期刊
RELIABILITY ENGINEERING & SYSTEM SAFETY
卷 231, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.ress.2022.109036
关键词
Fault diagnosis; Rotating machinery; Multi-source domain adaptation; Self-attention mechanism; Discrepancy matching technique
This paper proposes a deep multi-source adversarial discrepancy matching adaptation network (MADMAN) to enhance the accuracy of cross-domain intelligent diagnosis. The proposed method utilizes the generalization knowledge learned from multiple domains to diagnose unknown tasks and adaptively adjusts the weight factors of multiple source domains using a self-attention mechanism. It also applies discrepancy matching technique to dynamically align the feature distributions of different domains and incorporates an adversarial classifier training method to improve transferability by considering task-specific decision boundaries. Extensive experiments using two bearing datasets demonstrate the superiority of the proposed approach compared to advanced methods.
In the health management of modern rotating machinery, domain adaptation is an effective method to solve the diagnostic problems of insufficient labeled signals and poor generalization performance. In engineering sce-narios, obtaining signals from various source domains can ensure abundant feature information and contribute to diagnostic ability improvement compared with learning from a single source domain. This paper presents a deep multi-source adversarial discrepancy matching adaptation network (MADMAN) for enhancing the accuracy of cross-domain intelligent diagnosis. Firstly, the proposed method makes use of the generalization knowledge learned from multiple domains to diagnose the unknown task, and adaptively adjusts the weight factors of multiple source domains utilizing the self-attention mechanism. Secondly, to better alleviate the domain shift phenomenon between different domains, the discrepancy matching technique is applied to dynamically align the feature distributions of different domains. Thirdly, an adversarial classifier training method is incorporated to raise the transferability by considering the decision boundary of specific tasks. The proposed method is verified by extensive experiments using two bearing datasets, and the superiority of the presented approach is demon-strated by comparison with advanced methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据