A methodology for quantitative analysis of non-determinacy relationships using fuzzy logic in Bayesian networks

Potential hazards may lead to catastrophic accidents in safety-critical systems. Therefore, the ability to analyze causal logic relationships between risks and accidents is tremendously beneficial. Due to the uncertainties and lack of data that characterize non-deterministic relationships, the Bayesian network can be applied as an appropriate tool for determining a conditional probability distribution. A new allocation method of conditional probability based on fuzzy logic in Bayesian networks is proposed in this paper. More specifically, we propose that a Bayesian network can be used for quantitative analysis after a risk model of influencing factors has been established, and then the proposed method can be used to analyze a particular case.