RESEARCH PAPER
Advanced Sparse Filtering-Based Domain Adaptation for Fault Diagnosis in Variable Working Conditions
More details
Hide details
1
National and Local Joint Engineering Research Center of Reliability Analysis and Testing for Mechanical and Electrical Products, Zhejiang Sci-Tech University, China
Submission date: 2024-05-18
Final revision date: 2024-09-05
Acceptance date: 2024-10-06
Online publication date: 2024-10-26
Publication date: 2024-10-26
Corresponding author
Ziyou Zhou
National and Local Joint Engineering Research Center of Reliability Analysis and Testing for Mechanical and Electrical Products, Zhejiang Sci-Tech University, China
Eksploatacja i Niezawodność – Maintenance and Reliability 2025;27(2):194181
HIGHLIGHTS
- Incorporating normalization and cosine penalty into sparse filtering enhances cross-domain feature extraction consistency.
- Integrating Bootstrap with maximum mean discrepancy improves domain difference assessment accuracy.
- The proposed method effectively addresses variable working condition fault diagnosis challenges.
KEYWORDS
TOPICS
ABSTRACT
Traditional domain adaptation (DA) methods often encounter challenges with cross-domain feature extraction and the precise assessment of domain differences. To overcome these limitations, we introduce the Enhanced Sparse Filtering-Based Domain Adaptation (ESFBDA) method. This method distinguishes itself by enhancing sparse filtering (SF) with the integration of row-column normalization and a cosine penalty, specifically designed to minimize feature loss—a critical issue in existing DA techniques. Additionally, we employ Bootstrap resampling to refine domain distribution alignment, a novel step that boosts feature similarity and effectiveness in DA. This integrated approach ensures more accurate feature extraction, which is crucial for the classifier's fault detection capability. In our study, through two distinct experiments on WT-planetary gearbox fault diagnosis and bearing fault diagnosis, the ESFBDA method demonstrated remarkable accuracy, significantly surpassing traditional approaches and showcasing its robust applicability across varied diagnostic scenarios.
REFERENCES (35)
1.
Alquier P, Chérief-Abdellatif B-E, Derumigny A, Fermanian J-D. Estimation of copulas via maximum mean discrepancy. Journal of the American Statistical Association. 2023;118(543):1997-2012.
https://doi.org/10.1080/016214....
2.
An Y, Zhang K, Chai Y, Liu Q, Huang X. Domain adaptation network base on contrastive learning for bearings fault diagnosis under variable working conditions. Expert Systems with Applications. 2023;212:118802.
https://doi.org/10.1016/j.eswa....
3.
Bao H, Yan Z, Ji S, Wang J, Jia S, Zhang G, et al. An enhanced sparse filtering method for transfer fault diagnosis using maximum classifier discrepancy. Measurement Science and Technology. 2021;32(8):085105.
https://doi.org/10.1088/1361-6....
4.
Center BD. Case western reserve university bearing data [Internet]. Cleveland, Ohio, U.S. Case School of Engineering. Available from:
http://csegroups, case. ed./bearingdatacenter/pages/down-loaddata-file.
5.
Chopra P, Yadav SK. Restricted Boltzmann machine and softmax regression for fault detection and classification. Complex & Intelligent Systems. 2018;4:67-77.
https://doi.org/10.1007/s40747....
6.
Ding Y, Jia M, Zhuang J, Cao Y, Zhao X, Lee C-G. Deep imbalanced domain adaptation for transfer learning fault diagnosis of bearings under multiple working conditions. Reliability Engineering & System Safety. 2023;230:108890.
https://doi.org/10.1016/j.ress....
7.
Gao T, Yang J, Tang Q. A multi-source domain information fusion network for rotating machinery fault diagnosis under variable operating conditions. Information Fusion. 2024;106:102278.
https://doi.org/10.1016/j.inff....
8.
Gould NI, Porcelli M, Toint PL. Updating the regularization parameter in the adaptive cubic regularization algorithm. Computational optimization and applications. 2012;53:1-22.
https://doi.org/10.1007/s10589....
9.
Griffin D, Lim J. Signal estimation from modified short-time Fourier transform. IEEE Transactions on acoustics, speech, and signal processing. 1984;32(2):236-243.
https://doi.org/10.1109/TASSP.....
10.
Han C, Lei Y, Xie Y, Zhou D, Gong M. Visual domain adaptation based on modified A− distance and sparse filtering. Pattern Recognition. 2020;104:107254.
https://doi.org/10.1016/j.patc....
11.
Ji S, Han B, Zhang Z, Wang J, Lu B, Yang J, et al. Parallel sparse filtering for intelligent fault diagnosis using acoustic signal processing. Neurocomputing. 2021;462:466-477.
https://doi.org/10.1016/j.neuc....
12.
Jiang M, Liang Y, Feng X, Fan X, Pei Z, Xue Y, et al. Text classification based on deep belief network and softmax regression. Neural Computing and Applications. 2018;29:61-70.
https://doi.org/10.1007/s00521....
13.
Li W, Huang R, Li J, Liao Y, Chen Z, He G, et al. A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: Theories, applications and challenges. Mechanical Systems and Signal Processing. 2022;167:108487.
https://doi.org/10.1016/j.ymss....
14.
Liu D, Cui L, Cheng W. A review on deep learning in planetary gearbox health state recognition: Methods, applications, and dataset publication. Measurement Science and Technology. 2023.
https://doi.org/10.1088/1361-6....
15.
Ma L, Yang P, Peng K. Multitask Learning Based Collaborative Modeling of Heterogeneous Data for Compound Fault Diagnosis in Manufacturing Processes. IEEE Transactions on Industrial Informatics. 2024.
https://10.1109/TII.2024.34416....
16.
Ma Y, Shan C, Gao J, Chen H. Multiple health indicators fusion-based health prognostic for lithium-ion battery using transfer learning and hybrid deep learning method. Reliability Engineering & System Safety. 2023;229:108818.
https://doi.org/10.1016/j.ress....
17.
Pang B, Liu Q, Sun Z, Xu Z, Hao Z. Time-frequency supervised contrastive learning via pseudo-labeling: An unsupervised domain adaptation network for rolling bearing fault diagnosis under time-varying speeds. Advanced Engineering Informatics. 2024;59:102304.
https://doi.org/10.1016/j.aei.....
18.
Qian Q, Wang Y, Zhang T, Qin Y. Maximum mean square discrepancy: a new discrepancy representation metric for mechanical fault transfer diagnosis. Knowledge-Based Systems. 2023;276:110748.
https://doi.org/10.1016/j.knos....
19.
Schwendemann S, Amjad Z, Sikora A. Bearing fault diagnosis with intermediate domain based layered maximum mean discrepancy: A new transfer learning approach. Engineering Applications of Artificial Intelligence. 2021;105:104415.
https://doi.org/10.1016/j.enga....
20.
Shi Y, Deng A, Ding X, Zhang S, Xu S, Li J. Multisource domain factorization network for cross-domain fault diagnosis of rotating machinery: An unsupervised multisource domain adaptation method. Mechanical Systems and Signal Processing. 2022;164:108219.
https://doi.org/10.1016/j.ymss....
21.
Smith WA, Randall RB. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study. Mechanical systems and signal processing. 2015;64:100-131.
https://doi.org/10.1016/j.ymss....
22.
Wang C, Zhu G, Liu T, Xie Y, Zhang D. A sub-domain adaptive transfer learning base on residual network for bearing fault diagnosis. Journal of Vibration and Control. 2023;29(1-2):105-117.
https://doi.org/10.1177/107754....
23.
Wang H, Li C, Ding P, Li S, Li T, Liu C, et al. A Novel Transformer-based Few-Shot Learning Method for Intelligent Fault Diagnosis with Noisy Labels under Varying Working Conditions. Reliability Engineering & System Safety. 2024:110400.
https://doi.org/10.1016/j.ress....
24.
Wang J, Ji S, Han B, Bao H. Intelligent fault diagnosis for rotating machinery using L1/2-SF under variable rotational speed. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. 2021;235(5):1409-1422.
https://doi.org/10.1177/095440....
26.
Yu X, Wang Y, Liang Z, Shao H, Yu K, Yu W. An adaptive domain adaptation method for rolling bearings’ fault diagnosis fusing deep convolution and self-attention networks. IEEE Transactions on Instrumentation and Measurement. 2023;72:1-14.
https://10.1109/TII.2024.34416....
28.
Zhang G, Han B, Li S, Wang J, Wang X. General normalized maximum mean discrepancy: intelligent fault identification method for bearings and gears under unstable conditions. Measurement Science and Technology. 2021;32(10):104001.
https://doi.org/10.1088/1361-6....
29.
Zhang Y, Han D, Tian J, Shi P. Domain adaptation meta-learning network with discard-supplement module for few-shot cross-domain rotating machinery fault diagnosis. Knowledge-Based Systems. 2023;268:110484.
https://doi.org/10.1016/j.aei.....
30.
Zhang Y, Ji J, Ma B. Reciprocating compressor fault diagnosis using an optimized convolutional deep belief network. Journal of Vibration and Control. 2020;26(17-18):1538-1548.
https://doi.org/10.1177/107754....
31.
Zhang Z, Huang W, Liao Y, Song Z, Shi J, Jiang X, et al. Bearing fault diagnosis via generalized logarithm sparse regularization. Mechanical Systems and Signal Processing. 2022;167:108576.
https://doi.org/10.1016/j.ymss....
32.
Zhang Z, Yang Q. Unsupervised feature learning with reconstruction sparse filtering for intelligent fault diagnosis of rotating machinery. Applied Soft Computing. 2022;115:108207.
https://doi.org/10.1016/j.asoc....
33.
Zhou Z. Fault diagnosis method for imbalanced and unlabeled data based on bayesian graph balanced learning. Measurement Science and Technology. 2024;35(9):096131.
https://doi.org/10.1177/107754....
34.
Zhou Z, Chen W. Adaptive multi-scale graph fusion for fault diagnosis in concurrent variable conditions and unlabeled data. Journal of Vibration and Control. 2024:10775463241272933.
https://doi.org/10.1088/1361-6....
35.
Zhou Z, Chen W, Yang C. Adaptive range selection for parameter optimization of VMD algorithm in rolling bearing fault diagnosis under strong background noise. Journal of Mechanical Science and Technology. 2023;37(11):5759-5773.
https://doi.org/10.1007/s12206....