Fault diagnosis for BLDCM system used FFT algorithm and support vector machines

To effectively solve the fault diagnosis problem of BLDCM unbalanced three-phase winding under the unsteady case, this article puts forward a fault diagnosis method based on Support Vector Machine (SVM) and FFT. Using FFT to analyze the time-frequency of local signal can extract fault features, which are utilized for SVM training. Once satisfied effects are achieved, SVM structure and internal parameters should be freezed. To compare the output and fault codes with given input can realize the goal of winding unbalanced fault diagnosis. At the same time, to simulate the unbalanced three-phase winding by building BLDCM position servo model with MATLAB/SIMULINK verifies the validity of the proposed fault diagnosis method. The example simulation results show that the method can not only diagnose fault existence, but also judge the level of fault effectively. As a reliable fault diagnosis approach, the method is simple and effective with the capability of making up existing flaws.