期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 16, 期 7, 页码 4681-4690出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2019.2943898
关键词
Convolution; Fault diagnosis; Vibrations; Kernel; Deep learning; Rotating machines; Neural networks; Deep learning; deep residual networks; fault diagnosis; soft thresholding; vibration signal
类别
资金
- Key National Natural Science Foundation of China [U1533202, TII-19-3183]
This article develops new deep learning methods, namely, deep residual shrinkage networks, to improve the feature learning ability from highly noised vibration signals and achieve a high fault diagnosing accuracy. Soft thresholding is inserted as nonlinear transformation layers into the deep architectures to eliminate unimportant features. Moreover, considering that it is generally challenging to set proper values for the thresholds, the developed deep residual shrinkage networks integrate a few specialized neural networks as trainable modules to automatically determine the thresholds, so that professional expertise on signal processing is not required. The efficacy of the developed methods is validated through experiments with various types of noise.
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