Real time expert system for identifying rotor faults and mechanical influences in induction motor phase current

The authors describe the background to the development of a knowledge-based system for distinguishing rotor faults and load influences in the stator current spectra of an induction motor. Data and case histories from up to 100 users of this rotor fault detection technique have been accumulated over the past three to four years. From a study of this invaluable collection of knowledge, new information, both fundamental and empirical, has been deduced to improve and enhance the existing diagnostic technique. This was possible by organising the knowledge using rule based techniques and making the information available in the form of expert system software for use in real-time with data gathering equipment