A Reliability Evaluation Methodology of Complex Systems Based on Dynamic Object Oriented Bayesian Networks

摘要

A novel reliability evaluation methodology of complex systems is proposed by using Dynamic Object Oriented Bayesian Networks (DOOBNs). This modeling methodology consists of two main phases: one construction phase for Object Oriented Bayesian Networks (OOBNs) and another construction phase for DOOBNs. In the first phase, the network fragments that have the same structures and parameters are divided into classes, then the classes are encapsulated. OOBN construction is completed according to the relationship among the encapsulated classes. In the second phase, every fragment of DBNs which was constructed by the last phase is encapsulated as a class which is called DOOBN. DOOBN construction is completed according to the relationship between time fragments. The correctness of this methodology is validated by using an all series system, an all voting system, a voting after series system, a series after voting system, a parallel after series system and a series after parallel system. This methodology can model the system from global to local levels, effectively reducing the modeling difficulty, and can take more efficient arithmetic reasoning algorithms.