A lightweight and robust model for engineering cross-domain fault diagnosis via feature fusion-based unsupervised adversarial learning. (December 2022)

• Record Type: Journal Article
• Authors: Chen, Qitong; Chen, Liang; Li, Qi; Shi, Juanjuan; Zhu, Zhongkui; Shen, Changqing
• Is Part Of: Measurement. Volume 205(2023)
• Publication Date: 2022-12
• Subjects: Lightweight and robust -- Feature fusion -- Adversarial learning -- Channel residual; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2022.112139
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: Targeted for engineering application, a lightweight and robust model of cross-domain fault diagnosis is proposed. A customized feature fusion block is designed to make the model more lightweight. A channel residual strategy is proposed to enhance the robustness of the model. A new unsupervised learning strategy for adversarial domain adaptation is proposed to improve the convergence speed and generalization performance of the model. Abstract: Cross-domain bearing fault diagnosis models have weaknesses such as large size, complex calculation and weak anti-noise ability. Hence, a lightweight and robust model via feature fusion-based unsupervised adversarial learning (LRFFUAL) is proposed, which could be a special benefit for practical engineering applications. A main innovation lies in a customized feature fusion block to achieve a tradeoff between model lightweight and robustness. Accordingly, a channel residual strategy is proposed to apply residual techniques for channels with weak feature information to achieve data augmentation. Concerning cross-domain tasks with huge distribution discrepancy, a new adversarial learning strategy is proposed to improve model convergence rate by inputting marginal features into a discriminator. Experimental results show that the proposed LRFFUAL has advantages of smaller size, less computation, and stronger robustness compared with other existing methods.