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 901–1,000 of 1,001
Han, B., Zhang, G., Wang, J., Wang, X., Jia, S., & He, J. (2020) · IEEE Access · doi:10.1109/access.2020.2975531 · Cited by 5
“Most of the methods used in fault diagnosis can achieve high accuracy under the general assumption that training and testing datasets are extracted at constant rotating speeds [4], [5].”
MethodZhou, C. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/7268963 · Cited by 5
“Since the database table is the main unit of database, a database table firstly needs to be built through the sensor data, and then the fixed database relationship rules shall be specified [13].”
BackgroundHui, D., & Xie, D. (2021) · Mobile Information Systems · doi:10.1155/2021/3315160 · Cited by 6
“,ese provide the feasibility for the introduction of big data into tax information construction [22].”
BackgroundLoad Fault Diagnosis in Induction Motor using Artificial Intelligence Algorithm
Kumar, B. R., Gowrisankar, M., Ramana, S., Aakash, P. D., & Aravind, S. (2022) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc54411.2022.9885468 · Cited by 5
Numerical Simulation Data-Aided Domain-Adaptive Generalization Method for Fault Diagnosis
Yan, T., Guo, J., Zhou, Y., Zhu, L., Fang, B., & Xiang, J. (2025) · Sensors · doi:10.3390/s25113482 · Cited by 4
“This can both ensure the normal operation of the machinery and serve as an important measure to protect the safety of the operator [1–4].”
Gabor Wavelet Initialized Sparse Filtering: An Interpretable Network for Bearing Fault Diagnosis
Wang, J., Wei, Y., Jiang, X., Bao, J., Jiang, X., Zhang, Z., & Jiang, X. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3580858 · Cited by 4
Eljyidi, A., Jebari, H., Rekiek, S., & Reklaoui, K. (2025) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2025.0161021 · Cited by 4
“While effective to a certain degree, this process is notoriously time-consuming, subjective to expert bias, and may easily miss subtle but critical degradation indicators hidden within the raw data [22].”
Belay, M. A., Bernardino, L. F., Blakseth, S. S., Rasheed, A., Montañés, R. M., & Rossi, P. S. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3630886 · Cited by 4
“Consequently, unsupervised fault detection methods, which do not depend on labeled data, provide considerable advantages for proactive diagnostics [17].”
HATİPOĞLU, A., & Yılmaz, E. (2026) · Sensors · doi:10.3390/s26031015 · Cited by 4
Wu, Y., Hu, Z., An, W., Li, X., Wang, X., Du, P., & Yu, X. Y. (2019) · IEEE Access · doi:10.1109/access.2019.2927039 · Cited by 4
“Therefore, automatic fault diagnosis of rolling element bearing under the variable conditions is of great significance [2].”
BackgroundA Study on Multiple Factors Affecting the Accuracy of Multiclass Skin Disease Classification
Fan, J., Kim, J., Jung, I., & Lee, Y. (2021) · Applied Sciences · doi:10.3390/app11177929 · Cited by 4
Finite‐time sliding mode fault‐tolerant control of PEM fuel cell air supply system
Wang, Z., Guo, X., Dong, Z., & Cao, S. (2024) · Asian Journal of Control · doi:10.1002/asjc.3376 · Cited by 4
“[15] proposes a learning method for machine intelligent diagnosis, which uses an unsupervised neural network to learn features from mechanical vibration signals.”
Lu, Z., Chu, Z., Min, Z., & Dong, X. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06278-8 · Cited by 5
“Among these hyper-parameters, I , J and η have been systemically investigated in the published works, such as [22, 30].”
Zhang, D., Stewart, E., Entezami, M., & Roberts, C. (2019) · Prognostics and System Health Management Conference · doi:10.1109/phm-paris.2019.00060 · Cited by 6
“Many researchers have proposed different DL algorithms to build an ‘end-to-end’ model for machinery condition monitoring [6, 7] which can extract fault features directly from raw data.”
BackgroundMotor Bearing Fault Diagnosis Based on Wavelet Packet Analysis and Sparse Filtering
Wang, H., & Sun, W. (2021) · IEEE International Electrical and Energy Conference (CIEEC) · doi:10.1109/cieec50170.2021.9510588 · Cited by 4
Al-Tameemi, A. A., Wang, K., Li, L., & Zalhaf, A. S. (2021) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec52019.2021.9586957 · Cited by 4
Intelligent of Electric Vehicle Heat Pump Air Conditioning Control System
Zhao, L., Hou, W., & He, Q. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2143/1/012043 · Cited by 4
Zhu, Q., Wang, X., Zhang, N., Xu, Y., & He, Y. (2022) · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls55054.2022.9858431 · Cited by 4
“The most widely used methods are the common the SoftMax [11] method and the Support Vector Machine (SVM).”
MethodBearing Fault Diagnosis Based on Improved DBN Combining Attention Mechanism
Zhang, X., Geng, Y., Zhao, J., & Jiang, W. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892543 · Cited by 4
“Lei et al. [7] proposed a two-stage learning method for machine intelligent diagnosis, which directly uses an unsupervised two-layer neural network to learn the characteristics of the signal, and then uses softmax regression to classify the health status.”
MethodManifold learning-assisted sparse filtering method for machinery fault diagnosis
Wang, Q., Peng, D., Jiang, X., Song, Q., & Zhu, Z. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/aceff0 · Cited by 4
“Since that the feature distribution defined by the SF should satisfy the population sparsity, the lifetime sparsity, and the high dispersal [26], Zhang et al [27] further proposed an improved SF named as intrinsic component filtering (ICF) by adding an extra lifetime consistency into the SF, where…”
SM-GMVAE: an intelligent model for defect quantification evaluation based on few ultrasonic signals
Li, Z., Liu, X., Li, R., Song, S., Liu, W., & Song, Y. (2024) · Engineering Research Express · doi:10.1088/2631-8695/ad7669 · Cited by 4
End-to-End Intelligent Fault Diagnosis of Transmission Bearings in Electric Vehicles Based on CNN
Chen, Y., Li, G., Li, A. H., & He, B. (2024) · Lubricants · doi:10.3390/lubricants12110364 · Cited by 4
Wang, Y., & Hu, S. (2025) · PLoS ONE · doi:10.1371/journal.pone.0315917 · Cited by 4
Wang, H., Zhenning, H., Shi-qiang, L., Huanan, Y., & Bian, J. (2025) · Sustainable Energy Grids and Networks · doi:10.1016/j.segan.2025.101698 · Cited by 4
Data-Mining Techniques for Financial Fraud Detection : A Review
Unamma, U. M.-L., Iziduh, E. F., & Okwesa, I. J. (2021) · International Journal of Scientific Research in Science and Technology · doi:10.32628/ijsrst2152555 · Cited by 11
Multi-domain description method for bearing fault recognition in varying speed condition
Zhou, Z., Chen, J., Zi, Y., & Chen, X. F. (2016) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2016.7793687 · Cited by 4
“For now, the methods of fault diagnosis and recognition can be generally categorized into physical modelbased and data driven-based [5], [6].”
MethodZhao, L., Hu, S. Y., & Yao, Y. (2018) · Proceedings of the Institution of Mechanical Engineers Part E Journal of Process Mechanical Engineering · doi:10.1177/0954408918760903 · Cited by 4
Feature-difference sparse filtering for bearing health monitoring
Xiong, W., He, Q., & Ouyang, K. (2018) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc.2018.8409638 · Cited by 4
“[20] used SF to learn impulsive features representation.”
BackgroundMethodKang, J., Liu, Z., Sun, W., Zuo, M. J., & Qin, Y. (2018) · Prognostics and System Health Management Conference · doi:10.1109/phm-chongqing.2018.00014 · Cited by 4
“Moreover, in most reported intelligent bearing fault diagnosis methods, extracting and selecting features manually is a necessary procedure [9, 10], and such a step relies too much on prior diagnostic knowledge, which is time-consuming and labor-intensive [9].”
BackgroundLee, N., Azarian, M. H., PECHT, M. G., Kim, J.-Y., & Im, J.-S. (2019) · IEEE Conference on Prognostics and Health Management · doi:10.1109/icphm.2019.8819436 · Cited by 4
“[6] and Feng et al.”
A study on rotate vector reducer performance degradation based on acoustic emission techniques
An, H., Liang, W. G., Xiaojian, D., Zhang, Y., & Tan, J. (2019) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio49542.2019.8961866 · Cited by 4
“[16], [17] have performed the overload fatigue tests on the bearing and dealt with the vibration signals based on theoretical analysis.”
BackgroundFast convolution sparse filtering and its application on gearbox fault diagnosis
Zhang, Z., Li, S., An, Z., & Xin, Y. (2020) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/0954407020907818 · Cited by 4
“The physical interpretation of SF is given in Lei et al. 20 by fitting each weight vector with the Gabor function.”
BackgroundMethodInfluentialAn accurate and efficient machine fault diagnosis approach using a recurring broad learning model
Guo, L., Li, R., & Jiang, B. (2020) · Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering · doi:10.1177/0959651820936969 · Cited by 4
Wang, R., Liu, F., Hu, X., & Chen, J. (2020) · IEEE Access · doi:10.1109/access.2020.3024647 · Cited by 4
“While in reference [30], all the samples in the training dataset are used as labeled training samples.”
BackgroundMethodRobot Predictive Maintenance Method Based on Program-Position Cycle
Guo, D., Zhang, Y., & Chen, X. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-89095-7_8 · Cited by 4
Semi-Supervised Root-Cause Analysis with Co-Training for Integrated Systems
Pan, R., Li, X., & Chakrabarty, K. (2022) · IEEE VLSI Test Symposium (VTS) · doi:10.1109/vts52500.2021.9794192 · Cited by 4
“Traditional unsupervised methods cluster the failure samples by analyzing their similarity in test results without requiring diagnostic labels, where the samples in each cluster share similar root causes [2], [7].”
BackgroundA safety fault diagnosis method on industrial intelligent control equipment
Zhang, H., Li, Q., Meng, S., Xu, Z., Lv, C., & Zhou, C. (2022) · Wireless Networks · doi:10.1007/s11276-022-02980-4 · Cited by 5
“Inspired by the idea of unsupervised learning that uses artificial intelligence techniques to learn features from raw data, a two-stage learning method is proposed for intelligent safety fault diagnosis of machines by Yaguo Lei et al. [10].”
Data–Driven Wake Steering Control for a Simulated Wind Farm Model
Simani, S., Farsoni, S., & Castaldi, P. (2023) · International Journal of Robotics and Automation Technology · doi:10.31875/2409-9694.2023.10.02 · Cited by 4
“Thus, researches are involved in fault detection [17, 18] of Wind Turbines (WT)s, as for in this paper.”
BackgroundLiu, Y., Liu, Y., & Yang, Y. (2023) · Entropy · doi:10.3390/e25091316 · Cited by 4
“The vibration signal contains the most The vibration signal contains the most essential information on the operating state of the monitored object [33]. monitored object [33].”
BackgroundMulti-Scale Convolutional Neural Network Fault Diagnosis Based on Attention Mechanism
Wang, C., Wang, X., & Sun, Y. (2023) · Chinese Control Conference (CCC) · doi:10.23919/ccc58697.2023.10241216 · Cited by 4
“Therefore, rolling bearing fault diagnosis are an indispensable presence in rotating machinery [1].”
BackgroundEarly Stage Fault Diagnosis Method of Bearings Based on Nonlinear Sparse Blind Deconvolution
Zongzhen, Z., Jinrui, W., Baokun, H., Huaiqian, B., & Shunming, L. (2023) · Journal of Mechanical Engineering · doi:10.3901/jme.2023.16.157 · Cited by 4
Research on fault diagnosis of rigid guide in hoist system based on vibration signal classification
Lu, X., Liu, Z., Shen, Y., Zhang, F., Ma, N., Hao, H., & Liang, Z. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad64f8 · Cited by 4
“Lei et al [25] proposed a learning method for machine intelligent diagnosis, which facilitates the handling of big data in intelligent fault diagnosis and provides technical support for real-time assessment of the health status of the guide.”
Zehelein, T., Werk, P., & Lienkamp, M. (2019) · International Conference on Ecological Vehicles and Renewable Energies (EVER) · doi:10.1109/ever.2019.8813630 · Cited by 4
“[14] use Sparse Filter as a feature extraction process for the classification of bearing data using a softmax layer.”
MethodNguyen, S. D., & Choi, S. (2020) · International Journal of Fuzzy Systems · doi:10.1007/s40815-020-00856-3 · Cited by 4
“For impulse noise, however, reality has shown that seeking an appropriate solution to filter, especially to remove random-valued impulse noise in NMDs, is a challenge [7, 8, 23–28].”
BackgroundInfluentialFault Detection in Analog/Digtal VLSI Circuits based on Artificial Intelligence
Gaber, L., & Hussein, A. I. (2023) · IEEE International Conference on Electronics and Communication Engineering (ICECE) · doi:10.1109/icece59822.2023.10462277 · Cited by 3
“In addition, unsupervised two-layer neural network using the sparse filtering method was proposed in [14] for fault diagnosis.”
MethodAdaptive Convolution Sparse Filtering Method for the Fault Diagnosis of an Engine Timing Gearbox
Fan, S., Cai, Y., Zhang, Z., Wang, J., Shi, Y., & Li, X. (2023) · Sensors · doi:10.3390/s24010169 · Cited by 3
“Lei [14] conducted preliminary research in intelligent fault diagnosis, weak signal detection, and other fields, respectively.”
BackgroundA Novel Bidirectional Sparse Filtering Method for Bearing Fault Diagnosis Under Noise Interference
Zhao, L., Liu, Y., & Wang, J. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3472797 · Cited by 3
“Lei et al. [16] first constructed a two-stage intelligent fault diagnosis framework based on SF and achieved accurate bearing fault identification.”
MethodZhou, Z., Walther, M., & Verl, A. W. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-15311-6 · Cited by 3
Lin, D., & Wan, Q. (2018) · Journal of Electromagnetic Waves and Applications · doi:10.1080/09205071.2018.1553689 · Cited by 3
“In general, typical fault diagnosis procedure contains three steps [13]: signal acquisition, feature extraction, and fault categorization.”
BackgroundKovács, T., & Kő, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-35653-8_3 · Cited by 3
Big data attribute selection method in distributed network fault diagnosis database
Cao, H. Y. (2020) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-179859 · Cited by 3
“This method has become the focus of discussion among relevant experts and scholars, and its research has gradually entered the scope of experts and scholars [28, 30].”
Construction of a deep sparse filtering network for rotating machinery fault diagnosis
Cheng, C., Zou, W., Wang, W., & PECHT, M. G. (2021) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/09544070211014852 · Cited by 3
“Therefore, unsupervised feature learning methods including autoencoders, 12 sparse coding, 13 and sparse filtering (SF) 14 have been widely investigated.”
MethodInfluentialYang, H., & Liu, Q. (2021) · Personal and Ubiquitous Computing · doi:10.1007/s00779-021-01644-y · Cited by 3
RetractedZabaryłło, M., & Barszcz, T. (2022) · Energies · doi:10.3390/en15103651 · Cited by 4
Zaman, U. K. U., Ghoto, M. R., Siadat, A., Baqai, A. A., Aqeel, A. B., & Qamar, U. (2022) · International Conference on Digital Futures and Transformative Technologies (ICoDT2) · doi:10.1109/icodt255437.2022.9787394 · Cited by 4
Online Big Data Physical Education Classroom Based on Monitoring Network and Artificial Intelligence
Zhang, Y., & Wang, Y. (2022) · Security and Communication Networks · doi:10.1155/2022/3643799 · Cited by 4
“e integration of physical education classroom teaching and extracurricular physical activities is both an inevitable trend in the reform of university physical education in the new era and an inevitable choice for the effective achievement of school physical education goals [4], [5].”
BackgroundRetractedFault Classification in Vehicle Power Transmission using Machine Learning
Murugan, S., Raakesh, R., Srikaran, R. S., Surya, K., & Vino (2022) · Journal of Machine and Computing · doi:10.53759/7669/jmc202202014 · Cited by 3
“Various manage techniques consisting of gold standard state-feedback, returned stepping method, fuzzy methods were proposed within side the beyond to manipulate the lively transmission device [11].”
MethodRakesh Kumar, E. R., Liu, X., Rokunojjaman, M., Ali, R. N., & Abdullayev, V. H. (2022) · Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) · doi:10.2174/2352096515666220823093929 · Cited by 3
Li, Y., Lei, M., Cheng, Y., Wang, R., & Xu, M. (2022) · Science Progress · doi:10.1177/00368504221135457 · Cited by 3
“Npredict(Label predict ≠ 1) Nlabel:5 Label:5 ⎧⎪⎪⎨ ⎪⎪⎩ (22)”
Wu, J., Cui, J., Shu, Y., Wang, Y., Chen, R., & Wang, L. (2023) · Eksploatacja i Niezawodnosc - Maintenance and Reliability · doi:10.17531/ein.2023.1.4 · Cited by 3
Ma, J. (2023) · Soft Computing · doi:10.1007/s00500-023-08618-7 · Cited by 3
RetractedRoot-Cause Analysis with Semi-Supervised Co-Training for Integrated Systems
Pan, R., Li, X., & Chakrabarty, K. (2024) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3649313 · Cited by 3
“As such, the failure samples within the same cluster share similar root causes [ 3 , 8 ].”
BackgroundBig Data and its Impact on Demand-Driven Material Requirements Planning
Mukherjee, A. (2024) · International Journal of Supply Chain Management · doi:10.59160/ijscm.v13i2.6233 · Cited by 5
Adaptive spectrum amplitude modulation method for rolling bearing fault frequency determination
Tu, Z., Luo, Z., Li, M., Wang, J., Yang, Z.-X., & Wang, X. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad6786 · Cited by 3
“In recent years, several studies have proposed intelligent fault diagnosis methods that integrate advanced sensor technology, machine learning, and deep learning algorithms [16–18].”
Yi-Die, W., Pei-Pei, C., Rui-Yuan, Z., Tang, H., Yu-Cheng, W., & Hong-Liang, D. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112048 · Cited by 6
Optimization Strategy of Customer Relationship Management based on Big Data Analysis
Zhang, B., Zhang, S., & Zhang, C. (2024) · Informatica · doi:10.31449/inf.v48i14.5175 · Cited by 3
Health condition assessment of ball bearings using TOSELM
Niu, Q., Liu, F., Tong, Q., Cao, J., & Zhang, Y. (2018) · Journal of Vibroengineering · doi:10.21595/jve.2017.18978 · Cited by 3
“Vibration analysis is widely applied in the health condition assessment of ball bearings [1-18].”
BackgroundMethodRolling Bearing Anomaly Detection Based on Generative Adversarial Networks
华, 丰. (2019) · Artificial Intelligence and Robotics Research · doi:10.12677/airr.2019.84023 · Cited by 3
Deep learning inspired prognostics scheme for applications generating big data
Krishnan, R., Jagannathan, S., & Samaranayake, V. A. (2017) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2017.7966269 · Cited by 3
“The pre-processing step proposed here is fundamentally different from standard unsupervised dimension reduction methods [10]–[12].”
MethodInfluentialSparse filtering based intelligent fault diagnosis using IPSO-SVM
Yang, Y., Xiao, P., Cheng, Y., & Zhang, X. (2017) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2017.8028522 · Cited by 3
“Lei proposed a novel unsupervised learning method by which sparse features directly extracted from raw vibration signal, and explained the physical significant of the sparse filtering [8].”
MethodLi, X., Liu, D., Huang, H., & Wang, J. (2019) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-179146 · Cited by 3
RetractedDing, R., Li, S., Lu, J., Xu, K., & Wang, J. (2020) · Applied Sciences · doi:10.3390/app10176084 · Cited by 3
“[13] introduced sparse filtering into mechanical intelligent fault diagnosis.”
BackgroundFault Diagnosis of Gas Turbine Actuator Based on Improved Convolutional Neural Network
Zhou, Z., Sun, J., Gao, W., Kang, J., & Zhang, W. (2021) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac53711.2021.9486570 · Cited by 3
Acoustic Emission Recognition Based on a Three-Streams Neural Network with Attention
Xiaofeng, K., Hu, K., & Ran, L. (2023) · Computer Systems Science and Engineering · doi:10.32604/csse.2023.025908 · Cited by 3
He, W., Mao, J., Liu, L., Li, Z., Miao, Y., & Wang, Y. (2023) · Chinese Control Conference (CCC) · doi:10.23919/ccc58697.2023.10240667 · Cited by 3
Digital Inclusion and Workforce-Readiness Interventions in Emerging Economies : A Review
Unamma, U. M.-L., Ashore-Onisemo, F., Iwuanyanwu, U. A., & Okwesa, I. J. (2018) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit12283141 · Cited by 6
Kortmann, K.-P., Fehsenfeld, M. J., & Wielitzka, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.02784 · Cited by 3
“Alter-natively, supervised end-to-end estimation methods from the field of deep learning explicitly manage without previously extracted features, but require a large amount of already labeled data for training [2].”
BackgroundExplainable artificial intelligence approaches for fault diagnosis in rotating machinery
Brito, L. C. (2022) · doi:10.14393/ufu.te.2022.557 · Cited by 4
Tiwari, G., Saini, S., & Minaxi (2025) · Neural Computing and Applications · doi:10.1007/s00521-024-10847-2 · Cited by 2
“Advanced methods like deep learning offer utilities the potential to optimize fault management by overcoming the limitations of traditional methods, reducing downtime, improving customer satisfaction, and enhancing operational efficiency [15, 16].”
Fault Diagnosis Method for EMU Traction Motor Based on Machine Learning
Kong, H., Cheng, X., Niu, B., & Peng, C. (2024) · Global Reliability and Prognostics and Health Management Conference (PHM) · doi:10.1109/phm-beijing63284.2024.10874454 · Cited by 2
“LEI, JIA and other scholars proposed a two-layer unsupervised learning network and verified the algorithm based on the motor bearing sample database [9].”
IDL-BiGRU: Integrated deep learning assisted smart scheduling of big data over cloud environment
Satish, K. V. R., Vibha, M. B., & Sasidharan, L. (2025) · Data & Knowledge Engineering · doi:10.1016/j.datak.2025.102489 · Cited by 2
Compliant mechanism design using neural networks focusing on its procedure and limitations
Jin, S., Lee, K., & Yoo, J. (2025) · Structural and Multidisciplinary Optimization · doi:10.1007/s00158-025-04064-1 · Cited by 2
“…processing units (GPUs) has significantly impacted the efficiency of computational processes with its powerful prediction performance in engineering (Lei et al. 2016; Kober et al. 2013; Xie et al. 2018; Wang et al. 2019; Huang et al. 2021; Zabin et al. 2022) covering TO (Woldseth et al. 2022).”
Kumar, J. A. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110712 · Cited by 2
Lin, L., Zhao, S., Tang, X., & Zhao, W. (2025) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-025-01280-z · Cited by 2
CLASSIFICATION OF FAULT SIGNALS BASED ON DCT AND DEEP LEARNING
Akabi, H. A., & Al-Assadi, T. A. (2025) · Kufa Journal of Engineering · doi:10.30572/2018/kje/160413 · Cited by 2
Energy-Aware Anomaly Detection in Wind Turbine SCADA Systems
Ciocan, A. V., Hamrioui, S., Lorenz, P., Courboulay, V., & Ciocan, A. (2025) · International Conference on Software, Telecommunications and Computer Networks (SoftCOM) · doi:10.23919/softcom66362.2025.11197377 · Cited by 2
“Conventional methods, such as manual thresholding, statistical process control techniques, and standard deep learning models, struggle to handle the complex temporal dependencies in wind turbine SCADA (Supervisory Control and Data Acquisition) data and often fail to quantify uncertainty [1], [2].”
Wu, L., Song, S., Li, H., Hu, C., & Luo, Y. (2025) · Electronics · doi:10.3390/electronics15010131 · Cited by 2
A deep learning-assisted FEM approach for comprehensive fault detection in linear induction motors
Raja, C. V. N., Vaka, S. S. K. R., Khan, B., Sivanraju, R., Alatawi, K. S. S., & Almasoudi, F. M. (2026) · International Journal of Dynamics and Control · doi:10.1007/s40435-026-02042-z · Cited by 2
Xiao, F., Shang, X., Li, Q., Zhan, Y., Li, R., Ai, Q., & Zhang, Y. (2026) · Energies · doi:10.3390/en19092187 · Cited by 2
Research on Fault Diagnosis of Planetary Gearbox Based on Hierarchical Extreme Learning Machine
Sun, G., & Wang, Y. (2018) · Prognostics and System Health Management Conference · doi:10.1109/phm-chongqing.2018.00122 · Cited by 2
“Lei Y et al.[6] sparse features extracted from the raw vibration signals by an adaptive neural network sparse depth filter theory, and then input to the classifier Softmax bearing fault identification, compared to conventional diagnostic methods have higher diagnostic accuracy.”
MethodXu, M. F., Song, F., Sun, Y., Lang, S., & Ma, W. L. (2021) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/680/1/012007 · Cited by 2
Adversarial multi-domain adaptation for machine fault diagnosis with variable working conditions
Li, Q., Liu, S., Yang, B., Xu, Y., Chen, L., & Shen, C. (2020) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin45582.2020.9442084 · Cited by 2
“And it is proved that intelligent fault diagnosis is a promising tool to deal with mechanical big data[2].”
BackgroundXu, K., Li, S., Li, R., Lu, J., & Zeng, M. (2021) · IEEE Access · doi:10.1109/access.2021.3112605 · Cited by 2
An Interturn Short Circuit Fusion Model of Traction Motors for Fault Diagnosis
He, L., Kang, J., & Li, H. (2021) · IEEE International Power Electronics and Application Symposium (PEAS) · doi:10.1109/peas53589.2021.9628843 · Cited by 2
He, Y., Zhou, B., Guo, S., Yang, Y., Xiang, Y., Hu, Z., & Zhou, D. (2021) · IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia) · doi:10.1109/icpsasia52756.2021.9621612 · Cited by 2
Hu, Y., Jiao, Y., Shang, Y., Li, S., & Hu, Y. (2022) · Entropy · doi:10.3390/e24070997 · Cited by 2
“As a result, a machine learning-based fault diagnosis method that learns the pattern hidden behind multiple data for diagnosing faults is proposed [7,8].”
BackgroundAnomaly Detection System for Stepper Motors
Sharrar, L. (2022) · International Journal of Engineering Research in Electronics and Communication Engineering · doi:10.36647/ijerece/09.06.a005 · Cited by 2
CycleGAN Based Unsupervised Domain Adaptation for Machine Fault Diagnosis
Pattnaik, N., Vemula, U. S., Kumar, K., Kumar, A., Majumdar, A., Chandra, M. G., & Pal, A. (2022) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3560905.3568303 · Cited by 4
Sparse Filtering with Joint Distribution Adaptation for Intelligent Fault Diagnosis
Song, P., Yang, Q., Li, D., & Dang, H. (2023) · Chinese Control Conference (CCC) · doi:10.23919/ccc58697.2023.10241214 · Cited by 2
Jia, X., Xiao, X., & Wen, J. (2023) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-023-12381-2 · Cited by 2
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.