TY - JOUR
T1 - IF-EDAAN
T2 - An information fusion-enhanced domain adaptation attention network for unsupervised transfer fault diagnosis
AU - Lin, Cuiying
AU - Kong, Yun
AU - Han, Qinkai
AU - Chen, Ke
AU - Geng, Zhibo
AU - Wang, Tianyang
AU - Dong, Mingming
AU - Liu, Hui
AU - Chu, Fulei
N1 - Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2025/2/1
Y1 - 2025/2/1
N2 - Unlike domain adaptation methods that rely on single-source information for transfer diagnosis, multi-source information-based domain adaptation methods can leverage the extensive diagnostic features derived from multiple sources of data. However, the issues of potential feature conflicts, the critical fault information loss, and high computational burdens still hinder effective applications of multi-source information domain adaptation for transfer diagnosis. For resolving these issues, this study proposes an unsupervised multi-source information domain adaptation approach for transfer fault diagnosis, which utilizes an information fusion-enhanced domain adaptation attention network (IF-EDAAN). Firstly, an information fusion method that converts multi-source information into a fused image using principal component analysis and signal-to-image conversion is employed to enhance and compress data from both the source and target domains. Then, a parameter-free attention mechanism (PFAM) module is proposed to adaptively focus on the domain-invariant temporal and spatial features of information fusion samples. Subsequently, the weight assignment module and joint maximum mean discrepancy metric strategy are proposed to mitigate negative transfer, thus enabling the effective extraction and alignment of domain-invariant temporal and spatial features. Finally, experiment validations on two rotating machinery datasets have been comprehensively elaborated to verify the efficacy and advantages of our proposed IF-EDAAN approach for transfer fault diagnosis across different working conditions. Experiment results have proved that our proposed IF-EDAAN approach can rapidly adapt to new transfer diagnostic scenarios with impressive performance and outperform several mainstream unsupervised domain adaptation approaches.
AB - Unlike domain adaptation methods that rely on single-source information for transfer diagnosis, multi-source information-based domain adaptation methods can leverage the extensive diagnostic features derived from multiple sources of data. However, the issues of potential feature conflicts, the critical fault information loss, and high computational burdens still hinder effective applications of multi-source information domain adaptation for transfer diagnosis. For resolving these issues, this study proposes an unsupervised multi-source information domain adaptation approach for transfer fault diagnosis, which utilizes an information fusion-enhanced domain adaptation attention network (IF-EDAAN). Firstly, an information fusion method that converts multi-source information into a fused image using principal component analysis and signal-to-image conversion is employed to enhance and compress data from both the source and target domains. Then, a parameter-free attention mechanism (PFAM) module is proposed to adaptively focus on the domain-invariant temporal and spatial features of information fusion samples. Subsequently, the weight assignment module and joint maximum mean discrepancy metric strategy are proposed to mitigate negative transfer, thus enabling the effective extraction and alignment of domain-invariant temporal and spatial features. Finally, experiment validations on two rotating machinery datasets have been comprehensively elaborated to verify the efficacy and advantages of our proposed IF-EDAAN approach for transfer fault diagnosis across different working conditions. Experiment results have proved that our proposed IF-EDAAN approach can rapidly adapt to new transfer diagnostic scenarios with impressive performance and outperform several mainstream unsupervised domain adaptation approaches.
KW - Fault diagnosis
KW - Multi-source information fusion
KW - Transfer learning
KW - Unsupervised domain adaptation
UR - http://www.scopus.com/inward/record.url?scp=85210137168&partnerID=8YFLogxK
U2 - 10.1016/j.ymssp.2024.112180
DO - 10.1016/j.ymssp.2024.112180
M3 - Article
AN - SCOPUS:85210137168
SN - 0888-3270
VL - 224
JO - Mechanical Systems and Signal Processing
JF - Mechanical Systems and Signal Processing
M1 - 112180
ER -