A knowledge dynamic matching unit-guided multi-source domain adaptation network with attention mechanism for rolling bearing fault diagnosis

被引:46
|
作者
Wu, Zhenghong [1 ]
Jiang, Hongkai [1 ]
Zhu, Hongxuan [1 ]
Wang, Xin [1 ]
机构
[1] Northwestern Polytech Univ, Sch Civil Aviat, Xian 710072, Peoples R China
基金
中国国家自然科学基金;
关键词
Multi -source domain adaptation; Knowledge dynamic matching unit; Attention mechanism; Bearing fault diagnosis; ALGORITHM;
D O I
10.1016/j.ymssp.2023.110098
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Most current research on multi-source domain adaptation in bearing fault diagnosis focuses on training domain-agnostic networks whose parameters are static. However, it is challenging for static networks to address conflicts across multiple domains when there are domain discrepancies not only between source and target domains, but also between different source domains. Thus, this paper develops a knowledge dynamic matching unit-guided multi-source domain adaptation network with attention mechanism (KDMUMDAN) for bearing fault diagnosis, whose model parameters can dynamically adapt to input samples. KDMUMDAN consists of two modules: a feature extractor with the knowledge dynamic matching unit (KDMU) and two classifiers with attention mechanism. The feature extractor with KDMU is capable of dynamically adjusting the model parameters according to the distribution of input samples to obtain better feature representations, which can effectively facilitate the alignment of source and target domain distributions since it only needs to align the target domain with any part of the set of multi-source domains. Moreover, an attention mechanism is embedded into two classifiers to boost the impact of the more relevant source domain, which can leverage fully the knowledge in multi-source domains to promote data distribution alignment. Experimental results verify that KDMUMDAN has superior bearing fault diagnosis ability across multiple domains.
引用
收藏
页数:19
相关论文
共 50 条
  • [31] Class-Aware Multi-Source Domain Adaptation for Imbalanced Fault Diagnosis
    Gao, Huihui
    Xue, Zihan
    Han, Honggui
    Li, Fangyu
    2024 14TH ASIAN CONTROL CONFERENCE, ASCC 2024, 2024, : 1530 - 1535
  • [32] A multi-source ensemble domain adaptation method for rotary machine fault diagnosis
    Yang, Shengkang
    Kong, Xianguang
    Wang, Qibin
    Li, Zhongquan
    Cheng, Han
    Yu, Linyang
    MEASUREMENT, 2021, 186
  • [33] Research on rolling bearing fault diagnosis method based on improved multi-source fusion convolutional neural network
    Shi, Huaitao
    Sun, Huayang
    Bai, Xiaotian
    Song, Zelong
    Gao, Tianhao
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2025, 36 (01)
  • [34] A Gaussian-guided adversarial adaptation transfer network for rolling bearing fault diagnosis
    Wu, Zhenghong
    Jiang, Hongkai
    Liu, Shaowei
    Yang, Chunxia
    ADVANCED ENGINEERING INFORMATICS, 2022, 53
  • [35] A novel approach of fault diagnosis based on multi-source signals and attention mechanism
    Guan, Liuen
    Zhai, Xiaodong
    Tu, Xuan
    Qiao, Fei
    2021 IEEE 17TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), 2021, : 1213 - 1218
  • [36] Multi-Scale CNN based on Attention Mechanism for Rolling Bearing Fault Diagnosis
    Hao, Yijia
    Wang, Huan
    Liu, Zhiliang
    Han, Haoran
    2020 ASIA-PACIFIC INTERNATIONAL SYMPOSIUM ON ADVANCED RELIABILITY AND MAINTENANCE MODELING (APARM), 2020,
  • [37] Multi-source information deep fusion for rolling bearing fault diagnosis based on deep residual convolution neural network
    Wang, HongChao
    Du, WenLiao
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE, 2022, 236 (13) : 7576 - 7589
  • [38] A centroid contrastive multi-source domain adaptation method for fault diagnosis with category shift
    Li, Yufeng
    Xu, Xinghan
    Hu, Lei
    Sun, Kai
    Han, Min
    MEASUREMENT, 2025, 248
  • [39] Rolling bearing fault diagnosis based on multi⁃scale mixed domain feature extraction and domain adaptation
    Lei Z.
    Wen G.
    Zhou Q.
    Dong S.
    Huang X.
    Zhou H.
    Zhendong Ceshi Yu Zhenduan/Journal of Vibration, Measurement and Diagnosis, 2022, 42 (01): : 182 - 189
  • [40] Multi-source rolling bearing fault diagnosis under variable working conditions based on GCN
    Xie F.
    Wang L.
    Song M.
    Fan Q.
    Sun E.
    Zhu H.
    Journal of Railway Science and Engineering, 2024, 21 (05) : 2109 - 2118