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 801–900 of 1,003
Robust and Efficient Fault Diagnosis of mm-Wave Active Phased Arrays Using Baseband Signal
Nielsen, M. H., Zhang, Y., Xue, C., Ren, J., Yin, Y., Shen, M., & Pedersen, G. F. (2022) · IEEE Transactions on Antennas and Propagation · doi:10.1109/tap.2022.3179898 · Cited by 26
“Deep Neural Network (DNN) has shown promises in many fields of fault diagnosis [29]–[32].”
BackgroundSelf-citationBearing fault diagnosis method based on Gramian angular field and ensemble deep learning
Han, Y., Li, B., Huang, Y., & Li, L. (2022) · Journal of Vibroengineering · doi:10.21595/jve.2022.22796 · Cited by 24
“Example include convolutional neural network (CNN)-based methods [1], [2], [9], [10]-[14], sparse auto-encoder (SAE)-based methods [15], [16], and recursive neural network (RNN)-based methods [17], [18], etc.”
BackgroundMethodLing, L., Wu, Q., Huang, K., Wang, Y., & Wang, C. (2022) · Electronics · doi:10.3390/electronics11244110 · Cited by 23
Liu, Z., Wu, D., Huang, K., Yang, C., & Gui, W. (2022) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2022.3223723 · Cited by 21
“Therefore, fault diagnosis has become an extensive and meaningful research topic [6], [7], [8].”
BackgroundTire Condition Monitoring Using Transfer Learning-Based Deep Neural Network Approach
Vasan, V., Sridharan, N. V., Anoop, P. S., & Sugumaran, V. (2023) · Sensors · doi:10.3390/s23042177 · Cited by 21
“Reference Deep Learning Approach Application in Mechanical System [7] Convolution Neural Networks with Wavelet Transform Motor Bearing [8] Hierarchical Convolution Neural Network Roller Bearing [9] Convolution Neural Networks with Wavelet Transform [10] Deep Belief Network and Spare Autoencoder [11] Recurrent Neural N…”
BackgroundMethodInfluentialApplications of Artificial Intelligence for Fault Diagnosis of Rotating Machines: A Review
Kibrete, F., & Woldemichael, D. E. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-28725-1_4 · Cited by 26
Lu, J., Wang, K., Chen, C., & Ji, W. (2023) · Sensors · doi:10.3390/s23125487 · Cited by 25
“Wen et al. [10] converted the original vibration signal into a two-dimensional grayscale image, and input it into CNN for fault classification and diagnosis, which has attracted the attention of many scholars.”
BackgroundLi, C., Yu, Y., Shang, L., Zhang, H., & Jiang, Y. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08910-5 · Cited by 21
“Among them, convolutional neural networks (CNN) with powerful classification capabilities have been applied to several fault diagnosis areas [29–31], such as bearing fault diagnosis [32], actuator fault diagnosis [33], refrigerant fault diagnosis [34], motor bearing fault diagnosis [35], and gearbox fault diagnosis [3…”
BackgroundMei, J., Zhu, M., Liu, W., Fu, M., & Tang, Q. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3301058 · Cited by 22
Tang, G., Yi, C., Liu, L., Zhan, X., Zhou, Q., & Lin, J. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110870 · Cited by 21
Russell, M. B., & Wang, P. E. (2023) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2023.09.008 · Cited by 27
“Interest in pursuing trustworthy DL stems from early DL work in manufacturing that established its superiority over traditional approaches like Support Vector Machine (SVM) for analyzing condition monitoring data sets [3].”
BackgroundYe, L., Wu, H., Chen, Y., & Fei, Z. (2023) · Journal of Process Control · doi:10.1016/j.jprocont.2023.103086 · Cited by 24
Yousefi, S., Yin, S., & Alfarizi, M. G. (2023) · IEEE Open Journal of the Industrial Electronics Society · doi:10.1109/ojies.2023.3334429 · Cited by 27
“These models use hierarchical networks like fully-connected (FC) layers [42], [43], [44], [45], CNNs [46], [47], [48], [49], [50], deep belief networks [17], [51], [52], RNNs [53], [54], and multilayered auto-encoders [52], [55], [56] to find essential traits.”
MethodLiu, J., & Wang, H. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109873 · Cited by 21
Real-time robust bearing fault detection using scattergram-driven hybrid CNN-SVM
Mitra, S. K., & Koley, C. (2023) · Electrical Engineering · doi:10.1007/s00202-023-02162-1 · Cited by 21
“Several authors have demonstrated that the convolutional neural network (CNN) is the most significant and successful DL model with sparse connectivity and shared weights for bearing health images (colormap or grayscale) [19–21].”
Huang, P., Wang, Y., Gu, Y., & Qiu, G. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad2cd9 · Cited by 21
“Since the traditional data-driven-based methods depend heavily on expert experience in the feature extraction process, Wen et al [17] realized fault diagnosis using LeNet-5 based on converting the signal into a two-dimensional image to avoid subjectivity and completeness in the process of manual…”
Melanoma identification and classification model based on fine-tuned convolutional neural network
Almufareh, M. F., Tariq, N., Humayun, M., & Khan, F. A. (2024) · Digital Health · doi:10.1177/20552076241253757 · Cited by 26
GPSC-GAN: A Data Enhanced Model for Intelligent Fault Diagnosis
Lyu, P., Cheng, Y., Zhang, M., Yu, W., Xia, L., & Liu, C. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3457925 · Cited by 21
“The steps of the detailed data conversion [43] are as follows.”
DC Fault Detection and Classification Approach of MMC-HVDC Based on Convolutional Neural Network
Wang, J., Zheng, X., & Tai, N. (2018) · IEEE Conference on Energy Internet and Energy System Integration (EI2) · doi:10.1109/ei2.2018.8582391 · Cited by 21
Zehelein, T., Hemmert-Pottmann, T., & Lienkamp, M. (2020) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan9010008 · Cited by 23
Zhang, Y., Ren, Z., & Zhou, S. (2020) · Shock and Vibration · doi:10.1155/2020/8850976 · Cited by 24
“Wen [8] used a conversion method converting signals into twodimensional images to build a new fault diagnosis model of CNN based on LeNet-5.”
MethodSelf-citationWang, J., Wang, D., & Wang, X. (2020) · Chinese Control Conference (CCC) · doi:10.23919/ccc50068.2020.9189568 · Cited by 22
“Most previous research has focused on analyzing vibration signals captured by a single sensor [9,10].”
BackgroundQiu, G., Nie, Y., Peng, Y., Huang, P., Chen, J., & Gu, Y. (2024) · Quality and Reliability Engineering International · doi:10.1002/qre.3538 · Cited by 20
“By signal-to-image conversion method, 40 the reconstructed signals 𝑢 𝑖 (𝑡), 𝑖 = 1 ∶ 𝑛 are finally stacked into a two-dimensional image. where, the function 𝑟𝑜𝑢𝑛𝑑(⋅) is the rounding function.”
Motor fault diagnosis based on multisensor-driven visual information fusion
Long, Z., Guo, J., Ma, X., Wu, G., Rao, Z., Zhang, X., & Xu, Z. (2024) · ISA Transactions · doi:10.1016/j.isatra.2024.09.024 · Cited by 22
Ming, Z., Tang, B., Deng, L., & Li, Q. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109371 · Cited by 21
Zhang, B., Wang, W., & He, Y. L. (2025) · Scientific Reports · doi:10.1038/s41598-025-98138-1 · Cited by 21
“Asymmetric Convolutional Networks (AC-Net), through the design of asymmetric convolution structures, effectively extract local features and improve diagnostic capabilities in complex fault scenarios 63 .”
Transfer learning for process monitoring using reflection-mode ultrasonic sensing
Bowler, A. L., & Watson, N. J. (2021) · Ultrasonics · doi:10.1016/j.ultras.2021.106468 · Cited by 22
“Wen et al. (2018) 2019) achieved classification accuracies of up to 89.9 % when transferring models from different machines.”
BackgroundInfluentialChouhan, A., Gangsar, P., Porwal, R., & Mechefske, C. (2021) · Noise & Vibration Worldwide · doi:10.1177/09574565211030709 · Cited by 20
“Wen et al.27 introduced a convolutional neural network (CNN) scheme using LeNet-5 for IM defect detection and found it to be more effective than NN because CNN extracts the useful features automatically.”
MethodAn optimal method based on HOG-SVM for fault detection
Xu, P., Huang, L., & Song, Y. X. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12020-0 · Cited by 24
“In [16], the method of transforming the signal into gray image is proposed and applied to the signal preprocessing, which works well.”
BackgroundMethodPhan, T. L. J., Gehrhardt, I., David, H. A., Bahrpeyma, F., & Reichelt, D. (2022) · Logistics · doi:10.3390/logistics6020035 · Cited by 27
Convolutional Neural Network Based Two-Layer Transfer Learning for Bearing Fault Diagnosis
Zhang, W., Zhang, P., He, X., & Zhang, D. (2022) · IEEE Access · doi:10.1109/access.2022.3213657 · Cited by 23
“79% [40], AOCNN with the accuracy of 99.”
BackgroundBraig, M., & Zeiler, P. (2022) · IEEE Access · doi:10.1109/access.2022.3233220 · Cited by 24
“Approaches to which this applies are those in [9], [81], [84], [85], [86], [92], [93], [94], [95], [96], and [98] on bearings, [87], [93], [98] on gearboxes, [168] on tools for machinery, [83] on railway wheels, [18], [93] on electric”
BackgroundInfluentialWang, Y., Bao, D., & Qin, S. J. (2023) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2023.104878 · Cited by 21
A digital twin-based fault diagnostic method for subsea control systems
Tao, H., Jia, P., Wang, X., Chen, X., & Wang, L. (2023) · Measurement · doi:10.1016/j.measurement.2023.113461 · Cited by 22
Distributed Bearing Fault Classification of Induction Motors Using 2-D Deep Learning Model
Rajabioun, R., Afshar, M., Mete, M., Atan, Ö., & Akin, B. (2023) · IEEE Journal of Emerging and Selected Topics in Industrial Electronics · doi:10.1109/jestie.2023.3323253 · Cited by 23
Luo, Y., Lu, W., Kang, S., Tian, X., Kang, X., & Sun, F. (2023) · Sensors · doi:10.3390/s23218703 · Cited by 20
“And the integration of deep learning techniques [13–16] with acoustic radiation signals is specifically emphasized.”
BackgroundFault diagnosis of marine machinery via an intelligent data-driven framework
Xu, X., Lin, Y., & Ye, C. (2023) · Ocean Engineering · doi:10.1016/j.oceaneng.2023.116302 · Cited by 22
Guo, W., & Shi, Y. (2023) · IET Generation Transmission & Distribution · doi:10.1049/gtd2.13055 · Cited by 20
Debiased Contrastive Learning for Time-Series Representation Learning and Fault Detection
Zhang, K., Cai, R., Zhou, C., & Liu, Y. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3359409 · Cited by 24
MEMS Inertial Sensor Fault Diagnosis Using a CNN-Based Data-Driven Method
Gao, T. Y., Wei, S., Zhou, M., Fang, B., & Zheng, L. (2020) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s021800142059048x · Cited by 21
Park, C. H., Kim, H., Lee, J., Ahn, G., Youn, M., & Youn, B. D. (2020) · International Journal of Precision Engineering and Manufacturing-Green Technology · doi:10.1007/s40684-020-00279-3 · Cited by 22
“In the case of motors, several previous studies have mainly focused on devising efficient input data for training CNN models using vibration signals [24–26].”
Zhao, D., Liu, S., Zhang, H., Sun, X., Wang, L., & Wei, Y. (2021) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-021-05515-9 · Cited by 21
Yu, H., Wang, K., Li, Y., & He, M. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107755 · Cited by 23
Wang, C., & Liu, J. (2024) · IEEE Transactions on Reliability · doi:10.1109/tr.2024.3381579 · Cited by 19
Machine learning based mechanical fault diagnosis and detection methods: a systematic review
Xin, Y., Zhu, J., Cai, M., Zhao, P., & Zuo, Q. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad8cf6 · Cited by 28
Ye, L., Zhang, K., & Jiang, B. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3495768 · Cited by 19
Time- and frequency-domain fusion for source-free adaptation fault diagnosis
Gao, Y. X., Zhang, Z., Chen, B., Li, J., Lu, G., Sun, S., & Zong, L. (2025) · Information Fusion · doi:10.1016/j.inffus.2024.102875 · Cited by 21
Brusa, E. G. M., Delprete, C., & Maggio, L. G. D. (2022) · Mechanics of Advanced Materials and Structures · doi:10.1080/15376494.2022.2102274 · Cited by 21
“processing tools would mature few years later [51, 55, 66].”
BackgroundChen, S. (2021) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.23452 · Cited by 29
“The general process of intelligent identification of power equipment based on deep learning is as follows [22].”
BackgroundSun, Y., Zhao, T., Zou, Z., Chen, Y., & Zhang, H. (2021) · Review of Scientific Instruments · doi:10.1063/5.0057059 · Cited by 19
Hou, X., Guo, W., Ren, S., Li, Y., Si, Y., & Su, L. (2022) · Materials · doi:10.3390/ma15196757 · Cited by 19
“[12] adopted a new CNN based on LeNet-5 for fault diagnosis, which converts one-dimensional (1D) signals into two-dimensional (2D) images.”
MethodA New Fault Diagnosis Method for Unbalanced Data Based on 1DCNN and L2-SVM
Hu, B., Liu, J., Zhao, R., Xu, Y., & Huo, T. (2022) · Applied Sciences · doi:10.3390/app12199880 · Cited by 23
Adversarial Fault Detector Guided by One-Class Learning for a Multistage Centrifugal Pump
Cabrera, D. R., Villacís, M., Cerrada, M., Sánchez, R., Li, C., Sancho, F., Long, J., & Estupiñán, E. (2022) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2022.3226347 · Cited by 19
“Followingthisline,the mostwidelyusedmethodforpumpfaultdiagnosistransforms the1-Dinputsignalintoa2-Drepresentationthatisfedtoa convolutionalneuralnetwork(CNN)[21].”
MethodInfluentialMulti-Sensor Data Fusion Method Based on Improved Evidence Theory
Qiao, S., Fan, Y., Wang, G., & Zhang, H. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11061142 · Cited by 19
An evolutionary ensemble convolutional neural network for fault diagnosis problem
Najaran, M. H. T. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120678 · Cited by 24
Bouazzi, Y., Yahyaoui, Z., & Hajji, M. (2023) · Alexandria Engineering Journal · doi:10.1016/j.aej.2023.11.053 · Cited by 20
Attributions for ML-based ICS Anomaly Detection: From Theory to Practice
Fung, C., Zeng, E., & Bauer, L. (2024) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2024.23216 · Cited by 36
“Fault isolation requires an explicit definition of the types of faults expected in the system, which can be difficult to acquire [67].”
BackgroundDSMT-1DCNN: Densely supervised multitask 1DCNN for fault diagnosis
Shao, X., Li, D., Ra, I., & Kim, C. S. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111609 · Cited by 22
Zhang, X., Wang, Y., Wei, S., Zhou, Y., & Jia, L. (2024) · Journal of Instrumentation · doi:10.1088/1748-0221/19/05/p05015 · Cited by 20
“For comparison, six representative deep - learning networks – namely, LeNet5[29], CNN, VGG16[30], ResNet18[24], SENet18[16], and DenseNet121[31] were also adopted for bearing fault diagnosis on the CWRU dataset.”
MethodCui, B., Zhang, S., Su, J., & Cui, H. (2024) · IEEE Access · doi:10.1109/access.2024.3439620 · Cited by 21
Cheng, L., Qi, H., Ma, R., Kong, X., Zhang, Y., & Zhu, Y. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112658 · Cited by 21
Self-citationCarNet: A Dual Correlation Method for Health Perception of Rotating Machinery
Zhang, W., Yang, D., Wang, H., Huang, X., & Gidlund, M. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2912934 · Cited by 20
“92%) is not the highest among these works; it is lower than some literature, such as [23], [29] and [31].”
MethodInfluentialA neuro-inspired computational model for adaptive fault diagnosis
Moghaddam, M., Chen, Q., & Deshmukh, A. V. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.112879 · Cited by 20
A Method of Rolling Bearing Fault Diagnose Based on Double Sparse Dictionary and Deep Belief Network
Guo, J., & Zheng, P. (2020) · IEEE Access · doi:10.1109/access.2020.3003909 · Cited by 21
“In references [17], [18], the time-frequency domain method combined with convolutional neural network (CNN) was used for bearing fault feature extraction.”
MethodExtensible and displaceable hyperdisk based classifier for gear fault intelligent diagnosis
Hu, T., Cheng, J., Wang, P., Wang, J., & Yang, Y. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106250 · Cited by 19
Zimnickas, T., Vanagas, J., Dambrauskas, K., & Kalvaitis, A. (2020) · Energies · doi:10.3390/en13143690 · Cited by 19
Pasqualotto, D., & Zigliotto, M. (2021) · IET Electric Power Applications · doi:10.1049/elp2.12059 · Cited by 20
“[17, 18], in which a CNN was applied on induction motors in order to identify different types of fault.”
MethodWang, G., Zhang, M., Xiang, L., Hu, Z., Li, W., & Cao, J. (2021) · Measurement · doi:10.1016/j.measurement.2021.109627 · Cited by 20
You, D., Chen, L., Liu, F., Zhang, Y., Shang, W., Hu, Y., & We, L. (2021) · Shock and Vibration · doi:10.1155/2021/7346352 · Cited by 21
Self-citationAn Imbalanced Fault Diagnosis Method Based on TFFO and CNN for Rotating Machinery
Zhang, L., Liu, Y., Zhou, J., Luo, M., Pu, S., & Yang, X. (2022) · Sensors · doi:10.3390/s22228749 · Cited by 22
“It achieves bearing or gear failure classification and diagnosis by mining rules and connections within big data [12,13].”
BackgroundLightweight Network Bearing Intelligent Fault Diagnosis Based on VMD-FK-ShuffleNetV2
Jiang, W., Qi, Z., Jiang, A., Chang, S., & Xia, X. (2024) · Machines · doi:10.3390/machines12090608 · Cited by 22
A fault detector/classifier for closed-ring power generators using machine learning
Quintanilha, I. M., Elias, V. R. M., da Silva, F. B., Fonini, P., da Silva, E. A. B., Netto, S. L., Apolinário, J. A., de Campos, M. L. R., Martins, W. A., Wold, L. E., et al. (2021) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2021.107614 · Cited by 19
“Deep learning (DL) architectures are employed to detect and classify faults in high-voltage applications [36] and in hydraulic pumps [37].”
BackgroundPre-Processing Method to Improve Cross-Domain Fault Diagnosis for Bearing
Kim, T., & Chai, J. (2021) · Sensors · doi:10.3390/s21154970 · Cited by 22
“The performance of Wen’s model outperformed other models such as support vector machines, conventional CNNs, and artificial neural networks [9].”
MethodVenkateswaran, S., Sheriff, M. Z., Wilhite, B. A., & Kravaris, C. (2021) · Journal of Process Control · doi:10.1016/j.jprocont.2021.10.001 · Cited by 18
Fault detection based on extended state observer and interval observer for UAVs
Cao, L., Yang, X., Wang, G., Liu, Y., & Hu, Y. (2022) · Aircraft Engineering and Aerospace Technology · doi:10.1108/aeat-05-2021-0164 · Cited by 20
Local-feature and global-dependency based tool wear prediction using deep learning
Yang, C., Zhou, J., Li, E., Wang, M., & Jin, T. (2022) · Scientific Reports · doi:10.1038/s41598-022-18235-3 · Cited by 18
“With its powerful feature extraction, feature fusion and abstraction ability 13–15 , it can directly extract features from original data without relying on human experience, which makes it widely used in various industries and gradually applied in tool wear prediction 16–18 .”
BackgroundHou, L., Liu, L., & Mao, G. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3206764 · Cited by 18
“D images by wavelet transform [8] or specialized data preprocessing algorithm [9], [10] as the input of the following CNN fault classifier.”
MethodNew Transfer Learning Approach Based on a CNN for Fault Diagnosis
Ibrahim, A., Anayi, F., & Packianather, M. (2022) · International Electronic Conference on Machines and Applications (IECMA) · doi:10.3390/iecma2022-12905 · Cited by 18
“In addition, DL has shown itself to be a promising candidate in the area of defect detection [19], for example, the use of a convolutional neural network (CNN) in [20].”
Xu, M. F., Gao, J., Zhang, Z., & Wang, H. (2022) · Entropy · doi:10.3390/e24111569 · Cited by 26
“In STIM [37], the raw 1D signal is translated into 2D gray image directly as shown in Figure 1.”
MethodMeta-Self-Training Based on Teacher–Student Network for Industrial Label-Noise Fault Diagnosis
Pu, X., & Li, C. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3232654 · Cited by 22
“As modern industrial systems and corresponding fault diagnosis tasks become more and more complex, deep-learning-based fault diagnosis has attracted considerable attention [3], [4], [5], [6].”
BackgroundMethodIntelligent Tool-Wear Prediction Based on Informer Encoder and Bi-Directional Long Short-Term Memory
Xie, X., Huang, M., Liu, Y., & An, Q. (2023) · Machines · doi:10.3390/machines11010094 · Cited by 18
Huang, T., Gao, Y., Li, Z., Hu, Y., & Xuan, F. (2023) · Applied Sciences · doi:10.3390/app13105843 · Cited by 19
Intelligent Fault Diagnosis of Variable-Condition Motors Using a Dual-Mode Fusion Attention Residual
Xie, F., Li, G., Hu, W., Fan, Q., & Zhou, S. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11071385 · Cited by 19
Quan, Y., Liu, C., Yuan, Z., & Yan, B. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3372438 · Cited by 18
“D image generation [26] and are therefore more suitable for processing 2-”
Gao, Y., Zheng, X., Li, J., Zong, L., Yin, H., Li, H., & Lu, G. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3396554 · Cited by 20
Nonlinear Extended-state ARX-Laguerre PI Observer Fault Diagnosis of Bearings
Piltan, F., & Kim, J.-M. (2019) · Applied Sciences · doi:10.3390/app9050888 · Cited by 18
Ma, H., Li, S., & An, Z. (2019) · Applied Sciences · doi:10.3390/app9081603 · Cited by 21
Liu, G., Zhu, L. X., Yu, W., & Yu, W. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3018496 · Cited by 18
“CNN, a popular algorithm of deep learning [3], [10].”
BackgroundMethodYang, Q., Li, J., dos Santos, R. C., Huang, K., & Igić, P. (2020) · High Voltage · doi:10.1049/hve2.12033 · Cited by 20
“For power system fault studies, various AI methods including expert systems [18], Fuzzy system [19], Bayesian networks [20], rough set [21], Petri nets [22], neural networks (NNs) [23,24], support vector machine [25] and so on are applied in fault detection.”
MethodDash, P. B., Naik, B., Nayak, J., & Vimal, S. (2021) · Soft Computing · doi:10.1007/s00500-021-05572-0 · Cited by 19
RetractedFault Diagnosis of Bearing Based on Convolutional Neural Network Using Multi-Domain Features
Shao, X., Wang, L., Kim, C. S., & Ra, I. (2021) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2021.05.002 · Cited by 19
“Long et al. [21] applied a two-dimensional CNN (2D-CNN) based on the structure of LeNet-5 for fault diagnosis; the validation experiments proved its state-of-the-art performance.”
BackgroundMethodFault diagnosis based on TOPSIS method with Manhattan distance
Jiang, W. R., Wang, M., Deng, X., & Gou, L. (2019) · Advances in Mechanical Engineering · doi:10.1177/1687814019833279 · Cited by 18
Milani, A. E., Zappalá, D., & Watson, S. J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109477 · Cited by 20
Causal Disentanglement-Based Hidden Markov Model for Cross-Domain Bearing Fault Diagnosis
Chang, R., Ma, Y., Nie, W., Nie, J., Zhu, Y., & Liu, A.-A. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3513329 · Cited by 30
“Wen et al. [10] designed a CNN based on the classic LeNet-5 architecture [20], proposing a novel approach to converting raw signals into images for network training.”
Yimam, A. W., Vafaeipour, M., Messagie, M., Fante, K. A., Molla, E. M., Mekonnen, T., & Coosemans, T. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112645 · Cited by 21
Every Corporation Owns Its Image: Corporate Credit Ratings via Convolutional Neural Networks
Feng, B., Xue, W., Xue, B., & Liu, Z. (2020) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc51575.2020.9344973 · Cited by 24
“In traditional data-driven methods, the data feature extraction is vital since most of the data-driven methods cannot handle the raw data [19].”
Duan, J., He, Y., & Wu, X. (2021) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2021.106965 · Cited by 18
An Intelligent Process Fault Diagnosis System based on Andrews Plot and Convolutional Neural Network
Wang, S., & Zhang, J. (2022) · Journal of Dynamics Monitoring and Diagnostics · doi:10.37965/jdmd.2022.67 · Cited by 17
“Numerous prior studies evidenced that CNN has strong adaptability, exceptional local feature data mining capability, global training feature extraction and classification [23-26].”
BackgroundCombine Harvester Bearing Fault-Diagnosis Method Based on SDAE-RCmvMSE
Yang, G., Cheng, Y., Xi, C., Liu, L., & Gan, X. (2022) · Entropy · doi:10.3390/e24081139 · Cited by 19
Robust rotating machinery diagnosis using a dynamic-weighted graph updating strategy
Zhang, X., Hu, Y., Liu, J., Zhang, X., & Wu, B. (2022) · Measurement · doi:10.1016/j.measurement.2022.111895 · Cited by 17
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.