Complex Systems Reliability Modeling Using Bayesian Networks

摘要

It is important for systems to do reliability assessment, especially for some complex systems such as cars, machine tools, aircrafts etc. This paper presents the application of Bayesian networks to the reliability modeling and assessment of complex systems. Fault tree analysis is often used to assessment system reliability, but Bayesian networks are parallel structures, so the time of solving is much shorter than that of FTA. Bayesian networks permit not only computing the reliability indices of a system but also presenting the effect of each component or some components on the system reliability to distinguish the unsubstantial part of the system. The results of two examples prove the validity and superiority of the method in the application of the reliability modeling and assessment of system.