Intelligent Fault Diagnosis of Rotating Machinery Based on Visual‐Optimized Convolutional Neural Network

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Rotating machinery is an important part of mechanical system. Effective fault diagnosis of rotating machinery is of great significance to the whole operation and maintenance of mechanical system. The effectiveness of fault diagnosis for rotating machinery is the comprehensive embodiment of the accuracy of diagnosis results and the reliability of diagnosis methods. Since the 21 st century, in the field of rotating machinery fault diagnosis, a large number of studies have made gratifying achievements in improving the accuracy of diagnosis results with the help of deep learning. However, there are few studies on the reliability of diagnostic methods. In this paper, a deep convolutional network based on visual optimization is designed for fault diagnosis of rotating machinery. Class activation mapping (CAM) technology is used to observe the area of concern of the neural network and provide feedback with loss function to ensure that the neural network can correctly focus on the effective information in the image. With this optimization method, the reliability of diagnosis is improved. Through repeated test verification of the measured data, it is found that the proposed method improves the accuracy and stability of the diagnostic results without changing the network structure, which verifies the effectiveness of the proposed method.

This publication has 20 references indexed in Scilit: