期刊
SIGNAL PROCESSING
卷 161, 期 -, 页码 136-154出版社
ELSEVIER
DOI: 10.1016/j.sigpro.2019.03.019
关键词
Rolling element bearing; Fault diagnosis; Deep learning; Envelope spectrum; Attention mechanism
资金
- Fundamental Research Funds for the Central Universities [N170503012, N170308028, N180708009]
- National Natural Science Foundation of China [61871107]
In the recent years, deep learning-based intelligent fault diagnosis methods of rolling bearings have been widely and successfully developed. However, the data-driven method generally remains a black box to researchers and there is a gap between the emerging neural network-based methods and the well-established traditional fault diagnosis knowledge. This paper proposes a novel deep learning-based fault diagnosis method for rolling element bearings. Attention mechanism is introduced to assist the deep network to locate the informative data segments, extract the discriminative features of inputs, and visualize the learned diagnosis knowledge. Experiments on a popular rolling bearing dataset intuitively show the effectiveness of the proposed method, which is able to provide reliable diagnosis even with very few training data. The experimental results suggest this research offers a promising tool for intelligent fault diagnosis and provides effort in understanding the underlying mechanism of deep neural network. (C) 2019 Elsevier B.V. All rights reserved.
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