Power converter switching tube failure is a primary fault type in switched reluctance motor(SRM)speed control systems

significantly impacting the operational reliability of the entire system. To enhance fault diagnosis accuracy and system robustness

a novel fault diagnosis method for SRM power converters was proposed

based on variational mode decomposition(VMD)and multiscale fuzzy dispersion entropy(MFDE). The sparrow search algorithm(SSA)was employed to determine the optimal parameter combination for VMD

effectively addressing the difficulty of precisely configuring VMD parameters. Utilizing the optimized VMD

the MFDE of the effective components extracted from the SRM DC bus signal was used to construct feature vectors. These vectors were used as inputs for a support vector machine(SVM)to achieve the intelligent classification and identification of power converter switching tube faults. To validate feasibility and effectiveness of the proposed method

a simulation model was developed and compared with alternative fault diagnosis models. Furthermore

an SRM experimental platform was established to conduct classification tests on signals under open-circuit and short-circuit fault conditions. The results demonstrate that the proposed method can accurately diagnose faults in both simulation and experimental environments

effectively enhancing fault identification capability.