Bayesian Stochastic Petri Nets (BSPN) - A new modelling tool for dynamic safety and reliability analysis

An efficient formalism for safety analysis should be: (i) able to consider the failure behaviour of complex engineering systems, and (ii) dynamic in nature to capture changing conditions and have wider applicability. The current formalisms used for safety analysis are lacking in one of the above-listed criteria. Bayesian network (BN) allows the modelling of failure of systems where the inter-nodal dependencies are represented exclusively by conditional probabilities. Stochastic Petri nets (SPN) enable the study of the dynamic behaviour of complex systems; however, they lack the ability to adapt to changes in the data and operating conditions. This paper proposes a hybrid formalism that strengthens SPN with BN capabilities. The proposed formalism is graphical and uses advance feature such as predicates to perform the data updating functions. This ability enables the analysis of continuous input data without the necessity of time-slice discretization process. The proposed formalism is termed Bayesian Stochastic Petri Nets (BSPN). It provides a dynamic assessment of safety by capturing additional sets of data rends. In BSPN, the conditional probability is captured as a time-dependent function to allow consideration of the cumulative effect of the failure scenario. The BSPN implementation is demonstrated with an example illustrating the modelling capabilities.