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 601–700 of 1,001
Zhao, X., Qin, Y., He, C., & Jia, L. (2020) · IEEE Access · doi:10.1109/access.2020.2976868 · Cited by 18
“Research related to bearing fault diagnosis has attracted significant attention in recent years [1]–[3].”
BackgroundAn Improved Wide-Kernel CNN for Classifying Multivariate Signals in Fault Diagnosis
van den Hoogen, J., Bloemheuvel, S., & Atzmueller, M. (2020) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw51313.2020.00046 · Cited by 20
“In order to measure the behavior of a bearing element, sensors are placed on the designated parts of the machine that record vibration signals [9].”
BackgroundMethodGörür, O. C., Yu, X. Y., & Sivrikaya, F. (2021) · Applied Sciences · doi:10.3390/app11115042 · Cited by 18
Intelligent fault detection of reciprocating compressor using a novel discrete state space
Zhang, Y., & Zhang, L. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.108583 · Cited by 18
Intelligent fault diagnosis for rotating machinery using L 1/2 -SF under variable rotational speed
Wang, J., Ji, S., Han, B., & Bao, H. (2020) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/0954407020964625 · Cited by 18
“Lei et al.(23) first constructively employed SF to bearing intelligent fault diagnosis using a twostage learning method.”
MethodZhang, C., Wang, W., Chen, Z., Fan, B., Jian-guo, W., Gu, F., & Xue, Y. (2021) · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · doi:10.1177/09544062211016505 · Cited by 17
Emerging practices and research issues for big data analytics in freight transportation
Gorman, M. F., Clarke, J.-P., de Koster, R. B. M., Hewitt, M., Roy, D., & Zhang, M. (2023) · Maritime Economics & Logistics · doi:10.1057/s41278-023-00255-z · Cited by 23
Zhou, H., Yan, P., Huang, Q., Wu, D., Pei, J., & Zhang, L. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121076 · Cited by 17
Optimal weighted multi-scale entropy-energy ratio feature for machine fault diagnosis
Shen, C., Jiang, P., Luo, J., Lin, G., & Zhang, S. (2024) · Measurement · doi:10.1016/j.measurement.2024.115782 · Cited by 17
Ding, J., Wang, Y., Qin, Y., & Tang, B. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.103048 · Cited by 18
Zafar, T., Kamal, K., Sheikh, Z., Mathavan, S., Ali, U., & Hashmi, H. N. (2017) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-017-0606-2 · Cited by 19
“Lei et al. [15] developed a neural network based algorithm for intelligent diagnosis of rotating machinery using unsupervised features.”
MethodA Neural Network Model for Material Degradation Detection and Diagnosis Using Microscopic Images
Choi, W., Huh, H., Tama, B. A., Park, G., & Lee, S. (2019) · IEEE Access · doi:10.1109/access.2019.2927162 · Cited by 18
Lu, Y., & Wang, Y. (2021) · Procedia Manufacturing · doi:10.1016/j.promfg.2021.06.071 · Cited by 18
Li, X., Jin, W., Xu, X., & Yang, H. (2022) · Symmetry · doi:10.3390/sym14122654 · Cited by 18
Rahm, J., Graube, M., Müller, R., Klaeger, T., Schegner, L., Schult, A., Bönsel, R., Carsch, S., Oehm, L., & Urbas, L. (2018) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2018.8502615 · Cited by 20
“in rotating machines, mostly for condition monitoring and predictive maintenance [23], [24].”
BackgroundHan, X. D., Jiang, J., Zhang, C., Wen, Z., Chen, G., & Liu, Y. (2019) · IET Generation Transmission & Distribution · doi:10.1049/iet-gtd.2019.0832 · Cited by 17
Shift-Invariant Sparse Filtering for Bearing Weak Fault Signal Denoising
Wang, R., Ding, X., He, D. K., Li, Q., Li, X., Tang, J. X., & Huang, W. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3309848 · Cited by 16
“Sparse filtering (SF) is an unsupervised learning algorithm with powerful feature extraction ability, which has been increasingly concern in machinery fault diagnosis in recent years [23], [25].”
BackgroundMethodZhao, S., Bao, L., Hou, C., Bai, Y., & Yu, Y. (2024) · Structural Health Monitoring · doi:10.1177/14759217231225986 · Cited by 16
Attention-Enhanced AGRU Framework for Induction Motor Incipient Fault Diagnosis in Electric Vehicles
Saleh, M. A., Ghrayeb, A., Refaat, S. S., Abu‐Rub, H., Khatri, S. P., & Kammermann, J. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3502781 · Cited by 22
“…sparse autoenocders (SSAEs)-based DNN for bearing FD; Shao et al. [29] proposed a new ensemble deep autoencoders method for bearing FD; Lei et al. [30] proposed an unsupervised feature learning method-based sparse filtering for intelligent mechanical FD; Shao et al. [11] applied deep belief…”
yufei, C., Shi, J., Hu, J., Shen, C., Huang, W., & Zhu, Z. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adb329 · Cited by 18
“On the other hand, frequency-domain models are adept at identifying specific fault frequencies but tend to overlook transient characteristics, leading to reduced diagnostic accuracy, especially in noisy environments [12].”
Hadraoui, H. E., Maghraoui, A. E., Laayati, O., Sabani, E., Zegrari, M., & Chebak, A. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106157 · Cited by 17
KPCA and AE Based Local-Global Feature Extraction Method for Vibration Signals of Rotating Machinery
Hu, X., Xiao, Z., Liu, D., Tang, Y., Malik, O. P., & Xia, X. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/5804509 · Cited by 18
“+erefore, developing accurate fault diagnosis technologies is of great significance to avoid potential losses [3, 4].”
BackgroundCheng, C., Liu, W., Wang, W., & PECHT, M. G. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac02f3 · Cited by 17
Tang, J., Li, C., Fu, Y., & Li, C. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/4711617 · Cited by 16
“Although their research method has high accuracy, it lacks specific system test content [4].”
BackgroundQian, W., Li, S., & Lu, J. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.104749 · Cited by 17
Feature Mining and Sensitivity Analysis with Adaptive Sparse Attention for Bearing Fault Diagnosis
Jiang, Q., Bao, B., Hou, X., Huang, A., Jiang, J., & Mao, Z. (2023) · Applied Sciences · doi:10.3390/app13020718 · Cited by 16
A Review on Neurocomputing Based wind Turbines Fault Diagnosis and Prognosis
Baltazar, S., Li, C., Daniel, H. A., & de Oliveira, J. V. (2018) · Prognostics and System Health Management Conference · doi:10.1109/phm-chongqing.2018.00081 · Cited by 20
Jiang, N., Hu, X., & Li, N. (2020) · Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering · doi:10.1177/0959651819901034 · Cited by 16
“Lei et al. 17 and Wang et al. 18 applied deep autoenco-ders to learn features from signals directly for the health conditions classification and fault diagnosis of the bearing and blade breakage.”
BackgroundA review of recent AI applications in next-generation power electronics
Safari, A., Oshnoei, A., & Blaabjerg, F. (2025) · Applied Energy · doi:10.1016/j.apenergy.2025.126923 · Cited by 15
Vibration Diagnostic Methods from Methodsof Obtaining Data to Processing It Using Modern Means
Zhuravlev, A. O., Polyakov, A. O., & Andrikov, D. A. (2024) · RUDN Journal of Engineering Researches · doi:10.22363/2312-8143-2024-25-4-380-396 · Cited by 15
Sendlbeck, S., Fimpel, A., Siewerin, B. J., Otto, M. K., & Stahl, K. (2021) · International Journal of Prognostics and Health Management · doi:10.36001/ijphm.2021.v12i2.3026 · Cited by 18
“Approaches also exist that differ from the common combination of convolutional and LSTM layers, for example, by using sparse filtering for feature learning (Lei, Jia, Lin, Xing, & Ding, 2016).”
BackgroundZarchi, M., & Shahgholi, M. (2022) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-022-00702-w · Cited by 19
Kim, H., Ko, J. U., Na, K., Lee, H., Kim, H.-S., Son, J.-D., Yoon, H., & Youn, B. D. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119377 · Cited by 15
Intelligent Compound Fault Diagnosis of Roller Bearings Based on Deep Graph Convolutional Network
Chen, C., Yuan, Y., & Zhao, F. (2023) · Sensors · doi:10.3390/s23208489 · Cited by 16
“Common feature extraction methods include Wavelet Transform (WT), Principal Component Analysis (PCA), Short Time Fourier Transform (STFT), etc. [6].”
MethodShahid, M., Zabiri, H. B., Taqvi, S. A. A., & Hai, M. (2024) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2024.07.001 · Cited by 15
Zhang, Z., Yang, Q., & Wu, Z. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.3010505 · Cited by 15
“Lei et al. [2] have systematically investigated the effect of N in , N out , and λ using the motor bearing dataset.”
BackgroundMethodInfluentialHuang, M., Huang, T., Zhao, Y., & Dai, W. (2021) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/1043/4/042015 · Cited by 15
Xu, K., Li, S., Li, R., Lu, J., & Zeng, M. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac20f1 · Cited by 15
“And then, with the rise of deep learning, due to its powerful nonlinear feature classification ability, it is gradually applied in a large number of intelligent fault diagnosis [11].”
Gearbox fault identification based on lightweight multivariate multidirectional induction network
Zhu, X., Wang, R., Fan, Z., Xia, D., Liu, Z., & Li, Z. (2022) · Measurement · doi:10.1016/j.measurement.2022.110977 · Cited by 15
Chandrasekar, T., Raju, S. K., Manikandan, R., Patan, R., & Gandomi, A. H. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.108820 · Cited by 19
Selvaraj, S., Kavin, B. P., Kavitha, C., & Lai, W. (2022) · Electronics · doi:10.3390/electronics11234014 · Cited by 15
Guo, S., Zhou, B., Yang, Y., Wu, Q., Xiang, Y., & He, Y. (2022) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2022.3231581 · Cited by 15
“Finally, the gradient is calculated to update weight coefficients and biases in BPNN as follows [39],”
MethodArtificial Intelligence in Manufacturing Processes
Chryssolouris, G., Alexopoulos, K., & Arkouli, Z. (2023) · Studies in systems, decision and control · doi:10.1007/978-3-031-21828-6_2 · Cited by 17
Wang, S., Lei, Y., Lü, N., Li, X., & Yang, B. (2023) · Frontiers of Mechanical Engineering · doi:10.1007/s11465-022-0736-9 · Cited by 15
“[5] generated spatial-temporal graphs from the multivariate temporal data and then used the graphs for graph learning to improve the remaining useful life prediction.”
BackgroundMethodSelf-citationShe, D., Peng, N., Jia, M., & PECHT, M. G. (2020) · Journal of Instrumentation · doi:10.1088/1748-0221/15/06/p06002 · Cited by 15
“The condition monitoring and fault diagnosis of mechanical equipment are entering the era of big data gradually [1, 2].”
BackgroundCen, J., Chen, Z., Wu, Y., & Yang, Z. (2022) · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · doi:10.1177/09544062221136490 · Cited by 14
“…are 30 : uses ensemble empirical mode decomposition (EEMD) and SVM, 31 is based on principal component analysis (PCA) and deep belief network (DBN), 32 uses sparse filtering to learn features and employs Softmax to classify the health conditions, 33 uses deep convolutional network (ConvNet) for…”
MethodInfluentialShul, Y., Yi, W., Choi, J., Kang, D.-S., & Choi, J. (2023) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2023.110102 · Cited by 14
Wang, G., Xue, L., Zhu, Y., Zhao, Y., Jiang, H., & Wang, J. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106852 · Cited by 14
Qu, Y., Li, T., Fu, S., Wang, Z., Chen, J., & Zhang, Y. (2024) · Nonlinear Dynamics · doi:10.1007/s11071-024-10221-w · Cited by 17
“Lei et al. [25] developed a stacked autoencoder that employs a two-stage intelligent fault diagnosis method by first learning features from mechanical vibration signals using unsupervised sparse filtering, then the health status is classified using a Softmax classifier.”
Ten industrial software towards smart manufacturing
Gao, T., Wang, L., Song, W., Cheng, Y., Zuo, Y., Xiang, F., Zhang, H., & Tao, F. (2025) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2025.01.012 · Cited by 19
Global–Local Attention-Aware Zero-Shot Learning for Industrial Fault Diagnosis
Tang, H., Jing, W., Tang, D., Yang, Z., Yang, X., & Xie, W. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3550233 · Cited by 28
“Lei et al. [41] developed a two-layer autoencoder to extract features from fault signals, followed by softmax regression for health condition classification.”
Wang, B., Liu, C., Chen, S., Dong, S., & Hu, J. (2019) · IEEE Access · doi:10.1109/access.2019.2937993 · Cited by 14
“Besides using neural network with controllers, other applications also include parameter estimation [34], fault diagnostics [35], etc.”
MethodSmart dampers-based vibration control – Part 1: Measurement data processing
Nguyen, S. D., Choi, S., & Kim, J. (2020) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2020.106958 · Cited by 14
Three-Stage Root Cause Analysis for Logistics Time Efficiency via Explainable Machine Learning
Hao, S., Liu, Y., Wang, Y., Wang, Y., & Zhe, W. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539024 · Cited by 16
“From technical perspective, the practical problem considered in this work can potentially be solved using root cause analysis (RCA), which has been extensively studied and applied in multiple qualitycontrol related domains such as manufacturing [9, 17, 35, 37], mechanics [12], telecommunications [7, 38], supply chain…”
BackgroundXue, H., Song, Z., Wu, M. Y., Sun, N., & Wang, H. (2022) · Sensors · doi:10.3390/s22166316 · Cited by 14
“However, as IWMs are often working in variable and complex conditions, the methods directly applied for fault diagnosis show neither superior performance nor acclimatization [34,35].”
BackgroundMethodZheng, J., Liao, J., & Chen, Z. (2022) · Sensors · doi:10.3390/s22176489 · Cited by 15
“Although some excellent work fused multiple signal processing, deep learning, transfer learning, and other advanced technologies, our work still had higher fault diagnosis performance than theirs [31–34 ,45, 47, 51 ].”
BackgroundFault Diagnosis of Energy Networks: A Graph Embedding Learning Approach
Zhang, J., Cheng, Y., & He, X. Y. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3216669 · Cited by 18
“Although many fault diagnosis methods have been reported for traditional single energy networks, these methods may fail when the above assumptions of the ideal environment are not satisfied [33], [34].”
BackgroundLou, C., Atoui, M. A., & Li, X. (2023) · Transactions of the Institute of Measurement and Control · doi:10.1177/01423312231157118 · Cited by 17
“Finally, shallow learning-based classification models may not be able to completely learn the complex mapping relationship between signals and health states, resulting in insufficient generalization performance in fault diagnosis toward big data (Lei et al., 2016).”
Zhang, Z., Nie, G., Shao, M., Li, L., Zhou, J., & Shao, S. (2023) · Nonlinear Dynamics · doi:10.1007/s11071-023-08441-7 · Cited by 15
“Owing to its simple structure, few hyper-parameters to be adjusted, and high computational efficiency, sparse filtering has been widely applied in mechanical fault diagnosis [32].”
BackgroundHybrid Multi-model Feature Fusion-Based Vibration Monitoring for Rotating Machine Fault Diagnosis
Jigyasu, R., Shrivastava, V., & Singh, S. (2023) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-023-01014-3 · Cited by 15
“Monitoring the motor can be done with multiple 88.9% [55] 92.5% [56] 95.8% [57] 97.91% [58] 99.66% [59] 99.6% [60] 98.8% 98.8% 99.4% 99.4% 99.8% 96.8% [61] 98.75% [62] 92.4% [63] 99 domains, such as current, acoustic, and thermal; data from them can be merged to develop a more reliable model.”
InfluentialHadraoui, H. E., Laayati, O., Maghraoui, A. E., Sabani, E., Zegrari, M., & Chebak, A. (2023) · Global Power, Energy and Communication Conference · doi:10.1109/gpecom58364.2023.10175674 · Cited by 14
Shen, Z., Kong, X., Cheng, L., Wang, R., & Zhu, Y. (2024) · Sensors · doi:10.3390/s24041290 · Cited by 14
“The unsupervised learning [37] method is a two-layer neural network for intelligent fault diagnosis utilizes sparse fi ltering for feature learning of vibration signals and Softmax regression for classifying health conditions; MA-MSCNN [24] innovatively combines multi-scale convolutional layers with…”
MethodAn automatic feature extraction method and its application in fault diagnosis
Wang, J., Li, S., Jiang, X., & Cheng, C. (2017) · Journal of Vibroengineering · doi:10.21595/jve.2017.17906 · Cited by 14
“[24] investigated the selection of these two parameters.”
BackgroundHan, B., Jia, S., Liu, G., & Wang, J. (2020) · Shock and Vibration · doi:10.1155/2020/8836477 · Cited by 14
“[8] developed an unsupervised feature learning method based on sparse filtering to directly extract features from mechanical vibration signals and then classified the fault classes through softmax regression.”
MethodQian, W., Li, S., Yao, T., & Xu, K. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106886 · Cited by 14
Pedram, R., & Chaibakhsh, A. (2025) · Journal of Control and Decision · doi:10.1080/23307706.2025.2567006 · Cited by 13
Yao, J., Lu, B., & Zhang, J. (2021) · IEEE Access · doi:10.1109/access.2021.3104668 · Cited by 13
Cao, J., & Liu, Y. (2022) · Structural Health Monitoring · doi:10.1177/14759217221078766 · Cited by 14
How analytics is driving the supply chain innovation in North America
Rao, A. M., & Rothstein, M. A. (2022) · Business & IT · doi:10.14311/bit.2022.01.19 · Cited by 13
Data-driven Diagnostics for Electric Traction Systems: A Study of Induction Motor
Hadraoui, H. E., Zegrari, M., Maghraoui, A. E., Laayati, O., Sabani, E., & Chebak, A. (2023) · IEEE EUROCON - International Conference on Computer as a Tool (EUROCON) · doi:10.1109/eurocon56442.2023.10199047 · Cited by 13
“Yet another study [32] proposed substituting conventional techniques for feature extraction with ANN to detect broken rotor bar, as well as unbalance and misalignment, with an accuracy rate of 99.”
MethodMa, S., Cheng, G., Li, Y., Huang, Y., & Zhuang, D. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121817 · Cited by 15
Fault detection and diagnosis of electric vehicles using artificial intelligence
Mishra, D. P., Padhy, S. S., Pradhan, P. S., Gupta, S., Senapati, A., & Salkuti, S. R. (2024) · International Journal of Applied Power Engineering (IJAPE) · doi:10.11591/ijape.v13.i3.pp653-660 · Cited by 15
The Review of Bearing Fault Diagnosis Technology Based on Machine Learning
Jiang, Y. (2024) · Journal of advances in engineering and technology. · doi:10.62177/jaet.v1i3.91 · Cited by 13
Phusakulkajorn, W., Zeng, Y., Li, Z., & Núñez, A. A. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3557712 · Cited by 13
“In [40], [41], and [42], a method based on sparse filtering, an unsupervised two-layer neural network, was proposed for fault feature learning from mechanical vibration signals.”
Tamuly, P., Sharma, S. D., & Nava, V. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.121199 · Cited by 13
A Novel Autoencoder with Dynamic Feature Enhanced Factor for Fault Diagnosis of Wind Turbine
Nie, X., Liu, S., & Xie, G. (2020) · Electronics · doi:10.3390/electronics9040600 · Cited by 14
“Various DNNs, for example, autoencoder (AE) [13,19,20], sparse filter [4,21], deep belief network (DBN), convolutional neural network (CNN) [22,23], recurrent neural network (RNN) [24], have been employed widely for many challenging problems in fault diagnosis.”
Research on fault diagnosis method of rolling bearing based on 2DCNN
Peng, X., Zhang, B., & Gao, D. Q. (2020) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc49329.2020.9164026 · Cited by 13
Zhang, G., Han, B., Li, S., Wang, J., & Wang, X. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/abf3fb · Cited by 13
“Meanwhile, these algorithms have been widely adopted in practice to prove their effectiveness [26].”
Gargiulo, F., Liccardo, A., & Moriello, R. S. L. (2022) · Energies · doi:10.3390/en15124407 · Cited by 13
Wang, C., Qiao, Z., Huang, Z., Xu, J., Fang, S., Zhang, C., Liu, J., Zhu, R., & Lai, Z. (2022) · Sensors · doi:10.3390/s22228730 · Cited by 13
“To make the SR outputs able to be processed by the CNN for classification, a mapping method based on a noise intensity sequence is further proposed to convert the time-domain output of the Duffing system into an image that can be further processed in classification.”
Kumar, J. A., Gowthambigai, M., Shanker, N. R., & Jasper, J. (2022) · International Journal of Emerging Electric Power Systems · doi:10.1515/ijeeps-2022-0214 · Cited by 13
Hadraoui, H. E., Laayati, O., Maghraoui, A. E., Sabani, E., Zegrari, M., & Chebak, A. (2023) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme57830.2023.10253328 · Cited by 14
Ning, Y., Wang, G., Yu, J., & Jiang, H. (2018) · 2018 Condition Monitoring and Diagnosis (CMD) · doi:10.1109/cmd.2018.8535843 · Cited by 14
Xu, H., Song, P., & Liu, B. (2019) · IEEE International Conference on Automation, Electronics and Electrical Engineering (AUTEEE) · doi:10.1109/auteee48671.2019.9033363 · Cited by 16
“used multiple fully connected layers to extract multiple local eigenvectors of vibration signal, and used the mean value of these vectors as the feature of the whole signal for classification with softmax regression [6].”
MethodChen, J., Chang, Y., Qu, C., Zhang, M., Li, F., & Pan, J. H. (2020) · ISA Transactions · doi:10.1016/j.isatra.2020.07.039 · Cited by 14
AnoGAN-Based Anomaly Filtering for Intelligent Edge Device in Smart Factory
Kim, D., Cha, J., Oh, S., & Jeong, J. (2021) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1109/imcom51814.2021.9377409 · Cited by 13
“Support vector machine (SVM) [6], Bayesian classifier [7] and Deep Neural network [8], [9] have received attention by algorithm.”
MethodZhang, Z., Yang, Q., & Zi, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.04.066 · Cited by 13
Ma, S., Cheng, G., Li, Y., & Zhao, R. (2023) · Measurement · doi:10.1016/j.measurement.2023.112835 · Cited by 13
Li, Y., Chai, Y., Zhou, H., & Yin, H. (2019) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2019.12.420 · Cited by 13
An Explainable Deep Learning-based Prognostic Model for Rotating MachineryPreprint
Lee, N., Azarian, M. H., & PECHT, M. G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.13608 · Cited by 13
“can function as filters [8, 9], the second model replaced the”
BackgroundMethodDeep Q‐learning recommender algorithm with update policy for a real steam turbine system
Rousta, M. M., Shoorehdeli, M. A., Yari, M., & Ghahremani, A. (2023) · IET Collaborative Intelligent Manufacturing · doi:10.1049/cim2.12081 · Cited by 12
Yu, T., Jiang, Z., Ren, Z., Zhang, Z., Zhang, Y., Zhou, S., & Zhou, X. (2024) · Structural Health Monitoring · doi:10.1177/14759217241296804 · Cited by 12
“12–14 Recently, with the emergence of big data and the rapid development of deep learning, the intelligent diagnosis method based on deep learning has become a research hotspot.”
An, Z., Li, S., Wang, J., Qian, W., & Wu, Q. (2018) · Applied Sciences · doi:10.3390/app8060906 · Cited by 13
“[28], when the important parameter of input dimension increased, an initial increase in testing accuracies was followed by a marked decrease (in this paper, the rule is called non-monotonicity).”
BackgroundMethodInfluentialTong, J., Luo, J. M., Pan, H., Zheng, J., & Zhang, Q. (2020) · Shock and Vibration · doi:10.1155/2020/8891905 · Cited by 12
“*e shallow structure of machine learning lacks powerful representation capabilities and has difficulty in effectively learning the complex nonlinear relationships in mechanical fault diagnosis problems [13].”
BackgroundQian, W., Li, S., & Lu, J. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3148993 · Cited by 12
“As N1 and N2 are regular hyperparameters and their tuning has been widely investigated [16], so only their final setting (400 and 200, respectively) is provided here.”
BackgroundA multi-scale feature fusion network-based fault diagnosis method for wind turbine bearings
Ma, M., Hou, Y., & Li, Y. (2022) · Wind Engineering · doi:10.1177/0309524x221114621 · Cited by 12
Sun, Z., Wang, Y., Sun, G., Gao, J., & Pan, Z. (2022) · Structural Health Monitoring · doi:10.1177/14759217221112835 · Cited by 12
Zhang, Z., Xu, S., & Chen, H. (2023) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2023.110338 · Cited by 12
A Novel Data-Driven Fault Diagnosis Method Based on Deep Learning
Zhang, Y., Gao, L., Li, X., & Li, P. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-61845-6_44 · Cited by 12
Data-Based Fault Diagnosis Model Using a Bayesian Causal Analysis Framework
Diallo, T., Henry, S., Ouzrout, Y., & Bouras, A. (2018) · International Journal of Information Technology & Decision Making · doi:10.1142/s0219622018500025 · Cited by 12
“These 35 variables are divided into 3 groups according to the data model proposed in Section 4: 26 machine/process parameters (XMEAS(5), XMEAS(9), XMEAS(14), XMEAS(17), XMEAS(7), XMEAS(21), XMEAS(10), XMEAS(20), XMEAS(12), XMEAS(13), XMEAS(22), XMEAS(16), XMEAS(23), XMEAS(24), XMEAS(25), XMEAS(26), XMEAS(27), XMEAS(28…”
BackgroundInfluential
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.