Identification of stochastic and deterministic stochastic Petri net models for reliability analysis

Reliability analysis for dynamical systems is often based on timed stochastic Petri net (PN) models. A priori knowledge about failure processes is difficult to obtain and, as a consequence, the model structure and parameters are mainly unknown. In that case, synthesis and identification methods based on analysis of collected event sequences are of great interest. The contribution of this paper concerns the identification of timed stochastic PN models. Stochastic and deterministic stochastic PNs with deterministic and exponentially distributed transition durations are considered. A systematic identification method is proposed according to event sequences that are recorded by supervision systems. This method is based on the idea that the dynamic behaviour of considered PN can be mapped into a Markov model with state space isomorphic to the reachability graph of the untimed PN model.