期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 17, 期 3, 页码 1753-1762出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.2994621
关键词
Fault diagnosis; Task analysis; Training; Feature extraction; Machinery; Hidden Markov models; Informatics; Adversarial network; domain adaptation (DA); fault diagnosis; partial domain; transfer learning (TL)
类别
资金
- National Key R&D Program of China [2018YFB1702400]
- National Natural Science Foundation of China [51875208, 51705156, 51475170]
A novel weighted adversarial transfer network (WATN) is proposed for partial domain fault diagnosis, which reduces the distribution discrepancy of shared classes between domains and identifies and filters out irrelevant source examples by introducing adversarial training and a weighting learning strategy. Experiments show that WATN achieves satisfactory performance and outperforms state-of-the-art methods on two diagnosis data sets.
Recently, domain adaptation techniques have achieved great attention in solving domain-shift problems of mechanical fault diagnosis. However, existing methods mostly work under assumption that source domain and target domain share identical label spaces, which fail to handle those issues, where a large set of source data classes are available and target data only cover a subset of classes. To address this problem, a novel weighted adversarial transfer network (WATN) is proposed for partial domain fault diagnosis, in this article. Adversarial training is introduced to learn both class discriminative and domain invariant features, and a weighting learning strategy is adopted to weigh their contributions to both source classifier and domain discriminator. As such, the irrelevant source examples can be identified and filtered out, and the distribution discrepancy of shared classes between domains can be reduced. Experiments on two diagnosis data sets demonstrate that the proposed WATN achieves satisfactory performance and outperforms state-of-the-art 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