期刊
IEEE-ASME TRANSACTIONS ON MECHATRONICS
卷 25, 期 3, 页码 1243-1254出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMECH.2020.2971503
关键词
Convolutional neural networks (CNNs); Hilbert-Huang transform (HHT); remaining useful life (RUL) estimation; rolling bearings
类别
资金
- National Natural Science Foundation of China [91748112]
- Primary Research and Development Plan of Jiangsu Province [BE2017002]
In industrial applications, nearly half the failures of motors are caused by the degradation of rolling element bearings (REBs). Therefore, accurately estimating the remaining useful life (RUL) for REBs is of crucial importance to ensure the reliability and safety of mechanical systems. To tackle this challenge, model-based approaches are limited by the complexity of mathematical modeling. Conventional data-driven approaches, on the other hand, require massive efforts to extract the degradation features and construct the health index. In this article, a novel data-driven framework is proposed to exploit the adoption of deep convolutional neural networks (CNNs) in predicting the RULs of bearings. More concretely, raw vibrations of training bearings are first processed using the Hilbert-Huang transform to construct a novel nonlinear degradation energy indicator which can be used as the training label. The CNN is then employed to identify the hidden pattern between the extracted degradation energy indicator and the raw vibrations of training bearings, which makes it possible to estimate the degradation of the test bearings automatically. Finally, testing bearings' RULs are predicted through using an epsilon-support vector regression model. The superior performance of the proposed RUL estimation framework, compared with the state-of-the-art approaches, is demonstrated through the experimental results. The generality of the proposed CNN model is also validated by performance test on other bearings undergoing different operating conditions.
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