Bayesian Network: Modeling Formalism of the Structure Function of Boolean Systems
Philippe Weber, Christophe Simon · 2016
This chapter illustrates how Bayesian network (BN) can solve the modeling problems of dependability and risk analysis of complex systems. One of the principle characteristics of modeling Boolean stucture function using BN is the ability to construct models from knowledge without technical expertise regarding computing algorithms. It is important to understand that more than one BN can model the same structure function. For an illustration of BN applied to dependability analysis, the chapter shows the different BN models and their equivalence with usual models. In risk analysis, to assess the impacts of an undesired event, an event tree (ET) is added to the FT, resulting in a bowtie model. It is sufficient to directly map the Boolean equation inside the CPT. Then, Boolean logic such as OR, AND, XOR and NOT defines the failure scenarios that lead to the undesired event as described by FT or equivalent representations.