Mission reliability analysis of multiple-phased systems based on Bayesian network

Multiple-phased systems are defined as systems that its operational life can be divided into several disjoint periods, called “phases”. A phased mission is defined as a sequence of tasks which must be completed to achieve the system objective. In order to complete each task a different subset of the system need to function. During the mission, component or subsystem should fail at any time. However, if the fail component or subsystem is not critical in the phase, it will not affect the system performance. It is shown that if critical component of this phase is failed in the previous phase, it will lead to this phase and mission failure. So the transition from one phase to the next is a critical event. In this paper, Bayesian network reliability model is built and mission reliability of multiple-phased system is obtained. The modeling process includes two steps. In the first step, we construct phase Bayesian network for every phase which represent each phase mission by a Bayesian network. In the second step, we construct Bayesian networks of the multiple-phased system. The reliability analysis of the multiple-phased system is performed by discrete time Bayesian network. The model features are described and the approach demonstrated.