期刊
IEEE ACCESS
卷 8, 期 -, 页码 134246-134256出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.3006491
关键词
Convolutional neural network; vibration signal; explainable AI; fault diagnosis
资金
- Ministry of Science and Technology, Taiwan [MOST-109-2634-F-005-004, 108-2634-F-005-001, 107-2634-F-005-001, 108-2218-E-150-004, 106-2221-E-005-010-MY3]
This study introduces an explainable artificial intelligence (XAI) approach of convolutional neural networks (CNNs) for classification in vibration signals analysis. First, vibration signals are transformed into images by short-time Fourier transform (STFT). A CNN is applied as classification model, and Gradient class activation mapping (Grad-CAM) is utilized to generate the attention of model. By analyzing the attentions, the explanation of classification models for vibration signals analysis can be carried out. Finally, the verifications of attention are introduced by neural networks, adaptive network-based fuzzy inference system (ANFIS), and decision trees to demonstrate the proposed results. By the proposed methodology, the explanation of model using highlighted attentions is carried out.
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