Applications of Bayesian network in fault diagnosis of braking system
Braking system is very important in automotive equipments. To solve the problems caused by the complex failure mechanisms in automotive hydraulic brake systems and the uncertain linkages between fault type and fault symptoms, a method of Bayesian network is offered for failure diagnosis. A statistical strategy is adopted there in this algorithm on the rule base provided by many experts to discard the weak causal relationship rules while keep the relatively strong ones during the Bayesian network structure learning, and a Bayesian networkbased model of layered architecture is established for fault diagnosis of hydraulic braking systems. The experimental data shows that the diagnostic result obtained by using Bayesian network model is much more accurate than that by fuzzy logic method, thus the uncertainty existing in fault diagnosis is effectively solved.
Bayesian network fault diagnosis the braking system uncertainty
Yu-guo Chen
Information Technology College Eastern Liaoning University Dandong, CHINA
国际会议
杭州
英文
234-237
2011-08-26（万方平台首次上网日期，不代表论文的发表时间）