Fault diagnosis with automata generated languages

A SDG-based simulation procedure is proposed in this study to qualitatively predict the effects of one or more fault propagating in a given process system. These predicted state evolution behaviors are characterized with an automaton model. By selecting a set of on-line sensors, the corresponding diagnoser can be constructed and the diagnosability of every fault origin can be determined accordingly by inspection. Furthermore, it is also possible to define a formal diagnostic language on the basis of this diagnoser. Every string (word) in the language is then encoded into an IF-THEN rule and, consequently, a comprehensive fuzzy inference system can be synthesized for on-line diagnosis. The language generation steps are illustrated with a series of simple examples in this paper. The feasibility and effectiveness of this approach has been tested in extensive numerical simulation studies.