Abstract: In order to diagnose faults of the shearer motors timely and accurately, and handle the motor faults quickly and to reduce losses, a new method is introduced to diagnose the specific type of fault based on the characteristics of common faults in rolling bearings which maintenances strategy is put forward and warning information is provided by means of optimizing the wavelet parameters to obtain frequency feature of the fault efficiently and these features are identified based on an improved expert system. The research results show that the expert system for fault diagnosis of shearer motor can correctly judge the common faults of rolling bearings and satisfy the requirements of real-time monitoring and fault warning, and the diagnostic conclusion is consistent with the actual site conditions.