ROLLING BEARING FAULT DIAGNOSIS BASED ON FUSION CNN AND PSO-SVM

Abstract

Aiming at the problem that it is difficult to extract subtle fault features in the process of rolling bearing fault identification,this paper proposes a rolling bearing fault diagnosis method based on fusion convolutional neural network and support vector machine based on particle swarm optimization algorithm. In this method,the bearing vibration signal is used as the input signal of the one-dimensional convolutional neural network and the two-dimensional convolutional neural network,and the extracted fault information is fused in the convergence layer. Finally,the optimized classifier improves the accuracy of fault recognition. In order to verify the diagnostic performance of this method,a comparison will be made between the 1 D convolutional neural network and the 2 D convolutional neural network with the same specifications of the fusion convolutional neural network.Experimental results show that this method can not only improve the accuracy of fault identification,but also maintain good diagnostic performance when the signal is polluted by noise.

Keywords

• Rolling bearing;Fault diagnosis;Convolutional neural network;SVM