Fault diagnosis system based on sensitivity analysis and fuzzy logic

This paper describes three ways of building a decision system for model-based fault diagnosis. The aim is the management of uncertain and redundant information provided by a parity equation fault diagnosis method. Although any residual generation method may be considered, the input-output parity equation approach has been used. Sensitivity analysis is the key point in the evaluation of fault symptoms in order to obtain a final diagnosis. With this method, sensitivity estimates are easily obtainable by direct observation of the parity equations. Three ways to solve the decision problem are described: fuzzy logic-based, direct weighting of symptoms and directional properties. A simple simulated case has been used to prove its performance. Moreover, the fuzzy approach, that has showed to be the most robust of them, has been tested on a real laboratory equipment with similar results.