Rolling Bearing Fault Diagnosis based on Residual Neural Network

Abstract

<div class="Section0"><div>Because rolling bearings have been working in an environment with complex and variable working conditions and large noise interference for a long time, the bearing fault diagnosis method has a poor diagnostic effect under variable working conditions. To solve this problem, we propose a residual neural network based on the diagnosis method of rolling bearing fault. The proposed method takes rolling bearing time-domain signal data as input. Because bearing signals have strong time-varying properties, we construct a multi-scale residual block that can not only learn features at different levels, but also expand the width and depth of the residual neural network. We use the advantages of the dilated convolution to expand the receptive field, replace part of the ordinary convolution in the multi-scale residual block with the dilated convolution, and design a multi-scale hollow residual block. The advantage is that the method is made by expanding the receptive field. It has a strong feature learning ability and can learn better features under limited data. Finally, we add a Dropout layer to discard a certain proportion of neurons after the fully connected layer, which can effectively avoid the negative impact of overfitting, and use Case Western Reserve University bearing dataset, the simulation experiment, and the SVM + EMD + Hilbert envelope spectrum, BPNN + EMD + Hilbert envelope spectrum and Resnet three ways of comparative analysis, the results show that the method under the variable condition of the fault diagnosis of rolling bearing has higher diagnosis accuracy, stronger noise resistance, and generalization ability.</div><p> </p></div><p> </p>