (2022) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2022.108715 · Cited by 70
Bhuiyan, M. R., & Uddin, J. (2023) · Vibration · doi:10.3390/vibration6010014 · Cited by 84
“In [90], existing failure diagnosis (FD) techniques cannot be used on different types of multiphase machines due to varying stator phase layouts.”
BackgroundEang, C., & Lee, S. (2024) · Sensors · doi:10.3390/s25010025 · Cited by 99
“A typical CNN consists of convolutional layers for feature detection, pooling layers for dimensionality reduction, and fully connected layers for final classification [46–48].”
Online fault monitoring based on deep neural network & sliding window technique
Saeed, H. A., Wang, H., Peng, M., Hussain, A., & Nawaz, A. (2020) · Progress in Nuclear Energy · doi:10.1016/j.pnucene.2019.103236 · Cited by 62
CAFD: Context-Aware Fault Diagnostic Scheme towards Sensor Faults Utilizing Machine Learning
Saeed, U., Lee, Y.-D., Jan, S. U., & Koo, I. (2021) · Sensors · doi:10.3390/s21020617 · Cited by 75
“In [20], the authors proposed a Convolutional Neural Network (CNN)-based fault diagnosis method by image classification.”
BackgroundZhang, Y., & Yu, J. (2022) · Journal of Process Control · doi:10.1016/j.jprocont.2022.03.010 · Cited by 65
Self-citationHuang, K., Wu, S., Sun, B., Yang, C., & Gui, W. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3175888 · Cited by 73
“Wen et al. [22] introduced the LeNet-5-based 2-”
BackgroundWang, R., Liu, F., Hou, F., Jiang, W., Hou, Q., & Yu, L. (2020) · IEEE Access · doi:10.1109/access.2020.3010272 · Cited by 64
“To fit the input format of these DL models, sometimes one-dimensional vibration signals had to be converted into 2-D images before they were fed into DL models [26].”
BackgroundMethodZhu, J., Shi, H., Song, B., Tao, Y., & Tan, S. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3124578 · Cited by 68
“[21] covert signals into two-dimensional (2-D)”
Multi-level features fusion network-based feature learning for machinery fault diagnosis
Ye, Z., & Yu, J. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.108900 · Cited by 70
Compound Fault Diagnosis of Harmonic Drives Using Deep Capsule Graph Convolutional Network
Yang, G., Tao, H., Du, R., & Zhong, Y. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3176280 · Cited by 65
“The single-fault diagnosis of rotating machinery equipment (except for harmonic drive) has received considerable research interest [5]–[8].”
BackgroundZhang, Y., Shang, L., Gao, H., He, Y., Xu, X., & Chen, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3241367 · Cited by 67
“Data-driven methods [3] and analytical modelling meth-”
Self-citationApplications of Domain Generalization to Machine Fault Diagnosis: A Survey
Chen, Y., Zhang, D., Yan, R., & Xie, M. (2025) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2025.125120 · Cited by 88
Irfan, M., Mushtaq, Z., Khan, N. A., Mursal, S. N. F., Rahman, S., Magzoub, M. A., Latif, M. A., Althobiani, F., Khan, I., & Abbas, G. (2023) · IEEE Access · doi:10.1109/access.2023.3332243 · Cited by 59
Fault diagnosis of rotating machinery based on dual convolutional-capsule network (DC-CN)
Li, D., Zhang, M., Kang, T., Li, B., Xiang, H., Wang, K., Pei, Z., Tang, X., & Wang, P. (2021) · Measurement · doi:10.1016/j.measurement.2021.110258 · Cited by 68
Wang, Q., Zhao, B., Ma, H., Chang, J., & Mao, G. (2019) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-019-0504-x · Cited by 62
Intelligent Rolling Bearing Fault Diagnosis via Vision ConvNet
Wang, Y., Ding, X., Zeng, Q., Wang, L., & Shao, Y. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3042182 · Cited by 65
“Some scholars [17], [18], [23]–[29] have studied the influ-ence of convolution kernel size and stride on the accuracy of CNN, but the size of convolution kernel is concentrated in 3 to 11.”
BackgroundZhang, T., Zhang, R., Wang, H., Tu, R., & Yang, K. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3099638 · Cited by 65
“Wen et al. [28] proposed a new CNN based on Lenet-5, which could convert a one-dimensional signal into a two-dimensional signal image and eliminate the influence of manual features.”
Aero-engine gas path system health assessment based on depth digital twin
Zhou, L., Wang, H., & Xu, S. (2022) · Engineering Failure Analysis · doi:10.1016/j.engfailanal.2022.106790 · Cited by 65
A novel metric-based model with the ability of zero-shot learning for intelligent fault diagnosis
Fan, C., Zhang, Y., Ma, H., Ma, Z., Yu, K., Zhao, S., & Zhang, X. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107605 · Cited by 65
Self-citationTang, H., Fu, Z. C., & Huang, Y. J. (2020) · Applied Acoustics · doi:10.1016/j.apacoust.2020.107634 · Cited by 61
Deep Convolutional Neural Network Using Transfer Learning for Fault Diagnosis
Zhang, D., & Zhou, T. (2021) · IEEE Access · doi:10.1109/access.2021.3061530 · Cited by 64
Pan, Z., Gu, Z., Jiang, X., Zhu, G., & Ma, D. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3146573 · Cited by 69
Ribeiro, R. F., Areias, I. A. D. S., Campos, M. M., Teixeira, C. E., da Silva, L. E. B., & Gomes, G. F. (2022) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-022-00501-3 · Cited by 67
Integrated Gradient-Based Continuous Wavelet Transform for Bearing Fault Diagnosis
Du, J., Li, X., Gao, Y., & Gao, L. (2022) · Sensors · doi:10.3390/s22228760 · Cited by 68
Self-citationYe, Z., & Yu, J. (2021) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2021.03.022 · Cited by 62
A One-Class Generative Adversarial Detection Framework for Multifunctional Fault Diagnoses
Pu, Z., Cabrera, D. R., Bai, Y., & Li, C. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3108719 · Cited by 62
A new generative adversarial network based imbalanced fault diagnosis method
Li, M., Zou, D., Luo, S., Zhou, Q., Cao, L., & Liu, H. (2022) · Measurement · doi:10.1016/j.measurement.2022.111045 · Cited by 62
A Compressed Unsupervised Deep Domain Adaptation Model for Efficient Cross-Domain Fault Diagnosis
Xu, G., Huang, C., da Silva, D. S., & de Albuquerque, V. H. C. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3183225 · Cited by 61
Liu, K., & Chen, B. M. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3204953 · Cited by 73
“Note that the setting of α is very significant in the training network in the industrial applications, because the defects or anomalies in industrial applications are often the minority classes that are hard to be classified and the weights in the focal loss should be set in the proper range as indicated (α ∈ [2, 5]).”
BackgroundSerey, J., Alfaro, M. D., Fuertes, G., Vargas, M., Durán, C., Ternero, R., Rivera, R., & Sabattin, J. (2023) · Symmetry · doi:10.3390/sym15020535 · Cited by 87
Data-Knowledge-Based Fuzzy Neural Network for Nonlinear System Identification
Wu, X., Han, H., Liu, Z., & Qiao, J. (2019) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2019.2931870 · Cited by 59
“For these systems, efficient and reliable identification plays a key role in ensuring safety and product quality of processes [4], [5].”
BackgroundYao, Y., Wang, J., Long, P., Xie, M., & Wang, J. (2020) · International Journal of Energy Research · doi:10.1002/er.5348 · Cited by 59
“A mapping method involved stacking sensor signals in time domain horizontal directions was proposed by Wen in 2018.(28) A conversion method combines the time domain data of multiple sensors mounted on a rotating machine was proposed by Xia in 2018.”
MethodPei, Z., Jiang, H., Li, X., Zhang, J., & Liu, S. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/abe5e3 · Cited by 58
“The CNN-based diagnostic model is trained using the pre-and post-enhanced datasets, and the advantages of the proposed model over other data generation methods are verified through the analysis on diagnostic results [46].”
Self-citationNovel Three-Stage Feature Fusion Method of Multimodal Data for Bearing Fault Diagnosis
Wang, D., Li, Y., Jia, L., Song, Y., & Liu, Y. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3071232 · Cited by 95
“[17] developed a new LeNet-5-based CNN to extract the features of 2-D images converted from motor bearing data.”
MethodIrfan, M., Mushtaq, Z., Khan, N. A., Althobiani, F., Mursal, S. N. F., Rahman, S., Magzoub, M. A., Latif, M. A., & Khan, I. (2023) · IEEE Access · doi:10.1109/access.2023.3326367 · Cited by 57
Zhang, C., Yu, J., & Wang, S. (2020) · International Journal of Production Research · doi:10.1080/00207543.2020.1733701 · Cited by 61
“Wen et al. (2017) developed a new CNN-based fault diagnosis method using LeNet-5, which can eliminate those invalidated handcrafted features.”
MethodLi, H., Huang, J., Yang, X., Luo, J., Zhang, L., & Pang, Y. (2020) · Entropy · doi:10.3390/e22080851 · Cited by 62
“Each convolutional kernel further learns the deep features of each channel separately, and fuses the learned feature maps of each channel into a new feature map [29].”
BackgroundSensor and Actuator Fault Diagnosis for Robot Joint Based on Deep CNN
Pan, J., Qu, L., & Peng, K. (2021) · Entropy · doi:10.3390/e23060751 · Cited by 58
“One-dimensional CNN is used to analyze the raw time series data of the actuator and proved to be successful in diagnosing fault states [33], and a new CNN architecture based on LeNet-5 is set to process the bearing data set [34].”
MethodLi, G., Wu, J., Deng, C., Wei, M., & Xu, X. (2022) · Applied Acoustics · doi:10.1016/j.apacoust.2022.108663 · Cited by 67
Niu, S., & Srivastava, V. (2022) · International Journal of Solids and Structures · doi:10.1016/j.ijsolstr.2022.111521 · Cited by 61
Yuan, R. B., Lv, Y., Wang, T., Li, S., & Li, H. (2022) · Structural Health Monitoring · doi:10.1177/14759217221088492 · Cited by 59
Zhang, K., Li, H., Cao, S., Yang, C., Sun, F., & Wang, Z. (2022) · Measurement · doi:10.1016/j.measurement.2022.111697 · Cited by 59
Chen, W., Gao, Y., Gao, L., & Li, X. (2018) · Procedia CIRP · doi:10.1016/j.procir.2018.03.264 · Cited by 56
Self-citationVibration analysis in bearings for failure prevention using CNN
Pinedo-Sánchez, L. A., Mercado-Ravell, D., & Carballo-Monsivais, C. A. (2020) · Journal of the Brazilian Society of Mechanical Sciences and Engineering · doi:10.1007/s40430-020-02711-w · Cited by 63
Sun, J., Wen, J., Yuan, C., Liu, Z., & Xiao, Q. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3131722 · Cited by 57
Image deep learning in fault diagnosis of mechanical equipment
Wang, C., Sun, Y., & Wang, X. (2023) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-023-02176-3 · Cited by 65
“30 The structure of the capsule network reconstruct them into fusion images through capsule network models to detect power system faults (Li et al., 2018).”
Vibration Signal-Based Fusion Residual Attention Model for Power Transformer Fault Diagnosis
Zhou, Y., He, Y., Xing, Z., Wang, L., Shao, K., Lei, L., & Li, Z. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3382811 · Cited by 56
“Wen et al. [31] converted the signal into the 2-”
BackgroundAn Intelligent Fault Diagnosis Method for Reciprocating Compressors Based on LMD and SDAE
Liu, Y., Duan, L., Zhuang, Y., Wang, N., & Zhao, J. (2019) · Sensors · doi:10.3390/s19051041 · Cited by 58
Zhang, Z., Li, S., Wang, J., Xin, Y., An, Z., & Jiang, X. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.042 · Cited by 60
A review: data driven-based fault diagnosis and RUL prediction of petroleum machinery and equipment
Ji, D., Wang, C., Li, J., & Dong, H. (2021) · Systems Science & Control Engineering · doi:10.1080/21642583.2021.1992684 · Cited by 60
“In the past decade, it is found that 2-D CNN has more applications in the fields of FD and RUL prediction than the 1-D one (Grezmaka et al., 2019; S. Guo et al., 2020; T. Li et al., 2020; S. Shao et al., 2020; F. Wang et al., 2021; Wen et al., 2018; Xie et al., 2020; B. Yang et al., 2019; Zhu et al., 2019).”
MethodInfluentialHarmonic reducer in-situ fault diagnosis for industrial robots based on deep learning
Zhou, X., Zhou, H., He, Y., Huang, S., ZHU, Z.-H., & Chen, J. (2022) · Science China Technological Sciences · doi:10.1007/s11431-022-2129-9 · Cited by 56
“The same padding, a data processing method in CNNs [32], is used to make full use of information and avoid the loss of data dimension.”
MethodA Bearing Fault Diagnosis Method Based on Improved Mutual Dimensionless and Deep Learning
Xiong, J., Liu, M., Li, C., Cen, J., Zhang, Q., & Liu, Q. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3264870 · Cited by 57
“Many researchers have combined machine learning with signal analysis to perform intelligent fault recognition [18], [19].”
BackgroundFault Diagnosis in Microelectronics Attachment Via Deep Learning Analysis of 3-D Laser Scans
Dimitriou, N., Leontaris, L., Vafeiadis, T., Ioannidis, D., Wotherspoon, T., Tinker, G., & Tzovaras, D. K. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2931220 · Cited by 57
“strial shopfloors and manufacturing processes. CNNs are the most representative category of deep learning models and their architectures are able to deal with big multimodal datasets. For instance, in [8] a CNN framework is presented to convert sensor signals from manufacturing processes to 2-D images which are used to…”
MethodData-Driven Fault Diagnostics and Prognostics for Predictive Maintenance: A Brief Overview
Xu, G., Liu, M., Wang, J., Ma, Y., Wang, J., Li, F., & Shen, W. (2019) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2019.8843068 · Cited by 73
“, signalbased, model-based, data-driven, hybrid-driven [12].”
BackgroundInfluentialDomain Adaptation-Based Transfer Learning for Gear Fault Diagnosis Under Varying Working Conditions
Chen, C., Shen, F., Xu, J., & Yan, R. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3011584 · Cited by 66
“With the development of sensing technologies and artificial intelligence (AI), the GFD task can be treated as a pattern recognition problem which can be settled by machine-learning algorithms, such as decision tree [3], support vector machine (SVM) [4], neural networks [5], and association rule [6].”
BackgroundZhang, X., Wang, H. F., Wu, B., Zhou, Q., & Hu, Y. (2022) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-022-01944-x · Cited by 55
“Based on the difference in network structure and form, CNN can be divided into two types, i.e. one-dimensional CNN (1DCNN) (Kiranyaz et al., 2021) and two-dimensional CNN (2DCNN) (Wen et al., 2018).”
BackgroundSun, Z., Wang, Y., & Chen, Z. (2023) · International Journal of Hydrogen Energy · doi:10.1016/j.ijhydene.2023.10.148 · Cited by 54
Real-Time Fault Diagnosis for Hydraulic System Based on Multi-Sensor Convolutional Neural Network
Tao, H., Jia, P., Wang, X., & Wang, L. (2024) · Sensors · doi:10.3390/s24020353 · Cited by 62
“For example, Wen et al. [30] converted 1D vibration signals into 2D gray-level images using a signal-to-image conversion approach.”
MethodDeep learning in industrial machinery: A critical review of bearing fault classification methods
Rehman, A. U., Jiao, W., Jiang, Y., Wei, J., Sohaib, M., Sun, J., Shiju, E., Rehman, K. U., & Chi, Y. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.112785 · Cited by 69
Jiang, S. B., Wong, P. K., Guan, R., Liang, Y., & Li, J. (2019) · IEEE Access · doi:10.1109/access.2019.2895909 · Cited by 60
Transfer Learning Based Fault Diagnosis with Missing Data Due to Multi-Rate Sampling
Chen, D., Yang, S., & Zhou, F. (2019) · Sensors · doi:10.3390/s19081826 · Cited by 56
“Deep learning methods are widely used in fault diagnosis, such as deep belief networks (DBN) [14–18], stacked auto-encoders (SAE) [14,19–24], long short-term memory Sensors 2019, 19, 1826; doi:10.3390/s19081826 www.mdpi.com/journal/sensors Sensors 2019, 19, 1826 2 of 21 neural networks (LSTM) [25] and convolutional ne…”
BackgroundInfluentialYan, S., & Yan, X. (2019) · Applied Soft Computing · doi:10.1016/j.asoc.2019.105526 · Cited by 57
Pitfalls and protocols of data science in manufacturing practice
Lee, C., & Chien, C.-F. (2020) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-020-01711-w · Cited by 65
Permutation entropy-based 2D feature extraction for bearing fault diagnosis
Landauskas, M., Cao, M., & Ragulskis, M. K. (2020) · Nonlinear Dynamics · doi:10.1007/s11071-020-06014-6 · Cited by 53
“Such an approach is in a stark contrast to data driven fault diagnosis methods based on feature extraction from raw data [32].”
ResultA Hybrid Data-Driven Method for Wire Rope Surface Defect Detection
Zhou, P., Zhou, G., Li, Y.-M., He, Z., & Liu, Y. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2970070 · Cited by 53
“It should be noted that in the field of fault/defect detection/diagnosis, the methods can be divided into some classes involving model-based, signal-based, data-driven and hybrid/active-based method [6],[19].”
MethodZhang, S., Sun, Z., Li, C., Cabrera, D. R., Long, J., & Bai, Y. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2920661 · Cited by 54
“[28] proposed a convolutional neural network based on LeNet-5 to diagnose faults, where the collected signals were converted to two-dimensional images to extract features automatically.”
MethodZhang, L., Ding, X., & Hou, R. (2020) · Journal of Analytical Methods in Chemistry · doi:10.1155/2020/9652470 · Cited by 54
“A fault diagnosis model based on LeNet-5 network was proposed, and the original time domain signal was converted into a two-dimensional gray image as themodel input to realize fault diagnosis based on one-dimensional time domain signal [9].”
MethodMao, X., Zhang, F., Wang, G., Chu, Y., & Yuan, K. (2020) · Measurement · doi:10.1016/j.measurement.2020.108603 · Cited by 56
A Deep Neural Network-Based Feature Fusion for Bearing Fault Diagnosis
Hoang, D.-T., Tran, X.-T., Van, M., & Kang, H. (2021) · Sensors · doi:10.3390/s21010244 · Cited by 56
“The first method to compare is published in [30].”
MethodLi, W., Shang, Z., Qian, S., Zhang, B., Zhang, J., & Gao, M. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117716 · Cited by 52
Source-free domain adaptation framework for fault diagnosis of rotation machinery under data privacy
Li, Q., Tang, B., Deng, L., & Zhu, P. Y. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109468 · Cited by 54
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.