Research on rolling bearing fault diagnosis method based on improved SSA-VMD

Aiming at the problem of weak fault feature extraction difficulty of rolling bearings in a strong background noise environment, this paper proposes a fault diagnosis method based on an improved Sparrow Search Algorithm optimized Variational Modal Decomposition (SSA-VMD). Firstly, Tent chaotic mapping is introduced into the traditional SSA to optimize the population initialization strategy, and combined with Cauchy's variational operator to enhance the local search capability; secondly, the original vibration signal is decomposed with the minimum envelope entropy as the fitness function of the key parameters of the VMD, and then the signal is reconstructed by filtering the decomposed effective Intrinsic Modal Function (IMF) components; ultimately, the multiclassification model of the support vector machine is constructed. Finally, the support vector machine multi-classification model is built to complete the fault diagnosis. The simulation results show that compared with the traditional method, the fault diagnosis accuracy of this method is higher. It provides a new method for fault diagnosis of rolling bearings under a strong background noise environment.