Intelligent fault diagnosis research for permanent magnet linear synchronous motor

On basis of fault characteristics analysis of the permanent magnet linear synchronous motor (PMLSM), a fuzzy wavelet neural network model was established to achieve the PMLSM intelligent fault diagnosis, which used wavelet function as a fuzzy membership function and integrated fuzzy logic with BP neural network. Meanwhile a mixed learning algorithm based on self-organizing and instructors-guide-learning was proposed to train translation factor, flexing factor of wavelet function, and fuzzy neural network weights to make network parameters and structure achieve optimal approximation. The test results show that the method can realize fault diagnosis effectively, improve the efficiency and accuracy of diagnosis, and provide an effective way for the protection of PMLSM safe operation.