期刊
MEASUREMENT
卷 176, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.measurement.2021.109201
关键词
Remaining useful life prediction; Online transfer learning; Representations alignment; Rolling element bearing; Different operating condition
资金
- National Natural Science Foundation of China [51805077]
- Natural Science Foundation of Liaoning Province, China [2019-MS-118]
- Fundamental Research Funds for the Central Universities of China [N2024002/17]
A study proposes an online transfer learning method to accurately predict the remaining useful life of specified bearings by establishing a deep learning model and fine-tuning parameters using unlabeled data. The effectiveness and superiority of the proposed method are verified in transfer prognostics tasks of bearings through case studies.
In recent years, many artificial intelligence-based approaches are proposed for remaining useful life (RUL) prediction of bearings. However, most existing studies neglected the following problems: (1) Run-to-failure data of bearings of are generally less available; (2) Degradation trends of bearings under different working conditions are diverse; (3) Unlabeled data of bearings acquired in the online stage have not been taken into account. To solve these problems mentioned above, an online transfer learning method is proposed. In the offline stage, a deep learning model is established through semi-supervised training to align feature spaces of representations from different domains. Then, in the online stage, unlabeled data from target domain are utilized to fine-tune parameters of the established model. Finally, RUL of specified bearings can be estimated precisely by the established model. The effectiveness and superiority of the proposed method in transfer prognostics tasks of bearings are verified by case studies.
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