Fault diagnosis of the satellite power system based on the Bayesian network

Abstract

The satellite power system is an important piece of the satellite system; targeting on the problems of complex fault mechanisms and uncertainty between fault type and fault symptoms, the method of Bayesian network fault diagnosis in the satellite power system has been raised. In the learning process of Bayesian network structure, this algorithm adopts statistical strategy for the rule library provided by many experts, extracts causal relationship from expert knowledge base, fills in the causal relationship table, thereby sets up the fault diagnosis hierarchical structure model in the satellite power system based on Bayesian network. Simulation shows that the Bayesian network fault diagnosis model is effectively solving the uncertainties in fault diagnosis.