Basic Theory of Fuzzy Bayesian Networks and Its Application in Machinery Fault Diagnosis

Abstract

Bayesian network is an effective uncertain knowledge representation and reasoning method. Fuzzy sets can be used for expressing fuzzy events or fuzzy objectives in some special region. Combining these two theories, this paper discusses the probability of the fuzzy event and presents a hybrid inference system with fuzzy sets and Bayesian networks which are called "Fuzzy Bayesian Networks (FBNs) ". Then a case demonstrates the validity of FBNs in machinery fault diagnosis.