The Partial Reconstruction Symplectic Geometry Mode Decomposition and Its Application in Rolling Bearing Fault Diagnosis

Extracting the fault characteristic information of rolling bearings from intense noise disturbance has been a heated research issue. Symplectic geometry mode decomposition (SGMD) already adopted for bearing diagnosis due to its advantages no subjective customization parameters and ability reconstruct existing modes. However, SGMD suffers rapidly decreasing calculation efficiency as amount data increases, in addition invalid symplectic components affecting accuracy. The regularized composite multiscale fuzzy entropy (RCMFE) operator is constructed evaluate complexity each initial single component minimize residual energy. Combined with partial reconstruction threshold indicator filter out specific significant components, raw signal can be decomposed into multiple physically meaningful geometric components. Therefore, accuracy enhanced. Thus, method proposed based on (PRSGMD). Both simulated experimental analysis results show that PRSGMD improve speed while increasing accuracy, thereby augmenting robustness effectiveness algorithm.