期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 17, 期 8, 页码 5239-5249出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3032690
关键词
Feature extraction; Employee welfare; Informatics; Deep learning; Prognostics and health management; Task analysis; Adaptation models; Domain adaptation; deep learning; remaining useful life (RUL); transfer learning
类别
资金
- A*STAR Industrial Internet of Things Research Program under the RIE2020 IAF-PP [A1788a0023]
- National Natural Science Foundation of China [51835009]
- A*STAR SINGA Scholarship
This article introduces a novel contrastive adversarial domain adaptation (CADA) method for cross-domain RUL prediction, which combines adversarial domain adaptation architecture with contrastive loss to effectively consider target-specific information.
Enabling precise forecasting of the remaining useful life (RUL) for machines can reduce maintenance cost, increase availability, and prevent catastrophic consequences. Data-driven RUL prediction methods have already achieved acclaimed performance. However, they usually assume that the training and testing data are collected from the same condition (same distribution or domain), which is generally not valid in real industry. Conventional approaches to address domain shift problems attempt to derive domain-invariant features, but fail to consider target-specific information, leading to limited performance. To tackle this issue, in this article, we propose a contrastive adversarial domain adaptation (CADA) method for cross-domain RUL prediction. The proposed CADA approach is built upon an adversarial domain adaptation architecture with a contrastive loss, such that it is able to take target-specific information into consideration when learning domain-invariant features. To validate the superiority of the proposed approach, comprehensive experiments have been conducted to predict the RULs of aeroengines across 12 cross-domain scenarios. The experimental results show that the proposed method significantly outperforms state-of-the-arts with over 21% and 38% improvements in terms of two different evaluation metrics.
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