Bayesian Network Modeling for Dynamic Fault Tree  
Author Tetsushi Yuge


Co-Author(s) Shigeru Yanagi


Abstract A method of calculating the exact top event probability of a fault tree with dynamic gates and repeated basic events is proposed. It is a hybrid of a Bayesian network (BN) and an algebraic technique. At first, modularization is applied to a dynamic fault tree. The detected modules are classified into two types: the parental Markov condition is satisfied, or not. The module with parental Markov condition is replaced to an equivalent single event. The occurrence probability of this event is obtained as the sum of disjoint sequence probabilities. After the contraction, the BN algorithm is applied to the dynamic fault tree in which some repeated events or dynamic gates may be included. The conditional probability tables for dynamic gates are presented. The BN is almost a standard one and has hierarchical and modular features. Numerical example shows that our method works well for a complex system.


Keywords dynamic fault tree, Bayesian networks, top event probability, sequence probability
    Article #:  1854
Proceedings of the 18th ISSAT International Conference on Reliability and Quality in Design
July 26-28, 2012 - Boston, Massachusetts, U.S.A.