期刊
APPLIED SCIENCES-BASEL
卷 12, 期 15, 页码 -出版社
MDPI
DOI: 10.3390/app12157450
关键词
transfer learning; wavelet; limited data; fault detection; fault diagnosis; machinery fault
类别
资金
- Chungnam National University
This paper proposes a method that combines wavelet transformation and transfer learning for fault diagnosis with limited samples. The results show that the proposed method provides higher diagnostic accuracy under wide variations in the training data size and the fault severity.
Although various deep learning techniques have been proposed to diagnose industrial faults, it is still challenging to obtain sufficient training samples to build the fault diagnosis model in practice. This paper presents a framework that combines wavelet transformation and transfer learning (TL) for fault diagnosis with limited target samples. The wavelet transform converts a time-series sample to a time-frequency representative image based on the extracted hidden time and frequency features of various faults. On the other hand, the TL technique leverages the existing neural networks, called GoogLeNet, which were trained using a sufficient source data set for different target tasks. Since the data distributions between the source and the target domains are considerably different in industrial practice, we partially retrain the pre-trained model of the source domain using intermediate samples that are conceptually related to the target domain. We use a reciprocating pump model to generate various combinations of faults with different severity levels and evaluate the effectiveness of the proposed method. The results show that the proposed method provides higher diagnostic accuracy than the support vector machine and the convolutional neural network under wide variations in the training data size and the fault severity. In particular, we show that the severity level of the fault condition heavily affects the diagnostic performance.
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