Rolling bearing fault diagnosis based on the joint structure retention migration in multi-source domains

ZHOU Hongdi1, 2, WANG Zhiwen1, TAO Qi1, 2

Journal of Vibration and Shock ›› 2025, Vol. 44 ›› Issue (14) : 302-310.

PDF(1662 KB)
PDF(1662 KB)
Journal of Vibration and Shock ›› 2025, Vol. 44 ›› Issue (14) : 302-310.
FAULT DIAGNOSIS ANALYSIS

Rolling bearing fault diagnosis based on the joint structure retention migration in multi-source domains

  • ZHOU Hongdi1,2,WANG Zhiwen1,TAO Qi*1,2
Author information +
History +

Abstract

Aiming at the problem that the feature distributions of two domains of rolling bearings under the conditions of variable operating conditions have large differences, and the scarcity of target domain labels leads to low fault diagnosis accuracy, an unsupervised rolling bearing fault diagnosis method based on the joint structure of multi-source domains to maintain the migration is proposed. Firstly, the source domain with higher similarity to the target domain is screened out from the multi-source domain by the maximum mean difference metric; then the source and target domain data are projected to the common subspace by two projection matrices respectively, and the source and target domain samples are weighted, which maintains the neighboring relationship of the samples; at the same time, the marginal and conditional distributions between the two domains are aligned by using the maximum mean difference, and combined with the graph embedding theory and the Fisher's criterion Mining the shared potential fault structure features, and retaining the local flow structure and discriminative information of the data to minimize the domain differences; finally, using label propagation to obtain the predicted labels and judging the fault types through the voting mechanism. Experimental validation is carried out on four sets of rolling bearing datasets, and the proposed method outperforms the traditional method with good generalization performance.

Key words

multisource domain / jointly maintained structural migration / similarity metric / distribution alignment / fault diagnosis

Cite this article

Download Citations
ZHOU Hongdi1, 2, WANG Zhiwen1, TAO Qi1, 2. Rolling bearing fault diagnosis based on the joint structure retention migration in multi-source domains[J]. Journal of Vibration and Shock, 2025, 44(14): 302-310

References

[1] ZHOU Jian-min, YANG Xiao-tong, LI Jia-hui. Deep Residual Network Combined with Transfer Learning Based Fault Diagnosis for Rolling Bearing[J]. APPLIED SCIENCES-BASEL, 2022,12(15).
 [2] 朱朋, 董绍江, 李洋, 等. 基于残差注意力机制和子领域自适应的时变转速下滚动轴承故障诊断[J]. 振动与冲击, 2022,41(22):293-300.
ZHU Peng, DONG Shao-jiang, LI Yang, et al. Fault diagnosis of rolling bearings under time-varying speed based on residual attention mechanism and sub domain adaptation[J]. Vibration and shock , 2022,41(22):293-300.
 [3] 刘海宁, 宋方臻, 窦仁杰, 等. 小数据条件下基于测地流核函数的域自适应故障诊断方法研究[J]. 振动与冲击, 2018,37(18):36-42.
         LIU Haining, SONG Fang-zhen, DOU Ren-jie, et al. Research on domain adaptive fault diagnosis method based on geodesic flow kernel function under small data conditions[J]. Vibration and shock , 2018,37(18):36-42.
 [4] WU Jing-yao, ZHAO Zhi-bin, Sun Chuang, et al. Few-shot transfer learning for intelligent fault diagnosis of machine[J]. MEASUREMENT, 2020,166.
 [5] XING Sai-bo, LEI Y, YANG Bing, et al. Adaptive Knowledge Transfer by Continual Weighted Updating of Filter Kernels for Few-Shot Fault Diagnosis of Machines[J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2022,69(2):1968-1976.
 [6] YANG Bing, Lei Ya-guo, Jia Feng, et al. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings[J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2019,122:692-706.
 [7] LI Xing-qiu, JIANG Hong-kai, Xie Ming, et al. A reinforcement ensemble deep transfer learning network for rolling bearing fault diagnosis with Multi-source domains[J]. ADVANCED ENGINEERING INFORMATICS, 2022,51.
 [8] 杨胜康, 孔宪光, 王奇斌, 等. 基于多源域深度迁移学习的机械故障诊断[J]. 振动与冲击, 2022,41(09):32-40.
YANG Sheng-kang, KONG Xian-guang, WANG Qi-bing, et al. Mechanical Fault Diagnosis Based on Deep Migration Learning in Multiple Source Domains[J]. Vibration and shock , 2022,41(09):32-40.
 [9] CHEN Zhu-yun, LIAO Yi-xiao, LI Ji-pu, et al. A Multi-Source Weighted Deep Transfer Network for Open-Set Fault Diagnosis of Rotary Machinery[J]. IEEE Transactions on Cybernetics, 2023,53(3):1982-1993.
[10] CHEN Xing-kai, SHAO Hai-dong, XIAO Yi-ming, et al. Collaborative fault diagnosis of rotating machinery via dual adversarial guided unsupervised multi-domain adaptation network[J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2023,198.
[11] ZHU Xiaojin. Learning from Labeled and Unlabeled Data with Label Propagation[J]. Tech Report, 2002.
[12] ZHOU Deng-yong, Bousquet O, Lal T N, et al. Learning with Local and Global Consistency[C]// Proceedings of the 17th International Conference on Neural Information Processing Systems.Vancouver:NIPS,2004.
[13] 田青, 孙灿宇, 储奕. 基于自适应权重的多源部分域适应[J]. 软件学报, 2024,35(04):1703-1716.
TIAN Qing, SUN Can-yu, CHU Yi. Multi-source partial domain adaptation based on adaptive weights[J]. Software Journal, 2024,35(04):1703-1716.
[14] YAN Shui-chen, XU Dong, ZHANG Ben-yu, et al. Graph Embedding and Extensions: A General Framework for Dimensionality Reduction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(1):40-51.
[15] LI Hao-ran, MA Zhi-hao, WENG Yang. A Transfer Learning Framework for Power System Event Identification[J]. IEEE TRANSACTIONS ON POWER SYSTEMS, 2022,37(6):4424-4435.
[16] Azarbarzin S, Afsari F. Joint Robust Transfer Metric and Adaptive Transfer Function Learning[J]. NEURAL PROCESSING LETTERS, 2020,51(2):1411-1443.
[17] XU Huo-yao, PENG Xiang-yu, WANG Jun-lang, et al. Adaptive graph -guided joint soft clustering and distribution alignment for cross-load and cross-device rotating machinery fault transfer diagnosis[J]. MEASUREMENT SCIENCE AND TECHNOLOGY, 2024,35(4).
[18] XU Yong, FANG Xiao-zhao, WU Jian, et al. Discriminative Transfer Subspace Learning via Low-Rank and Sparse Representation[J]. IEEE Transactions on Image Processing, 2016,25(2):850-863.
[19] LEI Ya-guo, HE Zheng-jia, ZI Yan-yang, et al. Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs[J]. Mechanical Systems and Signal Processing, 2007,21(5):2280-2294.
[20] DENG Xiao-gang, TIAN Xue-min. Sparse Kernel Locality Preserving Projection and Its Application in Nonlinear Process Fault Detection[J]. CHINESE JOURNAL OF CHEMICAL ENGINEERING, 2013,21(2):163-170.
[21] 唐伯宇, 邵星, 王翠香, 等. 基于双通道CNN与SSA-SVM的滚动轴承故障诊断[J]. 控制理论与应用, 2023.
TANG Bo-yu, SHAO Xing, WANG Cui-xiang, et al. Rolling bearing fault diagnosis based on dual-channel CNN and SSA-SVM[J]. Control Theory and Applications, 2023.
[22] 张龙, 周俊. 多模型融合下的滚动轴承故障诊断方法[J]. 噪声与振动控制, 2022,42(03):132-137.
ZHANG Long, ZHOU Jun. Rolling bearing fault diagnosis method under multi-model fusion[J]. Noise and Vibration Control, 2022,42(03):132-137
[23] ZHENG Zhong, WANG Jin-fei, SHAN Bo, et al. A New Model for Transfer Learning-Based Mapping of Burn Severity[J]. REMOTE SENSING, 2020,12(4).
[24] Wumaier T, XU Chang, GUO Hong-yu, et al. Fault Diagnosis of Wind Turbines Based on a Support Vector Machine Optimized by the Sparrow Search Algorithm[J]. IEEE Access, 2021,9:69307-69315.
[25] JIAN Bo-lin, SU Xiao-yi, Yau Her-terng. Bearing Fault Diagnosis Based on Chaotic Dynamic Errors in Key Components[J]. IEEE ACCESS, 2021,9:53509-53517.
[26] ZHANG Zhong-wei, CHEN Huai-hai, LI Shun-ming, et al. A novel geodesic flow kernel based domain adaptation approach for intelligent fault diagnosis under varying working condition[J]. Neurocomputing,2020,376:54-64.
[27] ZHENG Huai-liang, WANG Ri-xin, YIN Jian-chen, et al. A new intelligent fault identification method based on transfer locality preserving projection for actual diagnosis scenario of rotating machinery[J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2020,135.
[28] ZHAO Zhi-bin, ZHANG Qi-yang, YU Xiao-lei, et al. Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study[J]. IEEE Transactions on Instrumentation and Measurement, 2021,70:1-28.
[29] 王姗姗, 汪梦竹, 骆志刚. 局部判别损失无监督域适应方法[J]. 计算机工程与科学, 2024,46(01):132-141.
WANG Shan-shan, WANG Meng-zhu, LUO Zhi-gang. A focally discriminative loss for unsupervised domain adaptation method[J]. COMPUTER ENGINEERING & SCIENCE, 2024,46(01):132-141.
[30] YANG Lei-lei, CHEN Song-can. Linear discriminant analysis with worst between-class separation and average within-class compactness[J]. FRONTIERS OF COMPUTER SCIENCE, 2014,8(5):785-792.
[31] YANG Wan-kou, YAN Xiao-yong, ZHANG Lei, et al. Feature extraction based on fuzzy 2DLDA[J]. NEUROCOMPUTING, 2010,73(10-12):1556-1561.
[32] Smith W A, Randall R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study[J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2015,64-65:100-131.
[33] Randall R B, Antoni J. Rolling element bearing diagnostics-A tutorial[J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2011,25(2):485-520.
[34] LI Ke, PING Xue-liang, WANG Hua-qing, et al. Sequential Fuzzy Diagnosis Method for Motor Roller Bearing in Variable Operating Conditions Based on Vibration Analysis[J]. sensors, 2013.
PDF(1662 KB)

99

Accesses

0

Citation

Detail

Sections
Recommended

/