Reliability Analysis of Failure-Dependent System Based on Bayesian Network and Fuzzy Inference Model

With the rapid development of information and automation technology, manufacturing system is evolving towards more complexity integration. The components will inevitably suffer from degeneration, impact component-level failure on reliability a valuable issue to be studied, especially when dependence exists among components. Thus, it vital construct evaluation mechanism that helps characterize healthy status facilitate wise decision making. In this paper, analysis framework for failure-dependent proposed, in which copula functions with optimized parameters are used description different correlations, fuzzy inference model constructed derive subsystem based correlation. Finally, Bayesian network applied infer structure combined correlation inside. Simulation results proposed method show reasonable effective cases. Compared method, shows better adaptability systems varying degrees. This work can provide theoretical guidance evaluating types.