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 401–500 of 1,001
Fault diagnosis of rolling bearing based on online transfer convolutional neural network
Xu, Q., Bo, Z., Huo, H., Meng, Z., Li, J., Fan, F., & Cao, L. (2022) · Applied Acoustics · doi:10.1016/j.apacoust.2022.108703 · Cited by 40
Monday, H. N., Li, J., Nneji, G. U., Nahar, S., Hossin, M. A., Jackson, J. K., & Oluwasanmi, A. (2022) · Complex & Intelligent Systems · doi:10.1007/s40747-022-00733-6 · Cited by 37
“The authors in [26] utilized 2D and CNN for the diagnosis of bearing faults.”
MethodChen, G., Xiang, D., Liu, T., Xu, F., & Li, W. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112180 · Cited by 41
Early and extremely early multi-label fault diagnosis in induction motors
Juez-Gil, M., Saucedo-Dorantes, J. J., González, Á. A., Nozal, C. L., García‐Osorio, C., & Lowe, D. (2020) · ISA Transactions · doi:10.1016/j.isatra.2020.07.002 · Cited by 40
Shang, Z., Li, W., Gao, M., Liu, X., & Yan, Y. (2021) · Chinese Journal of Mechanical Engineering · doi:10.1186/s10033-021-00580-5 · Cited by 38
Babu, M. S., & Rao, T. B. (2022) · Measurement · doi:10.1016/j.measurement.2022.111501 · Cited by 37
Wang, R., Xu, J., Zhang, W., Gao, J., Li, Y., & Chen, F. (2022) · Quality and Reliability Engineering International · doi:10.1002/qre.3175 · Cited by 43
Deep Belief Networks Ensemble for Blood Pressure Estimation
Lee, S., & Chang, J. (2017) · IEEE Access · doi:10.1109/access.2017.2701800 · Cited by 36
“Recently, the DBN technique has attracted increasing attention in both the machine learning [17], [18] and signal processing areas as a remarkable technique.”
MethodLiu, K., Chen, Z., Wu, J., Tan, Y., Wang, L., Yan, Y., Zhang, H., & Long, J. (2018) · IEEE Access · doi:10.1109/access.2018.2886198 · Cited by 36
“To solve these problems, intelligent medical system (expert system) [13]–[15] is gradually employed to improve the healthcare situation in developing countries.”
BackgroundTongguang, Y., Yu, X., Li, G., Dou, J., & Baojia, D. (2019) · Measurement Science and Technology · doi:10.1088/1361-6501/ab5342 · Cited by 36
“X l 1 i is one of the elements. ω lij is the weight matrix corresponding to the convolution kernel. b lj is the bias term. f ( ) is the activation function, for which ReLU function is commonly used [36] and the mathematical expression is 2.4.2.”
BackgroundInfluentialA self-Adaptive CNN with PSO for bearing fault diagnosis
Chen, J., Jiang, J., Guo, X., & Tan, L. (2020) · Systems Science & Control Engineering · doi:10.1080/21642583.2020.1860153 · Cited by 37
“…totally 12 classes of (Jiang et al., 2018) 96.53 12 HCNN (Wen et al., 2019) 99.82 10 CNN-Vibration image (Wen et al., 2018) 99.79 10 Sparse filter (Lei et al., 2016) 99.66 10 CNN-PSO-WP (Fuan et al., 2017) 99.71 8 CNN-Wavelet 96 × 96 (Verstraete et al., 2017) 99.8 4 CNN-STFT96 × 96 (Verstraete…”
MethodInfluentialEgwuonwu, A., Mendy, J., Oruh, E. S., & Egwuonwu, A. (2024) · IEEE Transactions on Engineering Management · doi:10.1109/tem.2023.3321426 · Cited by 46
“…adoption also highlights that when senior managers have optimistic expectations of IT system’s potential benefits, they are more likely to adopt BDA [66] and to propel as a driver for changes in organizational norms, values, and cultures, the adoption of new technologies [52], [54], [68] and the…”
BackgroundYao, Y., Feng, J. Y., & Liu, Y. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3369704 · Cited by 35
Reliability in Robotics and Intelligent Systems: Mathematical Modeling and Algorithmic Innovations
Исаметова, М., Martyushev, N. V., Malozyomov, B. V., Demin, A. Y., Pogrebnoy, A. V., Kuleshova, E. E., & Valuev, D. V. (2026) · Mathematics · doi:10.3390/math14030580 · Cited by 36
Zhang, Z., & Chen, J. (2018) · ISA Transactions · doi:10.1016/j.isatra.2018.10.015 · Cited by 35
Representation Learning With Class Level Autoencoder for Intelligent Fault Diagnosis
Yu, H., Wang, K., Li, Y., & Zhao, W. (2019) · IEEE Signal Processing Letters · doi:10.1109/lsp.2019.2936310 · Cited by 35
“We imitate the data sampling of [1], [2], [27], each collected signal with intercepted first 120,000 points was alternately sliced into 100 samples and each sample contains 1200 data points.”
Yang, Y., Zheng, H., Yin, J., Xu, M., & Chen, Y. (2019) · Measurement · doi:10.1016/j.measurement.2019.107233 · Cited by 35
Jin, Z., Han, Q., Zhang, K., & Zhang, Y. (2020) · Journal of Vibration and Control · doi:10.1177/1077546319889859 · Cited by 35
“Feature extraction: feature extraction is usually used for extracting features from signals by technicians according to specific problems (Lei et al., 2016).”
BackgroundMethodComparative Study of CNN and RNN for Motor fault Diagnosis Using Deep Learning
Choi, D.-J., Han, J.-H., Park, S.-U., & Hong, S.-K. (2020) · IEEE International Conference on Industrial Engineering and Applications (ICIEA) · doi:10.1109/iciea49774.2020.9102072 · Cited by 35
“2, high accuracy can be expected in limited environment if motor failure diagnosis is performed using CNN-based motor algorithm [2].”
MethodIntrinsic component filtering for fault diagnosis of rotating machinery
Zhang, Z., Li, S., Lu, J., Xin, Y., & Ma, H. (2020) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2020.07.019 · Cited by 35
Reliability‐based fault analysis models with industrial applications: A systematic literature review
Ahmed, Q., Raza, S. A., & Al-Anazi, D. M. (2020) · Quality and Reliability Engineering International · doi:10.1002/qre.2797 · Cited by 41
“…Fault characteristic mining and intelligent diagnosis Deep neural networks (DNNs) with deep architectures Industrial systems Rotating machinery Lei et al (2016)186 Fault diagnosis Unsupervised two-layer neural network and soft-max regression Power systems Motor bearing Janssens et al…”
BackgroundRobotic Grinding Process Monitoring by Vibration Signal Based on LSTM Method
Zhao, X., Lu, H., Yu, W., Tao, B., & Ding, H. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3210978 · Cited by 35
“Lei et al. [17] proposed a two-stage learning method, including an unsupervised two-layer neural network that learns features from mechanical big data and a softmax regression method that classifies health status according to the learned features.”
MethodZhang, H., Che, W., Cao, Y., Guan, Z., & Zhu, C. (2024) · Iranian Journal of Science and Technology Transactions of Mechanical Engineering · doi:10.1007/s40997-024-00783-w · Cited by 36
“The machine tool, an essential component of industrial equipment, possesses a generally sophisticated structure, and is mostly supported by bearings (Lei et al. 2016).”
Digital Twins in 3D Printing Processes Using Artificial Intelligence
Rojek, I., Marciniak, T., & Mikołajewski, D. (2024) · Electronics · doi:10.3390/electronics13173550 · Cited by 38
Qian, W., Li, S., Wang, J., & Wu, Q. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.09.027 · Cited by 34
Cross-domain fault diagnosis of rolling bearing using similar features-based transfer approach
Qin, A., Mao, H., & Hu, Q. (2020) · Measurement · doi:10.1016/j.measurement.2020.108900 · Cited by 35
Cross-Category Mechanical Fault Diagnosis Based on Deep Few-Shot Learning
Xu, J., Shi, Y., Yuan, X., & Lu, S. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3123807 · Cited by 34
“The success of deep learning-based methods heavily depends on a large number of training examples and the training and testing data follow identical data distribution and fault category [5]–[8].”
BackgroundJiang, Y., Xia, T., Wang, D., Zhang, K., & Xi, L. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.11.005 · Cited by 35
Tian, J., Jiang, Y., Zhang, J., Wang, Z., Rodriguez-Andina, J. J., & Luo, H. (2022) · Current Chinese Science · doi:10.2174/2210298102666220318100051 · Cited by 34
Yu, H., Wang, K., & Li, Y. (2018) · IEEE Signal Processing Letters · doi:10.1109/lsp.2018.2878356 · Cited by 34
“This intuition for the averaging operation aims to eliminate the shiftvariance of vibration signals [21], [22] whilst discovering and capturing more discriminative feature representations.”
BackgroundA novel multi-segment feature fusion based fault classification approach for rotating machinery
Liang, J., Zhang, Y., Zhong, J.-H., & Yang, H. (2018) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.12.009 · Cited by 33
Sun, G., Wang, Y., Sun, C., & Jin, Q. (2019) · Sensors · doi:10.3390/s19235222 · Cited by 36
“[19] performed sparse filtering on deep neural networks to achieve automatic feature extraction of bearing signals and complete fault identification.”
MethodAn Analytics Environment Architecture for Industrial Cyber-Physical Systems Big Data Solutions
Hinojosa-Palafox, E. A., Rodríguez-Elias, O. M., Hoyo-Montaño, J. A., Pacheco, J., & Nieto-Jalil, J. M. (2021) · Sensors · doi:10.3390/s21134282 · Cited by 33
“This can be illustr ted with the following examples in real scenarios: in [32] an intelligent f ult diag osis approach for a mechanical probl m using Big Data a d unsupervise feature learning for providing an accurate prediction in the case of motor bearings logs is presented.”
MethodAljemely, A. H., Xuan, J., Al-Azzawi, O., & Jawad, F. K. J. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07353-8 · Cited by 35
Deep Transfer Learning Framework for Bearing Fault Detection in Motors
Kumar, P., Kumar, P., Hati, A. S., & Kim, H. S. (2022) · Mathematics · doi:10.3390/math10244683 · Cited by 33
Improving Accuracy and Interpretability of CNN-Based Fault Diagnosis through an Attention Mechanism
Huang, Y., Zhang, J., Liu, R., & Zhao, S. (2023) · Processes · doi:10.3390/pr11113233 · Cited by 35
Yang, B., Lei, Y., Jia, F., & Xing, S. (2018) · International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC) · doi:10.1109/sdpc.2018.8664814 · Cited by 34
Self-citationEnsemble sparse supervised model for bearing fault diagnosis in smart manufacturing
Zhang, F., Yan, J., Fu, P., Wang, J., & Gao, R. X. (2020) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2019.101920 · Cited by 33
Han, T., Jiang, D., Zhang, X., & Sun, Y. (2017) · Sensors · doi:10.3390/s17040689 · Cited by 36
“From this point of view, this diagnosis strategy is also referred as intelligent diagnosis [12].”
BackgroundFrequency Occurrence Plot-Based Convolutional Neural Network for Motor Fault Diagnosis
Piedad, E., Chen, Y., Chang, H., & Kuo, C. (2020) · Electronics · doi:10.3390/electronics9101711 · Cited by 34
Unsupervised Joint Subdomain Adaptation Network for Fault Diagnosis
Wang, B., Wei, Y., Liu, S., Zhao, D., & Liu, X. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3163425 · Cited by 32
Liu, C., Ma, X., Han, T., Shi, X., Qin, C., & Hu, S. (2022) · Measurement · doi:10.1016/j.measurement.2022.112041 · Cited by 33
Deng, F., Chen, Z., Liu, Y., Yang, S., Hao, R., & Lyu, L. (2022) · Machines · doi:10.3390/machines10121226 · Cited by 32
Liu, Y., Wen, J., Liu, X., Yang, S., & Wang, G. (2025) · Machine Learning with Applications · doi:10.1016/j.mlwa.2025.100704 · Cited by 55
Apata, O., Munda, J. L., & Migabo, E. (2026) · Energies · doi:10.3390/en19020536 · Cited by 37
Xu, K., Li, S., Wang, J., An, Z., Qian, W., & Ma, H. (2019) · Measurement Science and Technology · doi:10.1088/1361-6501/ab230b · Cited by 33
“With the advent of the industrial big-data era [1], intelligent fault diagnosis based on data-driven technology has developed rapidly [2].”
BackgroundWang, B., Shen, C., Xu, K., & Zheng, T. (2019) · IET Electric Power Applications · doi:10.1049/iet-epa.2019.0101 · Cited by 31
Gao, W., Wai, R., & Chen, S.-Q. (2020) · IEEE Access · doi:10.1109/access.2020.3010233 · Cited by 31
“Three evaluation indicators [31] including precision, recall and F1-score are selected for examination, which are defined as follows:”
MethodAn adversarial model for electromechanical actuator fault diagnosis under nonideal data conditions
Wang, C., Tao, L., Ding, Y., Lü, C., & Ma, J. (2022) · Neural Computing and Applications · doi:10.1007/s00521-021-06732-x · Cited by 31
“The deep neural network (DNN)-based fault diagnosis model was proposed by Lei et al. [27].”
MethodLiu, Z., Chen, L., Wei, H., Wu, F.-M., Chen, L., & Chen, Y. (2022) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2022.108968 · Cited by 31
A Jointed Signal Analysis and Convolutional Neural Network Method for Fault Diagnosis
Wen, L., Gao, L., Li, X., Wang, L., & Zhu, J. (2018) · Procedia CIRP · doi:10.1016/j.procir.2018.03.117 · Cited by 32
Feng, H., Chen, R., & Wang, Y. (2018) · Advances in Mechanical Engineering · doi:10.1177/1687814018796367 · Cited by 32
“Lei et al.(14) proposed a two-stage intelligent fault diagnosis method using unsupervised feature learning.”
MethodZhang, C., Feng, J., Hu, C., Liu, Z., Cheng, L., & Zhou, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2981289 · Cited by 31
“2) For expanding the receptive fields, lots of parameters are introduced in the convolutional kernels of the above three methods [2], [27], [28].”
BackgroundMethodInfluentialA Parameter-Optimized DBN Using GOA and Its Application in Fault Diagnosis of Gearbox
Gai, J., Shen, J., Wang, H., & Hu, Y. (2020) · Shock and Vibration · doi:10.1155/2020/4294095 · Cited by 30
“1, 10].”
MethodA Decision-Making Tool Based on Exploratory Visualization for the Automotive Industry
Redondo, R., Herrero, Á., Corchado, E., & Sedano, J. (2020) · Applied Sciences · doi:10.3390/app10124355 · Cited by 30
Guo, C., Li, L., Hu, Y., & Yan, J. (2020) · IEEE Access · doi:10.1109/access.2020.3009644 · Cited by 30
“features can be adaptively learned from mechanical raw data with a general-purpose learning procedure instead of being extracted by diagnosticians, which is more intelligent than traditional diagnosis methods [1].”
BackgroundInfluentialIntelligent Condition-Based Monitoring Techniques for Bearing Fault Diagnosis
Singh, V., & Verma, N. K. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3021918 · Cited by 32
Pipeline small leak detection based on virtual sample generation and unified feature extraction
Zang, D., Liu, J., & Qu, F. (2021) · Measurement · doi:10.1016/j.measurement.2021.109960 · Cited by 30
An, Z., Jiang, X., Yang, R., Zhang, H., Liu, J., & Shen, C. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3218737 · Cited by 30
“Numerous DL-based intelligent fault diagnosis (IFD) methods, such as artificial neural networks [4], convolutional neural networks (CNN) [5], recurrent neural networks [6], k-nearest neighbor [7], restricted Boltzmann machine [8], autoencoders [9], discriminant analysis [10], and sparse filtering [11] and their varian…”
MethodReview of Machine Learning Techniques for Power Electronics Control and Optimization
Bahrami, M., & Khashroum, Z. (2023) · COMPUTATIONAL RESEARCH PROGRESS IN APPLIED SCIENCE & ENGINEERING · doi:10.61186/crpase.9.3.2860 · Cited by 32
Tool Condition Prognostic Model Based on Digital Twin System
Xie, N., Rui, K., & Yao, Y. (2020) · Procedia CIRP · doi:10.1016/j.procir.2020.03.045 · Cited by 29
Industrial process fault detection based on deep highly-sensitive feature capture
Liu, B., Chai, Y., Liu, Y., Huang, C., Wang, Y., & Tang, Q. (2021) · Journal of Process Control · doi:10.1016/j.jprocont.2021.04.003 · Cited by 29
A Two-Stage Semi-Supervised Learning Framework for Fault Diagnosis of Rotating Machinery
Nie, X., & Xie, G. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3091489 · Cited by 31
Bai, H., Zhan, X., Yan, H., Wen, L., & Jia, X. (2022) · Electronics · doi:10.3390/electronics11131969 · Cited by 29
Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering
Attaoui, M. O., Fahmy, H. M., Pastore, F., & Briand, L. (2022) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3550271 · Cited by 34
“Several unsupervised root cause analysis approaches have been proposed in the literature, for instance, Sparse Filtering [38], and Frequent Pattern Mining [51].”
MethodA data-driven Model for Fault Diagnosis of Induction Motor for Electric Powertrain
Hadraoui, H. E., Laayati, O., Guennouni, N., Chebak, A., & Zegrari, M. (2022) · IEEE Mediterranean Electrotechnical Conference (MELECON) · doi:10.1109/melecon53508.2022.9843046 · Cited by 30
Xu, Y., Cai, Z., Cai, X., & Ding, K. (2019) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-019-0505-9 · Cited by 29
“Many of the popular bearing fault extraction methods have been presented, including wavelet-based methods [1-3], spectral kurtosis and entropy [4-6], mode decomposition-based methods [7-10], independent cmponent analysis methods (ICA) [11, 12] and intelligent and optimization algorithms [13-18].”
MethodHuang, R., Li, W., & Cui, L. (2019) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc.2019.8827030 · Cited by 32
“combined the stacked auto-encoder and SC to identify the health conditions for bearing fault [3].”
MethodLi, S., An, Z., & Lu, J. (2020) · IEEE Access · doi:10.1109/access.2020.2996713 · Cited by 31
“Machine learning which is regarded as a data-driven model, depends less human knowledge and is quite suitable to deal with mechanical big data, has drawn wide attention in fault diagnosis field, such as Artificial Neural Networks (ANN) [14], [15], Autoencoders (AE) [16], [17], Restricted Boltzmann Machine (RBM) [18], Co…”
BackgroundQian, W., Li, S., Wang, J., Xin, Y., & Ma, H. (2018) · 2018 Prognostics and System Health Management Conference (PHM-Chongqing) · doi:10.1109/phm-chongqing.2018.00180 · Cited by 28
“In method 1, the prediction result of sparse filtering (SF) [16] is presented for comparison.”
MethodA novel compound fault diagnosis method using intrinsic component filtering
Zhang, Z., Li, S., Xin, Y., & Ma, H. (2019) · Measurement Science and Technology · doi:10.1088/1361-6501/ab62c5 · Cited by 28
“Sparse filtering, which was first proposed by Ngiam [28], is a simple and effective method and has been widely used in the area of intelligent fault diagnosis [29, 30].”
MethodZhang, H., Wang, Y., Liu, J., Li, C., Ma, T., Liu, X., & Yin, C. (2021) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2020-01-5113 · Cited by 28
An End-To-End CNN-BiLSTM Attention Model for Gearbox Fault Diagnosis
Zheng, X., Wu, J., & Ye, Z. (2020) · IEEE International Conference on Progress in Informatics and Computing · doi:10.1109/pic50277.2020.9350844 · Cited by 28
Zhang, Z., Wang, J., Li, S., Bao, H., & Han, B. (2022) · Measurement · doi:10.1016/j.measurement.2022.112347 · Cited by 29
An Analysis Method for Interpretability of Convolutional Neural Network in Bearing Fault Diagnosis
Guo, L., Gu, X., Yu, Y., Duan, A., & Gao, H. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3334350 · Cited by 30
“Lei et al. [30] analyzed the output of the first layer of the CNN-based model, and compared it with the input feature signal to analyze the filtering processing of the convolutional kernel.”
MethodIndividual intelligent method-based fault diagnosis
Lei, Y. (2017) · Elsevier eBooks · doi:10.1016/b978-0-12-811534-3.00003-2 · Cited by 28
Self-citationModeling Machine Health Using Gated Recurrent Units with Entity Embeddings and K-Means Clustering
Amihai, I., Chioua, M., Gitzel, R., Kotriwala, A. M., Pareschi, D., Sosale, G., & Subbiah, S. (2018) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin.2018.8472065 · Cited by 30
Big Data Opportunities: System Health Monitoring and Management
Tsui, K., Zhao, Y., & Wang, D. (2019) · IEEE Access · doi:10.1109/access.2019.2917891 · Cited by 30
“SHMM is entering the big data era [94].”
BackgroundAn, Z., Li, S., Xin, Y., Xu, K., & Ma, H. (2019) · Measurement Science and Technology · doi:10.1088/1361-6501/ab26a2 · Cited by 28
Hu, Q., Zhang, Q., Si, X., Sun, G., & Qin, A. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2995817 · Cited by 28
“In general, extracting informative features and selecting optimal features are two key steps in the field of intelligent fault diagnosis [2].”
BackgroundA research on fatigue crack growth monitoring based on multi-sensor and data fusion
Chang, Q., Weixi, Y., Liu, J., Gao, H., & Yao, M. (2019) · Structural Health Monitoring · doi:10.1177/1475921719865727 · Cited by 27
“Fault diagnosis is essentially a pattern recognition problem.(18) The pattern recognition method for the crack growth diagnosis commonly can be divided into two categories, namely data-driven and model-based.”
MethodIIoT Framework Based ML Model to Improve Automobile Industry Product
Gopalakrishnan, S., & Kumaran, M. S. (2021) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2022.020660 · Cited by 27
A Taxonomy and Archetypes of Business Analytics in Smart Manufacturing
Wanner, J., Wissuchek, C., Welsch, G., & Janiesch, C. (2023) · ACM SIGMIS Database the DATABASE for Advances in Information Systems · doi:10.1145/3583581.3583584 · Cited by 30
Abio, A., Bonada, F., Pujante, J., Grané, M., Nievas, N., Lange, D., & Pujol, O. (2022) · Materials · doi:10.3390/ma15103647 · Cited by 29
“Unsupervised learning has achieved great results in anomaly detection [15], fault and quality prediction [16], and predictive maintenance [17], among others.”
Backgroundİnan, R., Aksoy, B., & SALMAN, O. K. M. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107083 · Cited by 31
Yousefi, S., Yin, S., & Alfarizi, M. G. (2023) · IEEE Open Journal of the Industrial Electronics Society · doi:10.1109/ojies.2023.3334429 · Cited by 27
“The feature extraction phase uses signal processing techniques, including time-domain and Fourier spectral analysis to extract representative features from the recorded signals [20].”
MethodLiu, S., Li, J., Zhou, N., Chen, G., Lu, K., & Wu, Y.-T. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125398 · Cited by 34
Zhao, X., & Jia, M. (2018) · Measurement Science and Technology · doi:10.1088/1361-6501/aae27a · Cited by 27
Fault diagnosis method of rolling bearing based on deep belief network
Shang, Z., Liao, X., Geng, R. Z., Gao, M., & Liu, X. (2018) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-018-1012-0 · Cited by 27
“( 1| ) ( ) j j i ij i p h v b v w (6)”
Kim, J., Lee, D., Yang, J., & Lee, S. (2019) · Nuclear Engineering and Technology · doi:10.1016/j.net.2019.09.016 · Cited by 27
Xin, Y., Li, S., Wang, J., An, Z., & We, Z. (2020) · IET Science Measurement & Technology · doi:10.1049/iet-smt.2018.5672 · Cited by 29
Yang, C., & Jia, M. (2020) · Structural Health Monitoring · doi:10.1177/1475921720923973 · Cited by 29
Wang, J., Ji, S., Han, B., Bao, H., & Jiang, X. (2020) · Complexity · doi:10.1155/2020/6946702 · Cited by 29
“The structure of the condition recognition module is [1200, 600, 200, 100, 5], and the domain adversarial module is [1200, 600, 200, 100, 1], in which the unit number of the input layer is determined by the dimension of the samples, the unit number of the output layer for the condition recognition…”
BackgroundMethodLiu, Z., Kang, J., Zhao, X., Zuo, M. J., Qin, Y., & Jia, L. (2019) · Applied Mathematical Modelling · doi:10.1016/j.apm.2019.03.040 · Cited by 26
Liao, J., Shen, Z., Xiong, G., Liu, C., Luo, C., & Lu, J. Y. (2019) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2019.8834376 · Cited by 26
He, J., Ouyang, M., Chen, Y., Chen, D., Guo, J., & Zhou, Y. (2020) · Sensors · doi:10.3390/s20061774 · Cited by 26
“[47] proposed a bearing diagnosis method to integrate 12 sparse filter networks.”
MethodCascade of One Class Classifiers for Water Level Anomaly Detection
Tan, F. H. S., Park, J. R., Jung, K., Lee, J. S., & Kang, D.-K. (2020) · Electronics · doi:10.3390/electronics9061012 · Cited by 26
“However, manual examinations by human are generally labor-intensive and time-consuming, thus smart effective diagnosis on these anomalies is extremely imperative [6].”
BackgroundFault Diagnosis of Planetary Gearbox Based on Motor Current Signal Analysis
Jiang, Z., Han, Q., & Xu, X. (2020) · Shock and Vibration · doi:10.1155/2020/8854776 · Cited by 26
“Lei et al. [30] proposed a two-stage bearing fault diagnosis method.”
MethodAljemely, A. H., Xuan, J., Jawad, F. K. J., Al-Azzawi, O., & Subhi, A. A. (2020) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-020-1002-x · Cited by 27
“However, most traditional intelligent diagnosis methods still working on shallow architectures lack powerful representation in fault diagnosis tasks and have two intrinsic limitations [14]: feature extraction and selection.”
BackgroundBearing Health Condition Prediction Using Deep Belief Network
Zhao, G., Liu, X., Zhang, B., Zhang, G., Niu, G., & Hu, C. (2017) · Annual Conference of the PHM Society · doi:10.36001/phmconf.2017.v9i1.2484 · Cited by 26
“Model-based methods attempt to setup mathematical or physical models to describe degradation processes of machinery, and update model parameters using measured data (Lei et al., 2016), such as the Markov process model (Dui et al.”
BackgroundMethodResultInfluential
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.