Reliability analysis of phased-mission systems using Bayesian networks

Abstract

The paper presents a Bayesian networks (BN) based method to analyze the reliability of phased-mission systems (PMS). The method includes three steps. Firstly, each phase of PMS is represented by a BN framework, named phase-BN. Then, in order to express the dependences across phases, all the phase-BN are combined by (1) connecting the root nodes that represent the same component but belong to different phases, and (2) connecting the leaf nodes of the phase-BN with a new node that represents the whole PMS mission. The new constructed BN is named PMS-BN. Lastly, the reliability analysis is performed by a discrete-time BN modeling acting on PMS-BN. Two examples are used to expatiate on the proposed approach. The PMS-BN based method provides a new way to analyze PMS, especially those with dynamic phases. Further, based on PMS-BN, fault diagnoses and sensitivity analysis can be performed easily.