A reliability allocation method based on Bayesian networks and Analytic Hierarchy Process

Reliability has been greater concerned in recent years and allocating proper reliability value to each component of a complex system as an optimization process to reduce cost and rise productivity is very important. This paper presents a reliability allocation method based on Bayesian networks (BNs). In this paper, the approach are presented in two main aspects: modelling aspect and analysis aspect. At modelling aspect, three main steps are descried. Build model by Reliability Block Diagram (RBD) and transform it into BNs with special weight nodes converted by the weight vector calculated in Analytic Hierarchy Process (AHP). At analysis aspect, the procedure of algorithm is based on the Bayesian approach to interfere and iterate until the value of the leaf node attains the reliability target. To demonstration of this method capability, an example from the literature was described, and the result shows that presented method is convincing and practicable.