Fault Diagnosis of Automobile Brake System Based on Fuzzy Bayesian Network
The fault diagnosis approach based on Bayesian network is frequently used in fault diagnosis field, but it has some disadvantages due to lack of the quantitative data information, the paper puts forward the analysis method combining the fuzzy probability with Bayesian network.A fault tree was built first and was mapped into a Bayesian network.Then it employed fuzzy theory to map experts linguistic judgments on basic events failure probabilities into fuzzy numbers, defuzzified them and obtained precise results.It used gate rules to deal with the uncertainty of conditional probabilities, Bayesian network toolbox was used to calculate the probability of the fault, and then found out the vulnerabilities of the system.The results showed that the method is valid and it is able to make full use of fuzzy information and uncertain information in reliability analysis,which provides basis for completing fault diagnosis and improving system reliability.
bayesian network fuzzy theory automobile brake system fault diagnosis
Xie Xuefei Chen Lin Du Yan
School of Automobile, Changan University, Xian 710064, China
国际会议
西安
英文
186-190
2015-09-18（万方平台首次上网日期，不代表论文的发表时间）