A multi-source ensemble domain adaptation method for rotary machine fault diagnosis. (December 2021)

• Record Type: Journal Article
• Authors: Yang, Shengkang; Kong, Xianguang; Wang, Qibin; Li, Zhongquan; Cheng, Han; Yu, Linyang
• Is Part Of: Measurement. Volume 186(2021)
• Publication Date: 2021-12
• Subjects: Rotary machine -- Fault diagnosis -- Multi-source domain -- Transfer learning -- Domain adaptation; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2021.110213
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: A multi-source ensemble domain adaptation method is proposed for fault diagnosis. The method considers mutual distribution difference among multi-source domain. The method can extract domain invariant and discriminant fault feature. The method shows significant diagnosis performance and robustness. Abstract: Transfer learning has good ability to transfer knowledge for fault diagnosis under different working condition, while domain mismatches or domain shift can still occur during single-source domain transfer fault diagnosis. To alleviate the problem, a multi-source ensemble domain adaptation method is proposed for rotary machinery fault diagnosis. Firstly, multi-source and target domain anchor adapters are constructed based on class-central samples from multi-source domain. Secondly, multi-source ensemble domain adaptation transfer fault diagnosis model considering the mutual difference between multi-source domain is established to obtain multiple classifiers and prediction results. Then the classifiers with good performance are integrated to achieve final diagnosis model and results by ensemble of anchor adapters. Finally, the performance of the proposed method is verified by two experiments. The results show that the proposed method has ability to learn more comprehensive and general domain invariant diagnosis knowledge, significant diagnosis performance and robustness than other transfer learning methods.