Fault Diagnosis of Rolling Bearing Based on WOA-VMD-LSTM

In order to solve the problems of difficulty in extracting fault features of rolling bearings and the impact of external excitation on the accuracy of fault diagnosis, this paper proposes a fault diagnosis method based on whale optimization algorithm and LSTM(Long Short Term Memory) improved variational mode decomposition combined with support vector machine optimized convolutional neural network. Firstly, the variational mode decomposition of the vibration signal of the rolling bearing is carried out, and the minimum envelope entropy is taken as the fitness function, and the whale optimization algorithm is used to determine the number of decomposition modes and the secondary penalty factor of variational mode decomposition. Secondly, the LSTM noise reduction network is constructed, and the modal components decomposed by the variational mode are introduced into the noise reduction network, and the vibration signal after noise reduction is obtained by reconstructing each mode after noise reduction. Finally, support vector machine is used as the classifier of the convolutional neural network, and the vibration signal after noise reduction is input into the convolutional neural network to realize fault diagnosis. The analysis of experimental results shows that the method proposed in this paper has high fault diagnosis accuracy and better robustness.