In order to avoid the more serious motor fault and system breakdown which were caused by open phase during six-phase permanent magnet synchronous motor (PMSM) running, it is necessary to do the fault prediction and diagnosis. This paper derived mathematical model of neutral point isolation six-phase PMSM shifted by 30° with the principle of stator magnetomotive force invariance. Wavelet packet analysis was used to collect the feature values and wavelet neural network was built to do the fault prediction and avoid system spurious triggering. The K-Nearest Neighbor (KNN) machine learning system had also been built to diagnose the fault types quickly which could realize fault state perception. MATLAB and Scikit-Learn library of Python were used to do simulations which could verify the strategy reliable and effective.