Mechanical Cross-Domain Diagnosis Method Based on Multi-source Weighted Domain Adaptation

  • Jie Zhang
  • , Ke Chen
  • , Kangkang Zhao
  • , Yufan Lv
  • , Chuntao Zhang
  • , Yun Kong*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Source-target domains with large distributional differences may lead to the performance attenuation of multi-source domain adaptation, which in turn affects the accuracy of intelligent transfer fault diagnosis. To address this issue, this paper proposes a mechanical cross-domain diagnosis method based on multi-source weighted domain adaptation. First, a multi-source domain weighting method based on orthogonal bases in principal component space is proposed to assign weights to different source domains by measuring the similarity of each pair of source-target domains in order to guide the domain adaptation process and favor the high-weighted source domains. Then, a multi-attention network is designed to enhance the domain-invariant representation of critical fault features by fusing multi-level features. Finally, the health state identification on the target domain is realized by the trained feature extractor and classifier. Validations are performed on planetary gearbox datasets, and experimental results show that the proposed method exhibits superior domain adaptation and cross-domain diagnosis performance over other methods, obtaining the highest diagnosis accuracies of 98.48%.

Original languageEnglish
Title of host publicationProceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences, UNIfied 2025 - Volume 1
EditorsKexiang Wei, Wenxian Yang, Bingyan Chen, Juchuan Dai
PublisherSpringer Science and Business Media B.V.
Pages761-774
Number of pages14
ISBN (Print)9783032009678
DOIs
Publication statusPublished - 2026
EventUNIfied Conference of International Conference on Damage Assessment of Structures, DAMAS 2025, International Conference on Maintenance Engineering, IncoME 2025 and The Efficiency and Performance Engineering, TEPEN 2025 - Zhangjiajie, China
Duration: 16 May 202519 May 2025

Publication series

NameMechanisms and Machine Science
Volume188
ISSN (Print)2211-0984
ISSN (Electronic)2211-0992

Conference

ConferenceUNIfied Conference of International Conference on Damage Assessment of Structures, DAMAS 2025, International Conference on Maintenance Engineering, IncoME 2025 and The Efficiency and Performance Engineering, TEPEN 2025
Country/TerritoryChina
CityZhangjiajie
Period16/05/2519/05/25

Keywords

  • Attention mechanism
  • Fault diagnosis
  • Multi-source domain adaptation
  • Source domain weighted

Fingerprint

Dive into the research topics of 'Mechanical Cross-Domain Diagnosis Method Based on Multi-source Weighted Domain Adaptation'. Together they form a unique fingerprint.

Cite this