期刊
SHOCK AND VIBRATION
卷 2021, 期 -, 页码 -出版社
HINDAWI LTD
DOI: 10.1155/2021/6616861
关键词
-
资金
- National Natural Science Foundation of China [51505277, 51875375]
- Suzhou Prospective Research Program [SYG201802]
The convolutional neural network has shown achievements in RUL prediction, while the multiscale convolutional neural network can extract features from different receptive fields, leading to higher prediction accuracy.
Remaining useful life (RUL) prediction is necessary for guaranteeing machinery's safe operation. Among deep learning architectures, convolutional neural network (CNN) has shown achievements in RUL prediction because of its strong ability in representation learning. Features from different receptive fields extracted by different sizes of convolution kernels can provide complete information for prognosis. The single size convolution kernel in traditional CNN is difficult to learn comprehensive information from complex signals. Besides, the ability to learn local and global features synchronously is limited to conventional CNN. Thus, a multiscale convolutional neural network (MS-CNN) is introduced to overcome these aforementioned problems. Convolution filters with different dilation rates are integrated to form a dilated convolution block, which can learn features in different receptive fields. Then, several stacked integrated dilated convolution blocks in different depths are concatenated to extract local and global features. The effectiveness of the proposed method is verified by a bearing dataset prepared from the PRONOSTIA platform. The results turn out that the proposed MS-CNN has higher prediction accuracy than many other deep learning-based RUL methods.
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