Reliability modeling of complex mechanism system using GBN

The Bayesian Network (BN) as a probability-based knowledge representation method is appropriate for modeling complex mechanism system reliability, when it is of interest in complex structures or multiple failure modes in the system. This paper presents a new Grey Bayesian Network (GBN) to solve the reliability problem for complex mechanism system with incomplete information and high uncertainty. In this new model, grey probability density functions (GPDF) of its nodes are obtained by grey generation theory and interval analyses instead of the ones represent random variables. The reliability of the complex mechanism is computed by the Monte Carlo simulation. Research on this method is performed by a space mechanism, and the results show the feasibility and validity of the proposed method.