Abstract: A Fault information fusion diagnosis method based on HHT/PNN was brought forward to improve the diagnosis ability of dynamic and random fault.HHT was used to extract the instantaneous frequency feature and the instantaneous amplitude feature.Three fault features were fused by PNN to make fault diagnosis.The fault diagnosis method based on HHT/PNN was compared with the method based on Neural Networks.The simulation results show that for the dynamic and random fault,the fault information fusion diagnosis method based on HHT/PNN can get higher fault diagnosis veracity than the fault diagnosis method based on Neural Networks.