Based On The Normal Fuzzy Number Of Causality Diagram For Fault Diagnosis Application

Professor Zhang Qin developed a Dynamic Causality Diagram(In the below referred to as the Causality Diagram)in 1994.It is based on the belief network improvements over the uncertain knowledge representstion and reasoning based on the graphical analysis of probability theory.In people’s lives to prevent faults and fault analysis of a system is very necessary. Causality Diagram has a very wide range of application in these two areas.By Causality Diagram can solve the probability of occurrence of an event in the known evidence,which is the posterior probability.Prerequisity analysis is the assumption that the probability of basic event known value and independence when carrying out the analysis and to be organized into a logical expression of the basic events.At last calculated probability values. Causality Diagram requirements for the probability of occurrence of events under the exact value of the situation,but in reality the probability of occurrence of events fuzziness and uncertainty characteristics.So people in the study of the Causality Diagram exact value but also carried forward to expand the event into a general fuzzy event,and then map the causal events unfold based on fuzzy qualitative and quantitative analysis to obtain the exact value of the probability of the event,so that the Causality Diagram range of applications become more widespread.Currently,the study of Fuzzy Causality Diagram was the introduction of L-R Fuzzy Numbers.The common L-R Fuzzy Number are Triangulai Fuzzy number and Normal Fuzzy Number. This article is to aid normal fuzzy numbers for reasoning fuzzy Causality Diagram and to study the Causality Diagram with minimal cut sets and minimal path sets.And the reasoning applied to the vehicle drive axle system and warships offshore supply hydraulic system,Finally got the fuzzy likehood value system failure,thus obtaining the possibility of the occurrence probability of the value of the event to address the Causality Diagram reasoning requires precise value requirements.