期刊
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
卷 189, 期 -, 页码 -出版社
ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
DOI: 10.1016/j.ymssp.2022.110074
关键词
Fault diagnosis; Semisupervised domain generalization; Rotating machines; Deep learning
This study proposes a semi-supervised domain generalization fault diagnosis (Sem-iDGFD) method, which assigns reliable pseudo labels to unlabeled data with knowledge assistance from labeled data. An entropy-based sample purification mechanism is designed to improve the quality of the pseudo-labeled samples. Experimental results demonstrate that the proposed method achieves higher precision than other common SemiDGFD methods and comparable performance with up-to-date fully-labeled DGFD methods.
Generalizing deep models to unseen working conditions is an essential topic for intelligent fault diagnosis. Existing domain generalization-based fault diagnosis (DGFD) methods usually require sufficient annotated samples from all observed domains during the training phase, while anno-tating abundant samples is an expensive and difficult task. Therefore, this study proposes a mutual-assistance network for semisupervised domain generalization fault diagnosis (Sem-iDGFD), where only one source domain is labeled along with several unlabeled source domains. Reliable pseudo labels are assigned to unlabeled data with knowledge assistance from labeled data. Then, an entropy-based sample purification mechanism is designed to improve the quality of pseudo-labeled samples. Finally, pseudo-labeled samples cooperate with real-labeled samples to serve as the input of a low-rank decomposition, which discovers domain invariance against domain shift. Extensive diagnostic experiments demonstrate that the proposed method can obtain higher precision than other popular SemiDGFD methods and achieve comparable performance with up-to-date fully-labeled DGFD 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