A Fault Diagnosis Method of Rolling Bearings Based on Parameter Optimization and Adaptive Generalized S-Transform

As for the fault diagnosis of rolling bearings under strong background noises, whether the fault feature extraction is comprehensive and accurate is critical, especially for the data-driven fault diagnosis methods. To improve the comprehensiveness and accuracy of the fault feature extraction, a fault diagnosis method of rolling bearings is proposed based on parameter optimization and Adaptive Generalized S-Transform (AGST). The AGST is used to solve the problem of incomplete feature extraction of bearing faults. The Particle Swarm Brain Storm Optimization algorithm based on the Discussion Mechanism (PSDMBSO) is used for the parameter optimization of VMD, which can better separate the complete fault components. The effectiveness of the fault diagnosis method proposed in this paper is verified by comparison with other methods.