期刊
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
卷 68, 期 5, 页码 4351-4361出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIE.2020.2984968
关键词
Fault diagnosis; Machinery; Training; Testing; Adaptation models; Feature extraction; Training data; Deep learning; fault diagnosis; partial domain adaptation; rotating machines; transfer learning
资金
- Fundamental Research Funds for the Central Universities [N2005010, N180703018, N180708009, N170308028]
- National Natural Science Foundation of China [11902202]
- Key Laboratory of Vibration and Control of Aero-Propulsion System Ministry of Education, Northeastern University [VCAME201906]
- Liaoning Provincial Department of Science and Technology [2019-BS-184]
This article proposes a deep learning-based fault diagnosis method to address the partial domain adaptation problems, where the unsupervised target-domain training data do not cover the full machine health state label space. Conditional data alignment and unsupervised prediction consistency schemes are proposed to achieve partial domain adaptation.
In the past years, deep learning-based machinery fault diagnosis methods have been successfully developed, and the basic diagnostic problems have been well addressed where the training and testing data are collected under the same operating conditions. When the training and testing data are from different distributions, domain adaptation approaches have been introduced. However, the existing methods generally assume the availability of the target-domain data in all the health conditions during training, which is not in accordance with the real industrial scenarios. This article proposes a deep learning-based fault diagnosis method to address the partial domain adaptation problems, where the unsupervised target-domain training data do not cover the full machine health state label space. The conditional data alignment and unsupervised prediction consistency schemes are proposed to achieve partial domain adaptation. The experimental results on two rotating machinery datasets suggest the proposed method offers a promising tool for this practical industrial problem.
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