Design of low interaction distributed diagnosers for discrete event systems

This paper deals with distributed fault diagnosis of discrete event systems (DES). The approach held is model based: an interpreted Petri net (IPN) describes both the normal and faulty behaviour of DES in which both places and transitions may be non measurable. The diagnoser monitors the evolution of the DES outputs according to a model that describes the normal behaviour of the DES. A method for designing a set of distributed diagnosers is proposed; it is based on the decomposition of the DES model into reduced sub-models which require low interaction among them; the diagnosability property is studied for the set of resulting sub-models.