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 301–400 of 1,001
Zhang, Z., Li, S., Wang, J., Xin, Y., An, Z., & Jiang, X. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.042 · Cited by 60
Data augment method for machine fault diagnosis using conditional generative adversarial networks
Wang, J., Han, B., Bao, H., Wang, M., Chu, Z., & Shen, Y. (2020) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/0954407020923258 · Cited by 58
“4 Lei et al. 5 employed sparse filtering to directly extract features from time-domain signals and achieved bearing intelligent fault diagnosis.”
BackgroundWang, Q., Wang, S., Wei, B., Chen, W., & Zhang, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3066489 · Cited by 56
“[10] proposed a bearing fault classification method, which extracted 11 time-frequency domain features, selected features according to local and non-local preserved projections, and used the k-nearest neighbor (KNN) algorithm to classify bearing health.”
BackgroundMethodLeoni, L., BahooToroody, A., Abaei, M. M., Cantini, A., BahooToroody, F., & Carlo, F. D. (2023) · Safety Science · doi:10.1016/j.ssci.2023.106363 · Cited by 59
“…to be a fundamental factor to achieve human or super-human AI systems (Jia et al., 2016) (1061), Wen et al., (Wen et al., 2017) (903), Lei et al., (Lei et al., 2016)(715), Ince et al., (Ince et al., 2016) (684), Janssens et al., (Janssens, 2016) (636), Zhang et al., (Zhang et al., 2018) (624),…”
BackgroundData-Driven Approaches for Characterization of Delamination Damage in Composite Materials
Liu, H., Liu, S., Liu, Z., Mrad, N., & Milani, A. S. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.2973877 · Cited by 58
“been widely used in damage detection [11], soil corrosivity analysis [12], pipe deterioration estimation [13], etc.”
MethodParallel sparse filtering for intelligent fault diagnosis using acoustic signal processing
Ji, S., Han, B., Zhang, Z., Wang, J., Lu, B., Yang, J., & Jiang, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.049 · Cited by 56
Large scale foundation models for intelligent manufacturing applications: a survey
Zhang, H., Semujju, S. D., Wang, Z., Lv, X., Xu, K., Wu, L., Jia, Y., Wu, J., Liang, W., Zhuang, R., et al. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02536-7 · Cited by 83
Big Data-Based Improved Data Acquisition and Storage System for Designing Industrial Data Platform
Geng, D., Zhang, C., Xia, C., Xia, X., Liu, Q., & Fu, X. (2019) · IEEE Access · doi:10.1109/access.2019.2909060 · Cited by 60
“The data platform needs to support multiple types of data analysis and data visualization services, such as Finite Element Analysis [13], Optimization, Deep Learning [14]–[19], Knowledge Mapping [20], Digital Twins [21].”
MethodTransferable common feature space mining for fault diagnosis with imbalanced data
Lü, N., & Yin, T. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.107645 · Cited by 57
Mueller, P. N., Woelfl, L., & Can, S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106834 · Cited by 58
Hadraoui, H. E., Ouahabi, N., Bazi, N. E., Laayati, O., Zegrari, M., & Chebak, A. (2024) · IEEE Access · doi:10.1109/access.2024.3441517 · Cited by 67
“Knowledge of the system and the fault being diagnosed is necessary to identify the relevant features [72].”
BackgroundLocally Linear Embedding on Grassmann Manifold for Performance Degradation Assessment of Bearings
Ma, M., Chen, X., Zhang, X., Ding, B., & Wang, S. (2017) · IEEE Transactions on Reliability · doi:10.1109/tr.2017.2691730 · Cited by 56
Li, Y., Gu, J. X., Zhen, D., Xu, M., & Ball, A. D. (2019) · Sensors · doi:10.3390/s19092205 · Cited by 55
“By estimating the probability of one sample belonging to each category label, SR guarantees better classification performance [38].”
BackgroundMethodA survey of feature modeling methods: Historical evolution and new development
Li, L., Zheng, Y., Yang, M., Leng, J., Cheng, Z., Xie, Y., Jiang, P., & Ma, Y. (2019) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2019.101851 · Cited by 60
Wang, S., Wang, Q., Xiao, Y., Liu, W., & Shang, M. (2022) · Engineering Failure Analysis · doi:10.1016/j.engfailanal.2022.106424 · Cited by 53
Multi-size wide kernel convolutional neural network for bearing fault diagnosis
Kumar, P., Raouf, I., Song, J., Prince, & Kim, H. S. (2024) · Advances in Engineering Software · doi:10.1016/j.advengsoft.2024.103799 · Cited by 61
Gear Fault Intelligent Diagnosis Based on Frequency-Domain Feature Extraction
Wang, J., Li, S., Xin, Y., & An, Z. (2019) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-019-00089-1 · Cited by 53
“[17] deployed it in their system for intelligent fault diagnosis from time-domain data collected from rotating machinery and achieved a perfect performance with * Jinrui Wang wangjr33@163.”
MethodKulakli, A., & Osmanaj, V. (2020) · International Journal of Online and Biomedical Engineering (iJOE) · doi:10.3991/ijoe.v16i02.12617 · Cited by 59
Cheng, H., Yu, H., Zeng, P., Osipov, E., Li, S., & Vyatkin, V. V. (2020) · Sensors · doi:10.3390/s20195659 · Cited by 56
“In addition, this process largely depends on diagnostic expertise and prior knowledge, and it is time-consuming and labor-intensive [20].”
BackgroundCloud-Manufacturing-Based Condition Monitoring Platform With 5G and Standard Information Model
Yang, H., Sun, Z., Jiang, G., Zhao, F., Lu, X., & Mei, X. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3036870 · Cited by 57
“Currently, considerable attention has been paid to the diagnosis [14], [15] and prognosis [16], [17] methods, while the cloud-based CM remains a challenge considering edge-fog computing, data modeling, and cloud monitoring platform (CMP) construction.”
BackgroundMulti-feature fusion for fault diagnosis of rotating machinery based on convolutional neural network
Liu, S., Ji, Z., Wang, Y., Zhang, Z., Xu, Z., Kan, C., & Jin, K. (2021) · Computer Communications · doi:10.1016/j.comcom.2021.04.016 · Cited by 53
A novel bearing fault diagnosis method using deep residual learning network
Ayas, S., & Ayas, M. Ş. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11617-1 · Cited by 56
“The dataset provided by Case Western Reserve University (CWRU) [27] is publicly available and preferred in the studies focusing on bearing fault diagnosis [13, 15, 25, 34–36].”
BackgroundMethodInfluentialIntelligent fault diagnosis of rolling bearing based on novel CNN model considering data imbalance
Xing, Z., Zhao, R., Wu, Y., & He, T. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03196-x · Cited by 53
Wang, H., Wang, S., Sun, W., & Xiang, J. (2024) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2024.07.002 · Cited by 52
Deep semi-supervised generative adversarial fault diagnostics of rolling element bearings
Verstraete, D., Droguett, E. L., Meruane, V., Modarres, M., & Ferrada, A. (2019) · Structural Health Monitoring · doi:10.1177/1475921719850576 · Cited by 52
Mao, X., Zhang, F., Wang, G., Chu, Y., & Yuan, K. (2020) · Measurement · doi:10.1016/j.measurement.2020.108603 · Cited by 56
A Review of Modeling and Diagnostic Techniques for Eccentricity Fault in Electric Machines
Liu, Z., Zhang, P., He, S., & Huang, J. E. (2021) · Energies · doi:10.3390/en14144296 · Cited by 57
A hybrid deep-learning model for fault diagnosis of rolling bearings in strong noise environments
Zhang, K., Fan, C., Zhang, X., Shi, H., & Li, S. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac4a18 · Cited by 53
“For example, Lei et al [20] proposed a two-stage learning method; in the first stage, a sparse filtering neural network is used to extract fault features.”
A novel ResNet-based model structure and its applications in machine health monitoring
Duan, J., Shi, T., Zhou, H., Xuan, J., & Wang, S. (2020) · Journal of Vibration and Control · doi:10.1177/1077546320936506 · Cited by 52
“However, there still exist some unavoidable shortcomings in these studies (Lei et al., 2016; Qiao et al., 2018; Zhao et al., 2019).”
BackgroundMethodCondition Monitor System for Rotation Machine by CNN with Recurrence Plot
Hsueh, Y.-M., Ittangihala, V. R., Wu, W., Chang, H., & Kuo, C. (2019) · Energies · doi:10.3390/en12173221 · Cited by 53
“The proposed framework was compared to support vector machine SVM [45], artificial neural network (ANN) [22], adaptive deep convolutional neural network (ADCNN) [46], sparse filter [24], and deep belief network (DBN) [22].”
BackgroundMethodJalayer, M., Kaboli, A., Orsenigo, C., & Vercellis, C. (2022) · Machines · doi:10.3390/machines10040237 · Cited by 49
“[17] developed a stacked-AE to directly learn features of mechanical vibration signals on a motor bearing dataset and a locomotive bearing dataset; specifically, they first used a two-layer AE for sparse filtering and then applied a softmax regression to classify the motor condition.”
MethodZhang, J., Zhang, Q., Qin, X., & Sun, Y. (2023) · Structural Health Monitoring · doi:10.1177/14759217231168877 · Cited by 50
“12 On the other hand, it is difficult for machine learning models to express complex mapping.”
BackgroundRaj, K. K., Kumar, S., & Kumar, R. (2024) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-024-09866-x · Cited by 64
Kong, Y., Wang, T., Chu, F., Feng, Z., & Selesnick, I. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3049953 · Cited by 49
“First, the performances of traditional data-driven FDD methods heavily depend on the feature design and selection using the expert knowledge, which are time-consuming and labor-intensive [14].”
BackgroundFault Diagnosis of Rotating Machinery Based on Wasserstein Distance and Feature Selection
Ferracuti, F., Freddi, A., Monteriù, A., & Romeo, L. (2021) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2021.3069109 · Cited by 50
Hou, B., Wang, D., Yan, T., Wang, Y., Peng, Z., & Tsui, K. (2021) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2021.3100532 · Cited by 49
Image-based tool condition monitoring based on convolution neural network in turning process
Rui, K., Lian, S., Xie, N., Lu, B., & Liu, X. (2022) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-021-08282-x · Cited by 49
“The commonly used indirect measurements of TCM are divided into three stages: (1) signal acquisition, (2) feature extraction and selection, and (3) classification [6].”
MethodFault Diagnosis Using Adaptive Multifractal Detrended Fluctuation Analysis
Du, W., Kang, M., & PECHT, M. G. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2892667 · Cited by 48
“[10] used sparse filtering, an unsupervised two-layer neural network, to learn features from mechanical vibration signals and employed softmax regression to identify various health conditions of bearings on the learned features.”
MethodA review of machine learning for big data analytics: bibliometric approach
El-Alfy, E.-S. M., & Mohammed, S. A. (2020) · Technology Analysis and Strategic Management · doi:10.1080/09537325.2020.1732912 · Cited by 53
Shi, P., Guo, X., Han, D., & Fu, R. (2020) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-020-0306-1 · Cited by 48
Wang, Y., & Cheng, L. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/abaa1e · Cited by 50
“Early fault diagnosis and fault prediction of bearings and timely maintenance become an effective means to ensure the safety and reliability of rotating machinery [1–3].”
BackgroundGao, Y., & Yu, D. (2021) · Advanced Engineering Informatics · doi:10.1016/j.aei.2021.101253 · Cited by 48
Pang, S., Yang, X., Zhang, X., & Sun, Y. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.107821 · Cited by 48
Alomari, Y., Andó, M., & Baptista, M. L. (2023) · Scientific Reports · doi:10.1038/s41598-023-40315-1 · Cited by 48
“Lei et al. 38 used a GA to select features for predicting the RUL of rolling bearings.”
MethodAbtane, M., Dahi, K., Martinez, H., Mohamed, S., Kimi, H. E., Dahhassi, C., Hlib, C., & Borges, L. F. (2025) · Measurement · doi:10.1016/j.measurement.2025.117098 · Cited by 50
Weak fault detection and health degradation monitoring using customized standard multiwavelets
Yuan, J. P., Wang, Y., Peng, Y., & Wei, C. (2017) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2017.03.005 · Cited by 47
Ragab, A., El-Koujok, M., Ghezzaz, H., Amazouz, M., Ouali, M.-S., & Yacout, S. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.01.011 · Cited by 47
You, W., Shen, C., Wang, D., Chen, L., Jiang, X., & Zhu, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2962734 · Cited by 52
“Deep learning aims to learn the general underlying representation of input data [26], thereby automatically learning essential features from raw data [27].”
BackgroundXue, H., Wu, M. Y., Zhang, Z., & Wang, H. (2021) · ISA Transactions · doi:10.1016/j.isatra.2021.03.015 · Cited by 47
Abboush, M., Bamal, D., Knieke, C., & Rausch, A. (2022) · Sensors · doi:10.3390/s22114066 · Cited by 55
“, clustering, classification, regression and anomaly detection, ML techniques are classified into unsupervised learning methods [42], semi-supervised learning methods [43], supervised learning methods [44] and reinforcement learning methods [45].”
MethodFu, L., Sun, J., Wang, S., Xu, M., Yao, K., Cao, Y., & Tang, N. (2022) · Journal of Food Process Engineering · doi:10.1111/jfpe.14120 · Cited by 50
Gao, D.-W., Zhu, Y., Yan, K., Fu, H. C., Ren, Z., Kang, W., & Soares, C. G. (2023) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2022.110089 · Cited by 48
Lu, F., Tong, Q., Xu, J., Feng, Z., Wang, X., Huo, J., & Wan, Q. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102536 · Cited by 46
Bearing Fault Diagnosis Based on Shallow Multi-Scale Convolutional Neural Network with Attention
Huang, T., Fu, S., Feng, H., & Kuang, J. (2019) · Energies · doi:10.3390/en12203937 · Cited by 46
“The MSCNN is different from the multi-scale information in Reference [14], which was obtained from the signal before the input of the CNN; here, the multi-scale feature was obtained from the training process, combining it with the multi-attention mechanism.”
MethodInfluentialRolling bearing fault diagnosis based on intelligent optimized self-adaptive deep belief network
Gao, S., Xu, L., Zhang, Y., & Pei, Z. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/ab50f0 · Cited by 46
“Furthermore, the same features may not necessarily be suitable for new problems [15].”
BackgroundMachinery Fault Diagnosis Scheme Using Redefined Dimensionless Indicators and mRMR Feature Selection
Hu, Q., Si, X., Qin, A., Lv, Y., & Zhang, Q.-H. (2020) · IEEE Access · doi:10.1109/access.2020.2976832 · Cited by 47
Xie, Q., Tao, G., Xie, C., & Wen, Z. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3231279 · Cited by 50
“the study of machinery health monitoring (MHM) has entered the era of big data [1].”
BackgroundChang, H., Borghesani, P., & Peng, Z. (2020) · Tribology International · doi:10.1016/j.triboint.2020.106280 · Cited by 46
A Novel Probability Confidence CNN Model and Its Application in Mechanical Fault Diagnosis
Ma, B., Cai, W., Han, Y. M., & Yu, G. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3077965 · Cited by 50
“It is thought that p ( y = k | x ) can use as the probability that x belongs to the class k , k = 1 , 2 , . . . , N [19].”
BackgroundDecoupled Feature-Temporal CNN: Explaining Deep Learning-Based Machine Health Monitoring
Zhu, C., Chen, Z., Zhao, R., Wang, J., & Yan, R. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3084310 · Cited by 52
“In addition, we compared our method with benchmark methods on the two datasets, including local feature-based gated recurrent unit (LFGRU) [31], sparse fil-tering [35], and two conventional machine learning methods of the support vector machine (SVM) and k-nearest neighbors (KNN).”
MethodImproved Variational Mode Decomposition and CNN for Intelligent Rotating Machinery Fault Diagnosis
Xiao, Q., Li, S., Zhou, L., & Shi, W. (2022) · Entropy · doi:10.3390/e24070908 · Cited by 45
“However, the above methods have certain limitations for fault data in the context of big data [27].”
BackgroundTowards understanding sparse filtering: A theoretical perspective
Zennaro, F. M., & Chen, K. (2017) · Neural Networks · doi:10.1016/j.neunet.2017.11.010 · Cited by 46
“Sparse filtering may then be of interest not only for practical machine learning applications, but also for modeling and understanding biological systems.”
BackgroundHuang, J., Zhang, Z., Qin, R., Yu, Y., Wen, G., Cheng, W., & Chen, X. (2023) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2023.11.004 · Cited by 46
Zhang, J., Kong, Y., Chen, Z., Han, T., Han, Q., Dong, M., & Chu, F. (2024) · Measurement · doi:10.1016/j.measurement.2024.114795 · Cited by 46
A Novel Real-Time Fault Diagnosis Method for Planetary Gearbox Using Transferable Hidden Layer
Miao, X., Li, S., Zhu, Y., & An, Z. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2965988 · Cited by 44
“Deep learning technology has been widely studied and applied in the field of fault diagnosis, including deep belief nets (DBN) [6], [7], autoencoder (AE) [8]–[11], convolutional neural networks (CNN) [12]–[14], sparse filtering (SF) [15], etc.”
BackgroundA novel class imbalance-robust network for bearing fault diagnosis utilizing raw vibration signals
Qian, W., & Li, S. (2020) · Measurement · doi:10.1016/j.measurement.2020.107567 · Cited by 46
Zhang, Z., Li, S., Lu, J., Wang, J., & Jiang, X. (2020) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2020.106923 · Cited by 45
CNN-Based Fault Detection for Smart Manufacturing
Neupane, D., Kim, Y., Seok, J., & Hong, J. (2021) · Applied Sciences · doi:10.3390/app112411732 · Cited by 49
Imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning
Liu, J., Zhou, K., Yang, C., & Lu, G. (2021) · Frontiers of Mechanical Engineering · doi:10.1007/s11465-021-0652-4 · Cited by 44
Deep convolution feature learning for health indicator construction of bearings
Guo, L., Lei, Y., Li, N., & Xing, S. (2017) · Prognostics and System Health Management Conference · doi:10.1109/phm.2017.8079167 · Cited by 43
Self-citationLi, F., Chen, J., Pan, J. H., & Pan, T. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/ab6ade · Cited by 44
Liu, C., Qin, C., Shi, X., Wang, Z., Zhang, G., & Han, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3041905 · Cited by 52
“As for the studies concerned interpretability of deep models, Lei et al. [25] interpreted sparse filtering as measuring the similarity between the input and weight vectors and found the trained weight vectors perform as the Gabor wavelet.”
MethodBindi, M., Corti, F., Grasso, F., Luchetta, A., Manetti, S., Piccirilli, M. C., & Reatti, A. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3153827 · Cited by 44
“The recent diffusion of artificial intelligence in the industrial sector has led to the development of monitoring systems based on neural networks [6] and other machine learning algorithms [7], focusing on the data-driven approach.”
BackgroundPan, Z., Zhang, Z., Meng, Z., & Wang, Y. (2023) · ISA Transactions · doi:10.1016/j.isatra.2023.07.015 · Cited by 42
A Review on the Signal Processing Methods of Rotating Machinery Fault Diagnosis
Li, S., Xin, Y., Li, X., Wang, J., & Xu, K. (2019) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic.2019.8785572 · Cited by 42
“In recent years, with the development of deep learning theory[34], the research results of sparse filtering [36], sparse autoencoding unsupervised learning network [37-38], convolution neural network [39], optimization neural network [40], depth Boltzmann machine [41], depth confidence network [42] have been introduce…”
BackgroundHou, J., Wu, Y., Gong, H., Ahmad, A. S., & Liu, L. (2020) · Applied Sciences · doi:10.3390/app10010386 · Cited by 42
A novel normalized recurrent neural network for fault diagnosis with noisy labels
Nie, X., & Xie, G. (2020) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-020-01608-8 · Cited by 43
“The detailed implementation method can be found in Reference Arras et al. (2017).”
BackgroundInfluentialZhang, T., He, S., Chen, J., Pan, T., & Zhou, Z. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3134999 · Cited by 42
“We use the F1 score [32] to measure the performance of fault classification, as given in Fig.”
MethodWang, S., Lei, Y., Yang, B., Li, X., Shu, Y., & Lü, N. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107071 · Cited by 42
Self-citationParametric Fault Diagnosis Based on Fuzzy Cerebellar Model Neural Networks
Lin, Q., Chen, S., & Lin, C. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2884195 · Cited by 42
“Fault diagnosis techniques are usually divided into modelbased method [3], [4] and data-driven method [5]–[7].”
MethodFu, Y., Liu, K., Shen, Z., Deng, J., Gan, M., Liu, X., Lu, D., & Wang, K. (2019) · Remote Sensing · doi:10.3390/rs11030280 · Cited by 42
“In our approach, we adopt multinomial logistic regression (also known as softmax regression) as our classifier because it is efficient and straightforward [42].”
MethodYuan, J., & Tian, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2947714 · Cited by 43
“as deep belief networks (DBNs) [10], sparse auto-encoder (SAE) [11], stacked denoising auto-encoder (SDAE) [12], sparse filtering (SF) [13], convolutional neural networks (CNNs) [14] and long short-term memory (LSTM) [15].”
Zhang, Y., & Ji, J. (2020) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2020.3027912 · Cited by 41
A Fault Diagnosis Approach Based on 2D-Vibration Imaging for Bearing Faults
Mishra, R. K., Choudhary, A., Fatima, S., Mohanty, A. R., & Panigrahi, B. K. (2022) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-022-00735-1 · Cited by 40
Soft Manipulator for Soft Robotic Applications: a Review
Sut, D. J., & Sethuramalingam, P. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-01877-4 · Cited by 43
Regrouping particle swarm optimization based variable neural network for gearbox fault diagnosis
Liao, Y., Zhang, L., & Li, W. (2018) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-169542 · Cited by 40
Learning Representations With Local and Global Geometries Preserved for Machine Fault Diagnosis
Li, Y., Lekamalage, C. K. L., Liu, T., Chen, P.-A., & Huang, G.-B. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2905830 · Cited by 42
“To overcome the weakness of manual feature extraction, deep learning (DL)-based representational learning methods learn features automatically from raw data [7]–[9].”
Li, R., Li, S., Xu, K., Lu, J., Teng, G., & Du, J. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/abe163 · Cited by 44
Pei, X., Zheng, X., & Wu, J. (2021) · Measurement · doi:10.1016/j.measurement.2021.109452 · Cited by 40
Fault Detection of Bearing by Resnet Classifier with Model-Based Data Augmentation
Qian, L., Pan, Q. L., Lv, Y., & Zhao, X. (2022) · Machines · doi:10.3390/machines10070521 · Cited by 41
Multi-view and Multi-level network for fault diagnosis accommodating feature transferability
Lü, N., Cui, Z., Hu, H., & Yin, T. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119057 · Cited by 41
PeriodNet: Noise-Robust Fault Diagnosis Method Under Varying Speed Conditions
Li, R., Wu, J., Li, Y., & Cheng, Y. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3274290 · Cited by 46
“Hence, they cannot perform satisfactorily in solving complex fault diagnosis problems [21].”
BackgroundWang, J., Mo, Z., Zhang, H., & Miao, Q. (2020) · Measurement · doi:10.1016/j.measurement.2020.107517 · Cited by 39
An Advanced Operation Mode with Product-Service System Using Lifecycle Big Data and Deep Learning
Ren, S., Zhang, Y., Sakao, T., Liu, Y., & Cai, R. (2021) · International Journal of Precision Engineering and Manufacturing-Green Technology · doi:10.1007/s40684-021-00354-3 · Cited by 40
Vashishtha, G., & Kumar, R. (2022) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-022-00725-3 · Cited by 38
“In [34], the effects of sparse fil-tering’s input and output dimensions on diagnostic accuracy were investigated.”
BackgroundMethodXu, K., Huang, S., Yang, Z., Zhang, Y., Ye, F., Zheng, G., Lin, B., Zhou, M., & Sun, J. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107616 · Cited by 38
Mechanism and Method for Outer Raceway Defect Localization of Ball Bearings
Zhang, F., Huang, J., Chu, F., & Cui, L. (2020) · IEEE Access · doi:10.1109/access.2019.2950284 · Cited by 38
Bao, H., Yan, Z., Ji, S., Wang, J., Jia, S., Zhang, G., & Han, B. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/abe56f · Cited by 38
“Lei et al [11] applied SF to fault diagnosis and proposed a two-stage learning method for machine diagnosis that reduced the work-load of manually processing big data in fault diagnosis.”
End-to-end unsupervised fault detection using a flow-based model
Zhang, L., Lin, J., Shao, H., Zhang, Z., Yan, X., & Long, J. (2021) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2021.107805 · Cited by 38
Self-citationLiu, L., Wang, B., Ma, F., Zheng, Q., Yao, L., Zhang, C., & Mohamed, M. A. (2022) · Frontiers in Energy Research · doi:10.3389/fenrg.2022.837553 · Cited by 38
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.