Cross-Domain Bilateral Transfer Learning for Fault Diagnosis Under Incomplete Multisource Domains

被引:0
|
作者
Zhang, Shumei [1 ]
Wang, Sijia [2 ]
Lei, Qi [2 ]
Zhao, Chunhui [3 ]
机构
[1] Tianjin Univ, Sch Elect & Informat Engn, Tianjin Key Lab Proc Measurement & Control, Tianjin 300072, Peoples R China
[2] Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China
[3] Zhejiang Univ, Coll Control Sci & Engn, State Key Lab Ind Control Technol, Hangzhou 310027, Peoples R China
基金
中国国家自然科学基金;
关键词
Fault diagnosis; Transfer learning; Silicon; Process control; Knowledge transfer; Trajectory; Principal component analysis; incomplete multisource; bilateral transfer; fault diagnosis; ADAPTATION;
D O I
10.1109/TASE.2024.3409621
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recently, transfer learning (TL) approaches have been extensively applied in industrial cross-domain fault diagnosis, most of which depend on the consistency assumption of the source and target fault categories. In practice, it is common to utilize multiple source domains for transfer learning, but each of them may not include all fault categories in the target domain, which are referred to as incomplete multisource domains. For the challenge of fault diagnosis under incomplete multisource domains, a cross-domain bilateral transfer learning (CDBTL) method is proposed in this article. First, a cross-domain bilateral transfer strategy is developed, where the source and target domains are reconstructed from each other and their distribution differences are reduced by minimizing the reconstruction error to avoid negative transfer. Then, for the source domain with label information, CDBTL maximizes the between-class distance of different fault categories and minimizes the within-class distance of the same fault category to ensure the discriminative nature of its feature representation. Afterwards, the common projection matrix is learned through the mutual cooperation of projection matrices between different incomplete source domains and target domain to compensate for the missing fault categories in a single source domain. The key to discriminate CDBTL from many exiting TL algorithms is that it relaxes the restriction of consistent fault categories in the source and target domains, and skillfully integrates the knowledge of multiple incomplete source domains. Extensive experiments on Tennessee Eastman process demonstrate the superiority of CDBTL in solving cross-domain fault diagnosis problem, whose accuracy is averagely improved by 17.99% compared with eleven existing algorithms.
引用
收藏
页码:1 / 13
页数:13
相关论文
共 50 条
  • [31] Curriculum learning-based domain generalization for cross-domain fault diagnosis with category shift
    Wang, Yu
    Gao, Jie
    Wang, Wei
    Yang, Xu
    Du, Jinsong
    MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2024, 212
  • [32] On Generalizing Beyond Domains in Cross-Domain Continual Learning
    Simon, Christian
    Faraki, Masoud
    Tsai, Yi-Hsuan
    Yu, Xiang
    Schulter, Samuel
    Suh, Yumin
    Harandi, Mehrtash
    Chandraker, Manmohan
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 9255 - 9264
  • [33] Deep learning-based cross-domain adaptation for gearbox fault diagnosis under variable speed conditions
    Singh, Jaskaran
    Azamfar, Moslem
    Ainapure, Abhijeet
    Lee, Jay
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2020, 31 (05)
  • [34] Multi-Domain Weighted Transfer Adversarial Network for the Cross-Domain Intelligent Fault Diagnosis of Bearings
    Wang, Yuanfei
    Li, Shihao
    Jia, Feng
    Shen, Jianjun
    MACHINES, 2022, 10 (05)
  • [35] Cross-Domain Kernel Induction for Transfer Learning
    Chang, Wei-Cheng
    Wu, Yuexin
    Liu, Hanxiao
    Yang, Yiming
    THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 1763 - 1769
  • [36] Transfer learning in cross-domain sequential recommendation
    Xu, Zitao
    Pan, Weike
    Ming, Zhong
    INFORMATION SCIENCES, 2024, 669
  • [37] TLRec: Transfer Learning for Cross-domain Recommendation
    Chen, Leihui
    Zheng, Jianbing
    Gao, Ming
    Zhou, Aoying
    Zeng, Wei
    Chen, Hui
    2017 IEEE INTERNATIONAL CONFERENCE ON BIG KNOWLEDGE (IEEE ICBK 2017), 2017, : 167 - 172
  • [38] Boosted Multifeature Learning for Cross-Domain Transfer
    Yang, Xiaoshan
    Zhang, Tianzhu
    Xu, Changsheng
    Yang, Ming-Hsuan
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2015, 11 (03)
  • [39] Multisource-Refined Transfer Network for Industrial Fault Diagnosis Under Domain and Category Inconsistencies
    Chai, Zheng
    Zhao, Chunhui
    Huang, Biao
    IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (09) : 9784 - 9796
  • [40] Self-supervised domain adaptation for cross-domain fault diagnosis
    Lu, Weikai
    Fan, Haoyi
    Zeng, Kun
    Li, Zuoyong
    Chen, Jian
    INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2022, 37 (12) : 10903 - 10923