An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data
The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
Intelligent fault diagnosis is a promising tool to deal with mechanical big data due to its ability in rapidly and efficiently processing collected signals and providing accurate diagnosis results. In traditional intelligent diagnosis methods, however, the features are manually extracted depending on prior knowledge and diagnostic expertise. Such processes take advantage of human ingenuity but are time-consuming and labor-intensive. Inspired by the idea of unsupervised feature learning that uses artificial intelligence techniques to learn features from raw data, a two-stage learning method is proposed for intelligent diagnosis of machines. In the first learning stage of the method, sparse filtering, an unsupervised two-layer neural network, is used to directly learn features from mechanical vibration signals. In the second stage, softmax regression is employed to classify the health conditions based on the learned features. The proposed method is validated by a motor bearing dataset and a locomotive bearing dataset, respectively. The results show that the proposed method obtains fairly high diagnosis accuracies and is superior to the existing methods for the motor bearing dataset. Because of learning features adaptively, the proposed method reduces the need of human labor and makes intelligent fault diagnosis handle big data more easily.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
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 · cited 1×
“This would make intelligent fault diagnosis methods less dependent on the prior knowledge or human labor, so that novel applications could be done faster, and more importantly, to make mechanical fault diagnosis toward real artificial intelligence [20].”
BackgroundHinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260 · cited 1×
“tion [24], speech recognition [25], and high-energy physic [26], and state-of-the-art performances are obtained in these fields.”
BackgroundIndependent component analysis: algorithms and applications
Hyvärinen, A., & Oja, E. (2000) · Neural Networks · doi:10.1016/s0893-6080(00)00026-5 · Cited by 8,705 · cited 1×
“other and speed up the convergence of the sparse filtering training [37].”
BackgroundAn analysis of single-layer networks in unsupervised feature learning
Coates, A., Ng, A. Y., & Lee, H. (2011) · International Conference on Artificial Intelligence and Statistics · Cited by 4,675
Compressive Sensing [Lecture Notes]
Baraniuk, R. (2007) · IEEE Signal Processing Magazine · doi:10.1109/msp.2007.4286571 · Cited by 4,177
A Practical Guide to Training Restricted Boltzmann Machines
Hinton, G. E. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_32 · Cited by 2,852 · cited 1×
“Once these parameters are set inappropriately, the learned features may result in poor diagnosis accuracy [28].”
BackgroundWu, X., Zhu, X., Wu, G.-Q., & Ding, W. (2014) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.109 · Cited by 2,410 · cited 1×
“2519325 new perspectives and challenges in processing and discovering valuable information [4], but also may prompt its power to affect other fields, such as the field of condition monitoring”
BackgroundBeyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation
Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006) · Lecture Notes in Computer Science · doi:10.1007/11941439_114 · Cited by 1,974 · cited 1×
“To compare their performances with that of the proposed method, F-score is adopted [40], which is a commonly used criterion measuring the performance of a classification method.”
Method
Cited by
Items 801–900 of 1,001
Hybrid Approach for Onsite Monitoring and Anomaly Detection of Cutting Tool Life
Ying, Z., Shu, L., Kizaki, T., Iwama, M., & Sugita, N. (2021) · Procedia CIRP · doi:10.1016/j.procir.2021.11.260 · Cited by 8
Huang, K., Tao, S., Liu, Y., Yang, C., & Gui, W. (2021) · Science China Information Sciences · doi:10.1007/s11432-021-3341-y · Cited by 8
Han, B., Guo, L., Wang, J., Zhang, Z., Zhang, G., & Jia, S. (2022) · Measurement · doi:10.1016/j.measurement.2022.111136 · Cited by 8
Hwang, S., GÖRGÜLÜARSLAN, R. M., Choi, H., & Choi, S.-K. (2020) · Applied Sciences · doi:10.3390/app10020643 · Cited by 8
“To eliminate these issues, a rigorous design of stretchable electronics based on efficient capturing and modeling of correlated and high dimensional random variables is required [24].”
BackgroundHu, Q., Zhang, Q., Si, X., Qin, A., & Zhang, Q.-H. (2020) · IEEE Access · doi:10.1109/access.2020.2989460 · Cited by 8
“Consequently, there is a great demand for rolling bearing fault diagnosis techniques that can be used tomake reliablemaintenance decisions [2].”
BackgroundCross-Task Fault Diagnosis Based on Deep Domain Adaptation With Local Feature Learning
Tian, Y., Tang, Y., & Peng, X. (2020) · IEEE Access · doi:10.1109/access.2020.3006250 · Cited by 8
“The typical representatives of DNN applied for fault diagnosis includes Deep Belief Networks (DBN) [24], SAE [25], Sparse Filtering (SF) [26], Convolutional Neural Networks (CNN) [27].”
Lei, P., Shen, C., Zhu, J., Wang, D., Jiang, X., & Zhu, Z. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/abc38b · Cited by 9
Nie, X., & Xie, G. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/abd7a9 · Cited by 9
“Following the setting in [32], the testing accuracies with different training sample proportions are shown in figure 5(b).”
Trend-Based Repair Quality Assessment for Industrial Rotating Equipment
Toothman, M., Braun, B., Bury, S. J., Dessauer, M. P., Henderson, K., Wright, R., Tilbury, D. M., Moyne, J. R., & Barton, K. L. (2020) · IEEE Control Systems Letters · doi:10.1109/lcsys.2020.3041214 · Cited by 8
Park, D., Na, J., & Lee, J. M. (2021) · Industrial & Engineering Chemistry Research · doi:10.1021/acs.iecr.1c01271 · Cited by 8
Xu, K., Li, S., Li, R., Lu, J., Zeng, M., Li, X., Du, J., & Wang, Y. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac145f · Cited by 9
“Inspired by the idea of unsupervised feature learning, Lei et al [17] creatively proposed a two-stage artificial intelligence diagnosis method based on sparse filtering, which realized the accurate classification of fault features.”
Bearing Severity Fault Evaluation Using Contour Maps—Case Study
Soto-Ocampo, C. R., Cano-Moreno, J. D., Mera, J. M., & Maroto, J. (2021) · Applied Sciences · doi:10.3390/app11146452 · Cited by 8
“In this way, feature classifiers such as Support Vector Machine (SVM) algorithms [18,19], deep learning techniques [20,21] or both [22] have taken centre stage.”
MethodLiu, Z., Chen, L., Wei, H., Zhang, Y., Chen, L., & Lv, M. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3214624 · Cited by 8
“The softmax classifier has been widely used for multiclass classification tasks [33].”
MethodSimani, S., Farsoni, S., & Castaldi, P. (2023) · Energies · doi:10.3390/en16093644 · Cited by 9
RetractedTranslation Invariance-Based Deep Learning for Rotating Machinery Diagnosis
Du, W., Wang, S., Gong, X., Wang, H., Yao, X., & PECHT, M. G. (2020) · Shock and Vibration · doi:10.1155/2020/1635621 · Cited by 8
“0016, the sparsity regularization term changes within the range [1, 10], and the sparsity proportion term changes within the range [0.”
BackgroundMethodInfluentialBig Data Analytics: A Literature Review Perspective
Al-Shiakhli, S. (2019) · DiVA (Luleå University of Technology) · Cited by 26
Sun, M., Zhang, P., Guo, K., Sun, J., Li, D., & Huang, T. (2025) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2025.08.035 · Cited by 8
TFD-Trans: Time-frequency hierarchical decomposition transformer for mechanical fault diagnosis
Wang, H., Ren, Z.-H., & Qi, J. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104303 · Cited by 9
Fault Classification of High Voltage Transmission Line Based on Convolutional Neural Network
Ye, W., Jian, S., Ou, R., Huang, S., Gong, X., Peng, X., & Yuan, H. (2020) · International Conference on Information Science and Technology · doi:10.1109/icist49303.2020.9201950 · Cited by 7
“Compared with traditional MLs, DL methods meet the end-to-end technical requirements and have promising application prospects [12].”
MethodApplication of improved adaptive method of CEEMD and data-drive in fault diagnosis
Liu, M., Xiong, J., Li, C., Sun, W., Zhang, Q., & Zhang, Y. (2024) · Robotic Intelligence and Automation · doi:10.1108/ria-03-2023-0035 · Cited by 8
Deep Belief Network Based Faulty Feeder Detection of Single-Phase Ground Fault
Wei, H., Wei, H., Lyu, Z., Bai, X., & Tian, J. (2021) · IEEE Access · doi:10.1109/access.2021.3129780 · Cited by 7
“This kind of signal processing based characteristic extraction method usually requires an in-depth understanding of signal characteristics to extract typical fault characteristics effectively [13].”
BackgroundMethodZheng, J., Liao, J., & Zhu, Y. (2023) · Sensors · doi:10.3390/s23052395 · Cited by 12
Zio, E. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-91152-8.00014-4 · Cited by 15
A Review of Manufacturing Big Data: Connotation, Methodology, Application and Trends
Junliang, W., Gao, P., Zhang, J., & Wang, L. (2023) · Journal of Mechanical Engineering · doi:10.3901/jme.2023.12.001 · Cited by 8
Zhao, Y., Liu, Y., & Wang, R. (2017) · The Journal of Engineering · doi:10.1049/joe.2017.0850 · Cited by 7
Computational Framework for Machine Fault Diagnosis with Autoencoder Variants
Verma, N. K., Dixit, S., Sevakula, R. K., & Salour, A. (2018) · International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC) · doi:10.1109/sdpc.2018.8664980 · Cited by 7
“[36] reported use of DNN to handle big industrial data for fault diagnosis.”
MethodFault Diagnosis of Planetary Gearbox Based on Signal Denoising and Convolutional Neural Network
Sun, G., Wang, Y., & Sun, C. (2019) · Prognostics and System Health Management Conference · doi:10.1109/phm-paris.2019.00024 · Cited by 8
“[5] integrated the sparse filtering theory into DNN, adaptively extracted the sparse features from the original vibration signal, improved the feature expression ability, and then input it to the Softmax classifier to identify the bearing fault, which has higher diagnostic accuracy.”
MethodGeneralized sparse filtering for rotating machinery fault diagnosis
Cheng, C., Hu, Y. Z., Wang, J., Liu, H., & PECHT, M. G. (2020) · The Journal of Supercomputing · doi:10.1007/s11227-020-03398-5 · Cited by 7
Comparison of motor fault diagnosis performance using RNN and K-means for data with disturbance
Choi, D., Han, J.-H., Park, S.-U., & Hong, S.-K. (2020) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas50221.2020.9268271 · Cited by 7
“CNN undergoes a process of extracting features of data using convolution and classifying data based on the extracted features [1].”
MethodFault diagnosis in industrial processes based on predictive and descriptive machine learning methods
Ragab, A., El-Koujok, M., Ghezzaz, H., & Amazouz, M. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-821092-5.00002-4 · Cited by 7
He, X., Xu, C., Chen, R., Wang, J., & Li, J. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1955/1/012086 · Cited by 7
“The fault diagnosis methods include traditional mathematical processing methods and intelligent diagnosis methods [3-6] .”
MethodIndustrial Fault Detection Using Transfer Learning Models
Chakraborty, S., Shamrat, F. M. J. M., Afrin, S., Saha, S., Ahmed, I., & Thapa, S. (2021) · International Conference on Smart Electronics and Communication (ICOSEC) · doi:10.1109/icosec51865.2021.9591740 · Cited by 7
“Lei et al. [9] suggested an Artificial Intelligence-based fault detection method.”
MethodA Hierarchical Sparse Discriminant Autoencoder for Bearing Fault Diagnosis
Zeng, M., Li, S., Li, R., Lu, J., Xu, K., Li, X., Wang, Y., & Du, J. (2022) · Applied Sciences · doi:10.3390/app12020818 · Cited by 7
A support vector machine framework for fault detection in molecular pump
Yuan, X., Kai, J., Chen, Y., Zuo, G., Zhuang, H. D., Li, J., & Hu, J. (2022) · Journal of Nuclear Science and Technology · doi:10.1080/00223131.2022.2080124 · Cited by 7
Bearing Fault Detection based on Internet of Things using Convolutional Neural Network
Chakraborty, S., Shamrat, F. M. J. M., Ahammad, R., Billah, M. M., Kabir, M., & Hosen, M. R. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.0130424 · Cited by 8
“For learning features from raw signals, they present a sparse filtering and neural network [7].”
MethodMiao, J., Deng, Z., Deng, C., & Dong, M. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3347251 · Cited by 7
“Lei et al. [24] implemented semi-supervised fault diagnosis by combining a two-layer AE and a classifier.”
MethodSurvey of real-time fault diagnosis techniques for electromechanical systems
Kia, S. H., Henao, H., & Capolino, G. (2017) · IEEE Workshop on Electrical Machines Design, Control and Diagnosis · doi:10.1109/wemdcd.2017.7947761 · Cited by 7
A novel feature representation method based on deep neural networks for gear fault diagnosis
Wang, J., Jiang, X., Li, S., & Xin, Y. (2017) · Prognostics and System Health Management Conference · doi:10.1109/phm.2017.8079168 · Cited by 7
Gear pitting fault diagnosis using disentangled features from unsupervised deep learning
Qu, Y., Zhang, Y., He, M., He, D., Jiao, C., & Zhou, Z. (2018) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc.2018.8409555 · Cited by 7
An accident diagnosis algorithm for HTR-PM based on deep learning methods
Li, Z., Sun, J., Tong, J., Sui, Z., & Gang, L. (2019) · Progress in Nuclear Energy · doi:10.1016/j.pnucene.2019.03.038 · Cited by 7
A Novel Unsupervised Learning Method Based on Cross-Normalization for Machinery Fault Diagnosis
Zhang, Z., Li, S., Lu, J., Wang, J., & Jiang, X. (2020) · IEEE Access · doi:10.1109/access.2020.2992201 · Cited by 7
“it has become a promise diagnosis technology for the era of big data [5], [6].”
BackgroundMethodChen, G. (2022) · Applied Intelligence · doi:10.1007/s10489-021-03107-6 · Cited by 7
“The temporal logic relationships among basic events rely on the operational modes of the systems, which also define the constraints of the event delays; Secondly, TFPGs can be easily explained with natural language and understood by human users, which enables the cooperation between fault diagnosis systems and human m…”
BackgroundLi, Q., Zhang, K., Abdurahman, A., Wang, K., & Yang, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132017 · Cited by 6
Rule guided transformers for dynamic knowledge adaptation in rotating machinery fault diagnosis
Hogea, E., Onchiş, D. M., Yan, R., & Zhou, Z. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104444 · Cited by 6
Fort, A., Landi, E., Mugnaini, M., & Vignoli, V. (2023) · Sensors · doi:10.3390/s23177546 · Cited by 10
“During the last decades a huge quantity of research work on this topic has led to a variety of different possible solutions, such as artificial neural networks (ANN), support vector machines (SVM), neural fuzzy network [12,13] Bayesian networks [14,15], self-organizing maps [16], extreme learning machines (ELM) [17,18…”
BackgroundMo, C., Huang, K., & Ji, H. (2024) · Scientific Reports · doi:10.1038/s41598-024-81118-2 · Cited by 8
Fault diagnosis and classifications of rolling mill bearing-gear based on GADF-TL-ShuffleNet-V2
Hou, D., Cheng, R., Zhang, B., Wan, Q., & Shi, P. (2025) · Journal of Vibration and Control · doi:10.1177/10775463251336975 · Cited by 9
Sadat, M. M. N., Tokhi, M., Azizi, M., Esmati, S., & Emynorane, R. H. (2025) · Global Education Trends · doi:10.61798/get.v3i2.391 · Cited by 7
“Emotional engagement was enhanced by gamification elements and instant feedback mechanisms that provided recognition for students' efforts, thereby reinforcing motivation and building academic confidence (Lei et al., 2016).”
Guo, L., Wang, J., Wang, S., Han, B., Zhang, X., Yan, Z., & Jia, M. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac73da · Cited by 6
“…and technology, the intelligent fault diagnosis of rotating machinery has become a current research hotspot and has been shown to rapidly and efficiently process massive ∗ Author to whom any correspondence should be addressed. collected signals and provide accurate fault diagnosis results [6–10].”
Bearing Fault Diagnosis Based on Wide Deep Convolutional Neural Network and Long Short Term Memory
Chen, Z., & Zhao, J. (2022) · Tehnicki vjesnik - Technical Gazette · doi:10.17559/tv-20220512135354 · Cited by 8
“At present, deep learning-based methods [10-13] have become popular in the field of bearing fault diagnosis, which can adaptively extract representative features and overcome the limitations of manual feature extraction.”
Discrete learning-based intelligent methodology for heart disease diagnosis
Khashei, M., & Bakhtiarvand, N. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.104700 · Cited by 7
Qian, L., Liu, P., Lu, H., Shi, J., & Zhao, X. (2024) · Sensors · doi:10.3390/s24041095 · Cited by 6
“In [36], a two-stage intelligent learning framework is investigated to identify the health status of mechanical equipment, including an unsupervised sparse filtering to learn features adaptively and softmax regression to automatically classify the mechanical health conditions.”
MethodGandhi, P., & Pahwa, S. (2024) · doi:10.1177/ijim.241240911 · Cited by 11
Zhu, Y., Zi, Y., Zhang, M., & Xu, J. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.103037 · Cited by 6
Cui, M., Ma, X., Guo, J., Hou, T., & Wang, Y. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3527600 · Cited by 6
The Impacts of Big Data Analytics and Artificial Intelligence on Marketing Strategies
Nwobodo, L. K. (2025) · Global journal of economic and finance research. · doi:10.55677/gjefr/05-2025-vol02e1 · Cited by 10
Shrink: A Breast Cancer Risk Assessment Model Based on Medical Social Network
Li, A., Wang, R., & Xu, L. (2017) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2017.168 · Cited by 6
“Today, big data of medical and health is hoped to deliver healthy services towards prevention, early intervention and optimal management [18-20].”
BackgroundAn improved Laplacian Eigenmaps method for machine nonlinear fault feature extraction
Jiang, Q., Zhu, Q., Liu, W., Wang, B., & Xu, F. (2017) · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · doi:10.1177/0954406217743536 · Cited by 6
“expertise, an intelligent fault diagnosis method is proposed using unsupervised feature learning towards mechanical big data.(12) With the development of modern signal processing methods, manifold learning-based nonlinear feature extraction method is becoming a research hotspot.”
MethodRetrogressive Analysis of Industrial Robot Rotate Vector Reducer Using Acoustic Emission Techniques
An, H., Liang, W. G., Zhang, Y., Li, Y., Lu, S., & Tan, J. (2018) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2018.8688113 · Cited by 6
“Lei[5-6] did the overload fatigue test by the bearing and dealt with the vibration signals based on theoretical analysis and developed several algorithm of bearing fault diagnosis and introduced feature learning method into fault diagnosis.”
BackgroundFault Diagnosis Based on A Stacked Sparse Auto-Encoder Network and KNN Classifier
Yan, Z., Yuan, X., Zhou, F., Song, Y. H., Xu, Q., & Shao, Y. (2019) · Chinese Automation Congress · doi:10.1109/cac48633.2019.8996595 · Cited by 6
“For traditional methods, it becomes much more challenging when the problems get complex and multidimensional [6].”
MethodXu, M., Baraldi, P., Yang, Z., & Zio, E. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118962 · Cited by 6
Bearing Fault Diagnosis of Split Attention Network Based on Deep Subdomain Adaptation
Wang, H., & Pu, L. (2022) · Applied Sciences · doi:10.3390/app122412762 · Cited by 6
“However, such fault diagnosis methods require additional processing of data characteristics and cannot provide fast diagnostic services [12,13].”
BackgroundSystematic Approach for the Test Data Generation and Validation of ISC/ESC Detection Methods
Klink, J., Grabow, J., Orazov, N., Benger, R., Hauer, I., & Beck, H.-P. (2023) · Batteries · doi:10.3390/batteries9070339 · Cited by 6
“Using an ECM instead of elaborated models such as mathematical [154] or electrochemical models [88] comes with some advantages:”
MethodCheng, Z. (2017) · International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC) · doi:10.1109/sdpc.2017.54 · Cited by 6
“Features reflecting the running condition of REBs are first extracted from different domains.”
BackgroundInfluentialA dirty data recognition method for machinery condition monitoring in big data era
Lei, Y., Zhou, X., Xu, X., & Jia, F. (2017) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2017.8217235 · Cited by 6
Self-citationAESGRU: An Attention-Based Temporal Correlation Approach for End-to-End Machine Health Perception
Zhang, W., Yang, D., Wang, H., Zhang, J., & Gidlund, M. (2019) · IEEE Access · doi:10.1109/access.2019.2943381 · Cited by 6
“same time reduces the algorithm’s dependence on feature engineering, as stated in [14]–[16].”
BackgroundConvolutional Neural Network for Fault Diagnosis of High-Speed Train Bogie
Huang, C., Qin, N., Huang, D., & Liang, K. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8866446 · Cited by 6
“Typical DL methods include deep belief network (DBN) [3], sparse auto-encoder [4], stacked denosing auto-encoder [5], and sparse filtering [6], etc.”
MethodBearing Fault Diagnosis Based on Deep Semi-supervised Small Sample Classifier
Hu, Y., Jinfeng, G., Qiang, Z., & Zheng, F. (2019) · Prognostics and System Health Management Conference · doi:10.1109/phm-qingdao46334.2019.8943025 · Cited by 6
“With the development of deep learning and its application in fault diagnosis, many experts have proposed intelligent fault diagnosis methods based on deep learning [3-5], which accept the original vibration signals to achieve the fault diagnosis.”
BackgroundMulti-source fault identification based on combined deep learning
Xing, D., Chen, R., Qi, L., Zhao, J., & Wang, Y. (2020) · MATEC Web of Conferences · doi:10.1051/matecconf/202030903037 · Cited by 6
Multidimensional Blind Deconvolution Method Based on Cross-Sparse Filtering for Weak Fault Diagnosis
Wang, S., Zhang, Z., Wang, J., & Han, B. (2020) · IEEE Access · doi:10.1109/access.2020.3037243 · Cited by 6
“In recent years, deep learning-based methods are applied gradually to rotating machinery fault diagnosis, such as intelligent fault classification [32], [33] and remaining useful life (RUL) prediction [34], [35].”
MethodDenoising convolutional autoencoder configuration for condition monitoring of rotating machines
de Godói, L. F., & Nóbrega, E. G. D. O. (2021) · Journal of the Brazilian Society of Mechanical Sciences and Engineering · doi:10.1007/s40430-020-02776-7 · Cited by 6
Soft Fault Diagnosis Using URV-LDA Transformed Feature Dictionary
Chen, C., Yang, Y. S., Ye, X., & Zhai, G. (2021) · IEEE Access · doi:10.1109/access.2021.3051409 · Cited by 6
“In modern industries, electromechanical systems have become more integrated and complex [1].”
BackgroundUnsupervised Root-Cause Analysis with Transfer Learning for Integrated Systems
Pan, R., Li, X., & Chakrabarty, K. (2021) · IEEE VLSI Test Symposium (VTS) · doi:10.1109/vts50974.2021.9441030 · Cited by 6
“To overcome the drawback of supervised methods, unsupervised methods have been proposed with less dependency on expert knowledge [2], [6].”
MethodHe, Y., Zang, C., Zeng, P., Wang, M., Wan, G., & Dong, Q. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-030-81007-8_49 · Cited by 6
Design and application of intelligent equipment management platform
Li, D., Liu, P., Huang, G., Ma, Y., Xie, Z., Li, Y., & Huang, X. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1983/1/012098 · Cited by 6
Fault Classification using Deep Learning in a Grid-Connected Photovoltaic Systems
Hichri, A., Mansouri, M. M., Hajji, M., Bouzrara, K., Nounou, H. N., & Nounou, M. N. (2022) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit55151.2022.9804132 · Cited by 6
“Among a variety of architectures, the objective is to discover the relation between the input and output variable [15], [16].”
BackgroundA Fault Diagnosis Method Based on EMD-SVM with Multi-Feature Fusion via Sound Signals
Yin, X., He, Q., Peng, S., Zhang, Y., & Zhang, B. (2022) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar54675.2022.9872243 · Cited by 6
“In the field of fault diagnosis via sound signals, there are two main aspects: the extraction and evaluation of fault signal feature based on signal processing and fault recognize [4].”
BackgroundSchroth, M., Hake, F., Merker, K., Becher, A., Klaeger, T., Huesmann, R., Eichhorn, D., & Oehm, L. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.11581 · Cited by 6
Wang, T., Li, T., Jiang, P., Cheng, Y., & Tang, T. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac2b72 · Cited by 5
Unsupervised Two-Stage Root-Cause Analysis With Transfer Learning for Integrated Systems
Pan, R., Li, X., & Chakrabarty, K. (2022) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2022.3176998 · Cited by 5
“To address the above limitation of supervised methods, unsupervised methods have been proposed with much less dependency on expert knowledge [4], [13]–[16].”
MethodBinomial adversarial representation learning for machinery fault feature extraction and diagnosis
Ma, L., Cheng, Y., Ding, Y., Zhao, Q. P., Wang, Z., & Lü, C. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109772 · Cited by 5
Fault diagnosis of printing press bearing based on deformable convolution residual neural network
Wu, Q., Zhu, Z., Tang, J., & Xia, Y. (2023) · Networks and Heterogeneous Media · doi:10.3934/nhm.2023027 · Cited by 5
Hou, B., Kong, J., Chen, Y., Liu, J., & Wang, D. (2022) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd57530.2022.10058298 · Cited by 5
“[20] designed a sparse filteringbased approach to achieve intelligent fault diagnosis.”
MethodStator Inter-Turn Fault Severity Classification Using Neural Based Approaches
Sharma, P., Cirrincione, G., Kumar, R., Mohammadi, A., & Cirrincione, M. (2023) · IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET) · doi:10.1109/ic_aset58101.2023.10150953 · Cited by 5
“Several stator and rotor breakdown cases were diagnosed using vibration or current monitoring with AI and ML techniques [9, 12-16].”
BackgroundMethodLing, Y., Fu, D., Jiang, P., Sun, Y., Yuan, C., Huang, D., Lu, J., & Lu, S. (2023) · Transactions of the Institute of Measurement and Control · doi:10.1177/01423312231185702 · Cited by 5
“In this circumstance, many intelligent algorithms based on ML models have been investigated recently (Jiang et al., 2022; Lei et al., 2016).”
MethodFault diagnosis method for rotating machinery based on SEDenseNet and Gramian Angular Field
Bai, R., Wang, H., Sun, W., & Shi, Y. (2024) · Eksploatacja i Niezawodnosc - Maintenance and Reliability · doi:10.17531/ein/191445 · Cited by 5
Application of a dense fusion attention network in fault diagnosis of centrifugal fan
Wang, R., Liu, Y., Fan, Z., Xu, X., & Wang, H. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05643-3 · Cited by 5
“However, the outcome of conventional intelligent diagnostic approaches relies heavily on the quality of feature extraction.”
Liu, Y., Xu, Y., Liu, J., Qin, H., & Niu, X. (2025) · Symmetry · doi:10.3390/sym17020241 · Cited by 5
Zhou, D., Ma, S., Chen, Y., Wei, T., Zhang, H., & Fang, W. (2018) · IEEE Conference on Prognostics and Health Management · doi:10.1109/icphm.2018.8448617 · Cited by 5
“However, these methods such as NN and SVM belongs to shallow learning model, and they are difficult to learn complex nonlinear relationships effectively [12, 13].”
MethodJiaxian, C., Wentao, M., & Yuejian, C. (2020) · Asia-Pacific International Symposium on Advanced Reliability and Maintenance Modeling (APARM) · doi:10.1109/aparm49247.2020.9209439 · Cited by 5
“Through multiple hidden-neuron layers, deep neural networks can effectively extract representative features of bearings from raw monitoring data [8].”
BackgroundBao, H., Shi, Z., Wang, J., Zhang, Z., & Zhang, G. (2021) · Entropy · doi:10.3390/e23081075 · Cited by 5
“The first method, standard sparse filtering (SF) [27] method can achieve the accuracy of 92.”
MethodFault Diagnosis for Rolling Bearing Based on RF-LSTM
Li, Q., Wang, X., Yang, Y., Wang, R., & Lv, F. (2021) · CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS) · doi:10.1109/safeprocess52771.2021.9693700 · Cited by 5
“Methods based on machine learning (ML) and statistic have been widely applied to fault diagnosis of rotary machines, such as K-Nearest Neighbor (K-NN) algorithm[2], Bayesian classifier[3], Support Vector Machine (SVM) [4], Artificial Neuron Network (ANN) [5] and deep learning (DL) methods[6].”
Learning self-supervised task progression metrics: a case of cloth folding
Verleysen, A., Biondina, M., & wyffels, F. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03466-8 · Cited by 9
“In [15] raw manufacturing data is converted to latent features learned by an autoencoder neural network.”
MethodResearch on residual life prediction of rolling bearings based on STFT-CNN
Liu, Q., Xu, S., & Cao, X. (2022) · International Conference on Computer Application and Information Security (ICCAIS) · doi:10.1117/12.2637638 · Cited by 5
“Jia, Lei, Ding made good progress in characterizing the degradation state of bearings and transmission by using the deep learning method and the method of establishing health indicators [6-8].”
MethodHou, B., Liu, J., & Wang, D. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3322491 · Cited by 5
“An interesting finding of this work [24] is that weight parameters in sparse filtering showed some similarity to the Gabor wavelet.”
BackgroundMethodAshore-Onisemo, F., Okwesa, I. J., & Unamma, U. M.-L. (2020) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit2066446 · Cited by 11
An intelligent fault diagnosis method in the case of rotating speed fluctuations
An, Z., Li, S., Qian, W., & Wang, J. (2017) · Prognostics and System Health Management Conference · doi:10.1109/phm.2017.8079199 · Cited by 5
“Therefore, in this paper, aiming at these problems, based on the deep learning, the method has been applied in [10].”
MethodYang, J., Lee, D., & Kim, J. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-94229-2_47 · Cited by 5
Anomaly Detection of 2.4L Diesel Engine Using One-Class SVM with Variational Autoencoder
Jang, G.-B., & Cho, S. (2019) · Annual Conference of the PHM Society · doi:10.36001/phmconf.2019.v11i1.804 · Cited by 5
Zhang, Z., Yang, Q., & Zhou, W. (2019) · IEEE Access · doi:10.1109/access.2019.2951409 · Cited by 5
“According to [16], [31], F − score is defined as”
BackgroundMethodInfluential
Metadata
- Authors
- Lei, Y., Jia, F., Lin, J., Xing, S., & Ding, S. X.
- Affiliations
- Xi'an Jiaotong University (CN)
- University of Duisburg-Essen (DE)
- Venue
- IEEE Transactions on Industrial Electronics
- Published
- 2016-05
- Volume
- 63
- Issue
- 5
- Pages
- 3137-3147
- ISSN
- 0278-0046 (ISSN-L)
- 1557-9948
- OpenAlex
- W2317595875
- Semantic Scholar
- 2d2fe4a73c98933ae9b8df73c8452b0d8be6475e
- Cited by
- 1,191
- References
- 53
- Citations by year
- 2026: 53 · 2025: 69 · 2024: 88 · 2023: 130 · 2022: 168 · 2021: 177 · 2020: 199 · 2019: 142 · 2018: 97 · 2017: 63 · 2016: 5
- FWCI
- 85.94
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Industrial Electronics (publishedVersion)
- Funders
- National Natural Science Foundation of China (51222503, 51475355, 51421004)
- Fundamental Research Funds for the Central Universities (2012jdgz01, XTD2014001)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- intelligent fault diagnosis, unsupervised feature learning, mechanical vibration signals, sparse filtering, two-layer neural networks, softmax regression, bearing fault classification, motor bearings
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.