Skip to Main Content
An approach to model-based fault diagnosis using knowledge base and fuzzy logic techniques is presented. The input/output measurements are used to generate analytic symptoms. Heuristic symptoms observed by the operator or based on the process history are another source for fault diagnosis. Both kinds of symptoms are weighted by confidence measures calculated using fuzzy logic techniques and are fed into the fault diagnosis procedure. A summary of simulation results with a feed drive system is presented.
Date of Conference: 2002