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 701–800 of 1,001
Different analytical techniques for big data analysis: A review
Narayanan, U., Paul, V., & Joseph, S. (2017) · International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS) · doi:10.1109/icecds.2017.8390139 · Cited by 12
An intelligent fault diagnosis method of rotating machinery using L1-regularized sparse filtering
Qian, W., Li, S., Wang, J., An, Z., & Jiang, X. (2018) · Journal of Vibroengineering · doi:10.21595/jve.2018.19339 · Cited by 12
“A whitening approach [2] is utilized to preprocess the training samples and obtain the whitened dataset S ∈ R × , where K is the number of samples and N is the dimension of samples.”
BackgroundMethodInfluentialReview of various Artificial Intelligence Techniques and its applications
Varshney, S., Jigyasu, R., Sharma, A., & Mathew, L. (2019) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/594/1/012023 · Cited by 12
Diagnosis of Electric Motor Using Acoustic noise Based on CNN
Choi, D.-J., Han, J.-H., Park, S.-U., & Hong, S.-K. (2019) · International Conference on Electrical Machines and Systems (ICEMS) · doi:10.1109/icems.2019.8922130 · Cited by 12
“((1)Inamometer controller, (2)Gearbox, (3)Inamometer, (4)NI PXI, (5)Motor, (6) Audio unit, (7) Audio Interface)”
Termite, M. R., Baraldi, P., Al‐Dahidi, S., Bellani, L., Compare, M., & Zio, E. (2019) · Energies · doi:10.3390/en12244802 · Cited by 12
“The use of unsupervised clustering methods [31,32] has been proposed to reduce expert efforts.”
MethodMachine-Learning-Based Intelligent Mechanical Fault Detection and Diagnosis of Wind Turbines
Gao, Q., Wu, X., Guo, J., Zhou, H., & Ruan, W. (2021) · Mathematical Problems in Engineering · doi:10.1155/2021/9915084 · Cited by 12
“Also, a collection of deep learning methods, such as deep belief network (DBN) [29], sparse autoencoder (SAE) [30], denoising autoencoder (DAE) [31], sparse filtering [32], convolutional neural network (CNN) [33], and recurrent neural network (RNN) [34], have shown extraordinary feature learning capacity and significa…”
BackgroundGao, D., Lin, X., & Yang, Q. (2022) · International Journal of Control Automation and Systems · doi:10.1007/s12555-021-0234-6 · Cited by 12
A Fault Diagnosis System for a Pipeline Robot Based on Sound Signal Recognition
Cao, H., Yu, J., Wang, Y., Zhang, L., & Kim, J. (2022) · Sensors · doi:10.3390/s22093275 · Cited by 12
Li, L., Zhang, M., & Wang, K. (2020) · Sensors · doi:10.3390/s20071841 · Cited by 12
A Feature Transferring Fault Diagnosis based on WPDR, FSWT and GoogLeNet
Cao, G., Zhang, K., Zhou, K., Pan, H., Xu, Y., & Liu, J. (2020) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc43012.2020.9129483 · Cited by 12
“However, the decomposed signals of high frequency exist poor frequency resolution and uneven distribution [15-16].”
BackgroundHu, Z., Shen, D., & Chen, W. (2023) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2023.108313 · Cited by 12
Shao, T., Wang, S., Wang, Q., Wu, T., & Huang, Z. (2023) · Friction · doi:10.1007/s40544-023-0752-8 · Cited by 11
“In contrast to feature engineering-based machine learning methods, the CNN model is able to automatically learn the representation features from a large number of image samples [25, 26].”
Multiscale ECA network: a rotation mechanical domain adaptation method with minimal class confusion
Li, X., Yu, T., Wang, X., Li, D., Xie, Z., & Kong, X. (2024) · Structural Health Monitoring · doi:10.1177/14759217241261155 · Cited by 12
Deng, J., Cheng, Z., Gu, A., & Zhang, S. (2025) · PLoS ONE · doi:10.1371/journal.pone.0324180 · Cited by 11
“With the advancement of machine learning and deep learning, data-driven fault diagnosis methods have become a research hotspot [11].”
Self-Adaption AAE-GAN for Aluminum Electrolytic Cell Anomaly Detection
Cao, D., Liu, D., Ren, X., & Ma, N. (2021) · IEEE Access · doi:10.1109/access.2021.3097116 · Cited by 11
A key-factor denoising strategy for quasi periodic non-stationary incipient faults diagnosis
Yang, J. M., Xie, G., & Yang, Y. (2022) · Measurement · doi:10.1016/j.measurement.2022.111304 · Cited by 11
Gear fault diagnosis using gear meshing stiffness identified by gearbox housing vibration signals
Yu, X., Huangfu, Y., Yang, Y., Du, M., He, Q., & Peng, Z. (2022) · Frontiers of Mechanical Engineering · doi:10.1007/s11465-022-0713-3 · Cited by 11
Yang, J. M., Xie, G., & Yang, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3244795 · Cited by 13
“and has long been valued and studied [4], [5], [6], [7].”
BackgroundZhang, Z., Peng, L., Dai, G., Wang, M., Bai, J., Lei, Z., & Li, J. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3291736 · Cited by 12
“The effectiveness of most intelligent fault diagnosis techniques is predicated upon two fundamental requirements, as illustrated in [11], [12], and [13].”
BackgroundWeighted-feature and cost-sensitive regression model for component continuous degradation assessment
Liu, J., & Zio, E. (2017) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2017.03.012 · Cited by 11
Lan, Y., Han, X., Zong, W., Ding, X., Xiong, X., Huang, J., & Ma, B. (2017) · Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · doi:10.1177/0954406217728091 · Cited by 11
Condition Based Maintenance of Oil and Gas Equipment: A Review
Abbasi, T., Lim, K. H., Soomro, T. A., Ismail, I. B., & Ali, A. (2020) · International Conference on Computing, Mathematics and Engineering Technologies (iCoMET) · doi:10.1109/icomet48670.2020.9073819 · Cited by 14
“[80] utilized stacked autoencoder to learn feature from the vibration signals and then use softmax regression to classify the health condition of bearing.”
MethodLi, X., Zhang, Y., Li, Y., Zhan, Y., & Yang, L. (2021) · Shock and Vibration · doi:10.1155/2021/6699611 · Cited by 11
Application of Machine Learning in Fused Deposition Modeling: A Review
Equbal, A., Akhter, S., Equbal, M. A., & Sood, A. K. (2021) · Materials forming, machining and tribology · doi:10.1007/978-3-030-68024-4_23 · Cited by 16
Artificial Neural Networks ( ANNs )
Nandi, A. K., & Ahmed, H. (2019) · Wiley eBooks · doi:10.1002/9781119544678.ch12 · Cited by 13
Scale adaptive subdomain matching network for bearing fault diagnosis
Zhang, D., Wei, Y., Wang, B., & Liu, S. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac3627 · Cited by 11
“Lei et al [9] established an unsupervised sparse filter network that learns features from the original vibration signal and diagnosed the device state through softmax regression.”
Wang, S., & Zhang, Y. (2022) · Journal of Marine Science and Engineering · doi:10.3390/jmse10060743 · Cited by 13
Research on online fault detection tool of substation equipment based on artificial intelligence
Xingxin, C., Xin, Z., & Gangming, W. (2022) · Journal of King Saud University - Science · doi:10.1016/j.jksus.2022.102149 · Cited by 11
Restricted Boltzmann Machines Based Fault Estimation in Multi Terminal HVDC Transmission System
Muzzammel, R. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-5232-8_66 · Cited by 11
Guo, X., Liu, A., Li, X., & Xiao, Y. (2020) · International Journal of Fuzzy Systems · doi:10.1007/s40815-020-00859-0 · Cited by 12
Dynamic Bhattacharyya Bound-Based Approach for Fault Classification in Industrial Processes
Jiang, B., & Zhu, B. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3056533 · Cited by 11
Gu, L. (2021) · Mobile Information Systems · doi:10.1155/2021/6452418 · Cited by 14
“Its definition is as follows: there are ra records in dataset X, and its GiniIndex definition is as follows [15]:”
BackgroundMa, M., Wang, Z., Li, T., & Zhang, Z. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad4ab3 · Cited by 10
Wind Turbine Condition Monitoring Based on SCADA Data–Image Conversion
Long, H., Xu, S., Cai, H., & Gu, W. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3470060 · Cited by 10
“Various deep neural network models have been developed to estimate WT status based on SCADA data, including a deep belief network stacking [10], sparse filtering [11], automatic denoising encoder [12], and recursive neural network [13].”
MethodZhang, F., Liu, J., Liu, Y., Li, Y., Duan, R., Chen, Z., & Jiang, X. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110240 · Cited by 10
Yao, Y., Sun, X., Feng, J. Y., & Xing, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129517 · Cited by 10
Monitoring Pneumatic Actuators’ Behavior Using Real-World Data Set
Kovács, T., & Kő, A. (2020) · SN Computer Science · doi:10.1007/s42979-020-00202-2 · Cited by 13
Unsupervised Root-Cause Analysis for Integrated Systems
Pan, R., Zhang, Z., Li, X., Chakrabarty, K., & Gu, X. (2020) · IEEE International Test Conference (ITC) · doi:10.1109/itc44778.2020.9325268 · Cited by 12
“Thus, more dynamic and less human-dependent, unsupervised root-cause analysis methods have been proposed [7], [13].”
BackgroundMethodArtificial Intelligence and employment: a systematic review
de Acypreste, R., & Paraná, E. (2022) · Brazilian Journal of Political Economy · doi:10.1590/0101-31572022-3320 · Cited by 14
Robust locally linear embedding and its application in analogue circuit fault diagnosis
He, W., Yuan, Z., Yin, B., Wu, W., & Min, Z. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/acdcb1 · Cited by 10
“Softmax regression is widely exploited as the final layer of neural networks for multiclass classification due to its advantages of flexibility, implementation simplicity and computational efficiency [37].”
Multi-Instance Attention Network for Anomaly Detection from Multivariate Time Series
Jang, G.-B., & Cho, S.-B. (2023) · Cybernetics & Systems · doi:10.1080/01969722.2023.2240651 · Cited by 10
“There are models that use deep learning (Lei et al. 2016) and hybrid methods (Zhao et al. 2017) for anomaly detection.”
MethodDiscriminative Stacked Autoencoder: Feature-Integration Boosting for Bearing Fault Diagnosis
Liu, S., He, J., Chen, Z., Chen, D., & Chen, Y. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3317873 · Cited by 10
“…the FCL, and l was the output number of the FCL. Supposing it was a classification problem of t class, the output of the FCL was connected to the softmax [31] classifier, and the probability value of the current sample belonging to each class was obtained ; θ) p ( U = 2 | O ( l ) ; θ) ... ...”
MethodAFCNet: A Fusion Method of Multisensor Data Based on Adaptive Feature Complementation
Sun, L., Cao, C., Bai, G., Zhong, Z., Sun, W. F., & Wang, D. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3384516 · Cited by 10
“Questions persist regarding the optimal feature extraction method for specific types of sensory data [9], [10].”
MethodAkbalık, F., Yildiz, A., Ertuğrul, Ö. F., & Zan, H. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-024-03746-5 · Cited by 11
Xing, S., Lei, Y., Jia, F., & Lin, J. (2017) · IEEE International Conference on Industrial Engineering and Engineering Management (IEEM) · doi:10.1109/ieem.2017.8290228 · Cited by 10
Self-citationKang, S., Qiao, C., Wang, Y., Wang, Q., Hu, M., & Микулович, В. И. (2020) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-020-1003-9 · Cited by 11
“[11] used the frequency-domain amplitude spectrum of rolling bearings as the input to an autoencoder to identify faults in rolling bearings in different states.”
MethodRetracted: A Convenient Machine Learning Model for Cyber Security
Thanuja, N., & Deepak, N. R. (2021) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc51019.2021.9418051 · Cited by 25
RetractedTian, J., Han, D., Xiao, L., & Shi, P. (2021) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-210932 · Cited by 10
Technical Language Supervision for Intelligent Fault Diagnosis in Process Industry
Löwenmark, K., Taal, C., Schnabel, S., Liwicki, M., & Sandin, F. (2022) · International Journal of Prognostics and Health Management · doi:10.36001/ijphm.2022.v13i2.3137 · Cited by 14
A Semisupervised Method With Swarm Intelligence Optimization for Intelligent Fault Diagnosis
Xu, Z., Feng, Z., Wu, Q., & Yang, S. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3268131 · Cited by 10
“For example, autoen-coders have been used in fault diagnosis [14], [15], [16], and several innovative semisupervised learning methods using autoencoders for assistance have emerged [17], [18], [19].”
Methodvan den Hoogen, J., Hudson, D., Bloemheuvel, S., & Atzmueller, M. (2023) · International Journal of Data Science and Analytics · doi:10.1007/s41060-023-00440-6 · Cited by 12
Structural health monitoring of aircraft through prediction of delamination using machine learning
Rajeswari, D., Khalaf, O. I., Srinivasan, R., Pushpalatha, M. N., & Hamam, H. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.1955 · Cited by 10
“Lei et al. (2017) proposed multi-task architecture and ensembleDetNet technique to detect and classify infrastructure damage.”
MethodFeng, D., & Li, Y. (2017) · Polish Maritime Research · doi:10.1515/pomr-2017-0123 · Cited by 10
Ma, S. Q., Lu, S., Xia, M., Ding, J., Niu, J., & Liu, Y. (2019) · Measurement Science and Technology · doi:10.1088/1361-6501/ab5cca · Cited by 11
Time-series Deep Learning Fault Detection with the Application of Wind Turbine Benchmark
Rahimilarki, R., Gao, Z., Jin, N., & Zhang, A. (2019) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin41052.2019.8972237 · Cited by 10
“Many DL methods have been developed for fault diagnosis in literature review, such as sparse filtering [16], convolutional deep belief networks [17], and convolutional neural network [18].”
A Novel Deep Sparse Filtering Method for Intelligent Fault Diagnosis by Acoustic Signal Processing
Zhang, G., Wang, J., Han, B., Jia, S., Wang, X., & He, J. (2020) · Shock and Vibration · doi:10.1155/2020/8837047 · Cited by 10
“In order to show the superiority of DSF model, standard SF [19], L1 regularized sparse filtering (L1-SF) [21], and L2 regularized sparse filtering (L2-SF) [20] are used as comparison methods. output dimension of the three comparison methods is set as 1200, the number of iterations is 100, and the…”
BackgroundMethodGao, D., Lv, Y.-W., Sun, Y.-G., Wang, Y., & Yang, Q. (2020) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc49329.2020.9164523 · Cited by 10
Self-validating high-g accelerometers through data-driven methods
Wen, J., Yao, H., Ji, Z., Wu, B., & Xu, F. (2021) · Sensors and Actuators A Physical · doi:10.1016/j.sna.2021.112803 · Cited by 10
“Meanwhile, the fault detection and fault diagnosis results can be intuitively demonstrated with the confusion matrix, which is also one of the commonly used visualization methods for classification problems [50-54].”
Jun, S., Shen, C., & Zhu, Z. (2017) · International Journal of Rotating Machinery · doi:10.1155/2017/2384184 · Cited by 10
“Hence, the demand to inspect the health condition of these crucial components is increasing, and an efficient and intelligentmachine fault diagnosis method should be developed to improve the reliability, safety, and effectiveness of operating systems [3, 4].”
MethodA Data-Driven Smart Fault Diagnosis Method for Electric Motor
Gou, X., Bian, C., Zeng, F., Xu, Q., Wang, W., & Yang, S. (2018) · IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C) · doi:10.1109/qrs-c.2018.00053 · Cited by 10
Recent Advances in Intelligent Data Analysis and Its Applications
Zhang, C., Li, W., Zhang, H., & Zhan, T. (2024) · Electronics · doi:10.3390/electronics13010226 · Cited by 12
Fault causes identification of rotating machinery based on multiphase zoom permutation entropy
Ma, C., Wang, X., Li, Y., & Cai, Z. (2023) · Measurement · doi:10.1016/j.measurement.2023.114028 · Cited by 9
Enhancing Fault Diagnosis in IoT Sensor Data through Advanced Preprocessing Techniques
Sung, S.-H., Hong, S.-G., Choi, H., Park, D.-M., & Kim, S. (2024) · Electronics · doi:10.3390/electronics13163289 · Cited by 10
Wang, R., Yan, H., Dong, E., Cheng, Z., Li, Y., & Jia, X. (2024) · Open Physics · doi:10.1515/phys-2024-0110 · Cited by 10
“[62].”
Zou, X., Luo, L., Wang, Z., Tao, P., Wu, H., & Pan, J. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.112467 · Cited by 9
Multimodal Fault Diagnosis of Rotating Machinery Using Dynamic Fusion and Improved DS Theory
Yang, H., Yao, Q., & Yin, S. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3642387 · Cited by 11
Autoencoder and Incremental Clustering-Enabled Anomaly Detection
Connelly, A. C., Zaidi, S. A. R., & McLernon, D. (2023) · Electronics · doi:10.3390/electronics12091970 · Cited by 9
Jiao, Z., Zhang, Z., Li, Y., Wu, Y., Liu, L., & Shao, S. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad30bc · Cited by 9
“‹ SF is an efficient machine learning algorithm [46].”
Yi, C.-P., Lin, Y.-J., Ho, P.-J., & Yang, S.-C. (2024) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2024.3426031 · Cited by 9
Harnessing Deep Learning for Fault Detection in Industry 4.0: A Multimodal Approach
Shen, J., Morrison, M., Miao, H., & Gu, F. (2024) · IEEE International Conference on Cognitive Machine Intelligence (CogMI) · doi:10.1109/cogmi62246.2024.00045 · Cited by 14
Fault Detection for Discrete‐Time Uncertain Systems with Polytopic Uncertainties: A Markov Approach
Wang, G., Gao, X., Miao, X., & Cao, Y. (2018) · Asian Journal of Control · doi:10.1002/asjc.1872 · Cited by 9
“In order to obtain greater economic and social benefits [1,2], the technique for fault diagnosis [3,4] is proved to be very useful, where fault detection problem should be considered beforehand.”
BackgroundGu, L., & Yang, B. (2019) · IEEE Access · doi:10.1109/access.2018.2890154 · Cited by 9
An, Z., Li, S., Jiang, X., Xin, Y., & Wang, J. (2019) · IEEE Access · doi:10.1109/access.2019.2961711 · Cited by 9
“Therefore, various intelligent algorithms have been proposed for fault diagnosis, such as Artificial Neural Networks (ANN) [6], [7], Autoencoders [8], [9], Restricted Boltzmann Machine (RBM) [10], Convolutional Neural Networks (CNN) [11], [12], Sparse Filtering [13], [14] and k-Nearest Neighbor [15].”
MethodWang, R., Gao, X., Gao, J., Gao, Z., & Xie, J. (2020) · ISA Transactions · doi:10.1016/j.isatra.2020.12.021 · Cited by 9
Li, Q., Huang, Q., Zhou, Y., Yang, T., Ran, M., & Liu, X. (2021) · IEEE Access · doi:10.1109/access.2021.3078709 · Cited by 9
“In [18], an unsupervised learning method based on sparse filtering and softmax was proposed to solve the problem of fault diagnosis against the background of big data.”
MethodUnsupervised Two-Stage Root-Cause Analysis for Integrated Systems
Pan, R., Zhang, Z., Li, X., Chakrabarty, K., & Gu, X. (2021) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2021.3103818 · Cited by 9
Zhen, J. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/1543625 · Cited by 9
Wang, S., Zhang, Y., Zhang, B., Fei, Y., He, Y., Li, P., & Xu, M. (2022) · Journal of Marine Science and Engineering · doi:10.3390/jmse10101376 · Cited by 9
“A feature extraction approach based on the sparse filtering of the raw data was proposed in [13].”
MethodParallel network using intrinsic component filtering for rotating machinery fault diagnosis
Han, B., Liu, Z., Zhang, Z., Wang, J., Bao, H., Yang, Z., Xing, S., Jiang, X., & Li, B. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/aca705 · Cited by 9
“In recent years, it is widely used in the field of fault diagnosis [19–22].”
Self-citationAn Empirical Analysis about the Generalization Performance of Data-driven Fault Diagnosis Methods
Huailiang, Z., Rixin, W., Yang, Y., Jiancheng, Y., & Xu, M. (2020) · Journal of Mechanical Engineering · doi:10.3901/jme.2020.09.102 · Cited by 11
“1.1 影响诊断方法泛化性能的可能因素 数据驱动故障诊断方法通常按图 1 所示的基本 流程来执行,包括模型的训练和利用模型进行诊断 两个阶段。训练诊断模型阶段包含下述三个主要的 步骤 [13] (1) 训练数据的质量和数量。 数据是诊断知识的载体,是该类故障诊断方法 所依赖的基础,因此用于训练模型的数据质量和数 量将是影响诊断模型泛化性能和诊断结果的一个因 素。具体而言,训练数据的质量和数量包括下述几 个方面:已标记样本数据量;不同故障模式样本的 数量;同一模式下数据的质量。 在数据驱动的故障诊断方法中,推理故障特征 和模式之间对应关系的学习方法,例如 KNN [10, 22] 、 ANN…”
InfluentialIntelligent Process Quality Management for Supporting Collaboration of Mold Manufacturing SMEs
Kim, S., & Ryu, K. (2020) · Procedia Manufacturing · doi:10.1016/j.promfg.2020.10.054 · Cited by 9
Classification Based on Brain Storm Optimization With Feature Selection
Xue, Y., Zhao, Y. L., & Słowik, A. (2020) · IEEE Access · doi:10.1109/access.2020.3045970 · Cited by 9
“INTRODUCTION Classification problem has been widely studied in machine learning [1].”
BackgroundKESTİRİMCİ BAKIMDA MAKİNE ÖĞRENMESİ: LİTERATÜR ARAŞTIRMASI
DÜNDAR, D. R., Sarıçiçek, İ., Çinar, E. M., & Yazıcı, A. T. (2021) · Eskişehir Osmangazi Üniversitesi mühendislik ve mimarlık fakültesi dergisi :/Osmangazi Üniversitesi Mühendislik-Mimarlık Fakültesi dergisi · doi:10.31796/ogummf.873963 · Cited by 13
Using anomaly detection to support classification of fast running packaging processes
Klaeger, T., Schult, A., & Oehm, L. (2019) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin41052.2019.8972081 · Cited by 9
“A major research in this area is the analysis of different kind of rotating machine parts like motors, bearings and pumps [8], [9].”
BackgroundAn Improved Hybrid CNN-SVM based Method for Bearing Fault Diagnosis Under Noisy Environment
Xu, J., Ma, L., We, Z., Yang, Q., Li, X., & Liu, S. (2019) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2019.8832683 · Cited by 9
“Several methods have already been applied on the fault diagnosis, such as deep belief network (DBN) [7], sparse auto-encoder (SAE) [8], stacked denoising auto-encoder (SDAE) [9], sparse filtering [10], and the one-dimensional CNN [11].”
MethodDeep optimal feature extraction and selection-based motor fault diagnosis using vibration
Jigyasu, R., Shrivastava, V., & Singh, S. (2024) · Electrical Engineering · doi:10.1007/s00202-024-02356-1 · Cited by 9
Self-learning guided residual shrinkage network for intelligent fault diagnosis of planetary gearbox
Lv, X., Wang, J., Qin, R., Bao, J., Jiang, X., Zhang, Z., Han, B., & Jiang, X. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109603 · Cited by 8
Few-shot specific emitter identification via asymmetric dual-path masked autoencoder
Yang, S., Yu, S., Li, Q., Xia, K., & Zhu, H. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105201 · Cited by 8
Lee, S., Choi, J., & Son, Y. (2023) · Annals of Operations Research · doi:10.1007/s10479-022-05071-x · Cited by 9
Monitoring Pumping Units by Convolutional Neural Networks for Operating Point Estimations
Ma, H., Gaisser, L., & Riedelbauch, S. (2023) · Energies · doi:10.3390/en16114392 · Cited by 8
Rolling element bearing fault diagnosis using machine learning techniques: A review
Sahu, D., Dewangan, R. K., & Matharu, S. P. S. (2023) · AIP conference proceedings · doi:10.1063/5.0134211 · Cited by 10
Wang, R., Jia, X., Liu, Z., Dong, E., Li, S., & Cheng, Z. (2023) · Eksploatacja i Niezawodnosc - Maintenance and Reliability · doi:10.17531/ein/175291 · Cited by 9
“…maps (usually two-dimensional matrices) output from the convolutional and pooling layers into one-dimensional vectors, and to perform product and addition operations with a set of learnable weight matrices to obtain the final classification results by the SR classifier [22], as shown in Step 2.”
MethodEstimation of Tool Life in the Milling Process—Testing Regression Models
Paszkiewicz, A., Piecuch, G., Żabiński, T., Bolanowski, M., Salach, M., & Rączka, D. (2023) · Sensors · doi:10.3390/s23239346 · Cited by 9
“As [28], research is being conducted to develop methods that maintain good clas-si the number of data increases exponentially with the development of IoT technology [28], research is being conducted to develop methods that maintain good classification quality while reducing the amount of data used…”
MethodAI-based inspection of the axes of machine tools
Demetgül, M., Wang, W., Fleischer, J., & Tansel, I. (2023) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-023-12830-y · Cited by 10
Zhang, Z., Shen, Y., & Xu, S. (2024) · Control Engineering Practice · doi:10.1016/j.conengprac.2024.105871 · Cited by 8
Imbalanced classification in faulty turbine data: New proximal policy optimisation
Rousta, M. M., Shoorehdeli, M. A., & Yari, M. (2024) · IET Collaborative Intelligent Manufacturing · doi:10.1049/cim2.12114 · Cited by 8
Li, K., Yang, R., Wei, T., Yang, Y., & Xiang, J. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad8179 · Cited by 8
Lang, W., Li, Q., Liang, W., Niu, M., Chen, J. W., & Hu, Y. (2024) · IEEE Transactions on Transportation Electrification · doi:10.1109/tte.2024.3497319 · Cited by 8
“Current research focuses on intelligent fault diagnosis techniques, which can efficiently process massive sensor signals and provide accurate fault diagnosis results, offering promising solutions for improving the efficiency and accuracy of machine health monitoring [3], [4].”
Optimal weighted multi-scale entropy-energy ratio feature for rolling bearing degradation assessment
Shen, C., Luo, J., Jiang, P., Lin, G., & Zhang, S. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ada633 · Cited by 8
“We verify the effectiveness of the proposed method using the rolling bearing vibration experimental dataset from the NSFI/UCR Intelligent Maintenance Center (IMS) [24] and Xi’an Jiaotong University-Changxing Shengyang Technology (XJTU-SY) [25].”
Bynum, J., & Lattanzi, D. (2021) · Advances in Mechanical Engineering · doi:10.1177/16878140211009015 · Cited by 9
“18 Recently, a variety of studies have considered using a spectrogram representation of an acoustic signal as a neural network input, rather than the raw time series data.”
Background
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.