Estimation of the fault occurrence dates in DESs with partially observed stochastic Petri nets

In this paper, a method for fault occurrence date evaluation in stochastic discrete event systems is proposed. The system is modeled using partially observed stochastic Petri nets. This model includes the faulty behavior that represents the failure processes of the system. From timed observation sequences resulting from this modeling, our approach consists, first, on evaluating the probabilities of marking trajectories consistent with the observations. Diagnosis in terms of faults probability is obtained as a consequence. Thereafter, a probabilistic model based on the sum of random exponential variables is presented to determine the fault date probability.