Fault Diagnosis of Rolling Bearing Based on SSA-VMD-WPT

Due to the influence of external excitation, it is difficult to extract the fault characteristics of rolling bearings. In order to improve the accuracy of fault diagnosis, a fault diagnosis method based on sparrow search algorithm and wavelet packet threshold to improve variational mode decomposition combined with support vector machine to optimize convolutional neural network is proposed. Firstly, the original vibration signal is decomposed by variational mode decomposition, and the decomposition mode number and quadratic penalty factor are determined by sparrow search algorithm. Secondly, the wavelet packet threshold method is used to denoise each modal component after variational mode decomposition, and each mode after denoising is reconstructed to obtain the denoised vibration signal. Finally, the vibration signal after noise reduction is input into the convolutional neural network model based on support vector machine as the characteristic data, so as to realize the fault diagnosis of rolling bearings. The experimental results show that the proposed method has a good diagnostic effect on rolling bearing faults. Compared with other methods, its accuracy is higher and its generalization ability is stronger.