Open-circuit fault diagnosis of wind power converter based on LMD energy entropy and location analysis

In order to improve the fault diagnosis accuracy of wind power converters, Aiming at single open circuit and double open circuit faults of grid-side converter (GSC) IGBT modules of permanent magnet synchronous generators (PMSG) wind turbines, an open-circuit fault diagnosis method for wind power converters based on local mean decomposition (LMD) energy entropy and localization analysis is proposed. First, the three-phase output current of the GSC is collected as the original signal, and is decomposed into multi-layer product function (PF) components by LMD, and the energy entropy of the PF component in each state is obtained. Secondly, according to the three-phase current sequence, the positioning parameters are added to determine the upper and lower bridge arms. Finally, the eigenvectors of energy entropy and localization parameters are fused and input into the Stacked Sparse Autoencoder (SSAE) network for training and fault identification. The simulation and experimental results show that the fusion of energy entropy and location analysis makes the fault features more obvious, which can effectively improve the fault diagnosis accuracy compared with other feature extraction algorithms.