贝叶斯网络在模型诊断中的应用  

Application of Bayesian network in model-based fault diagnosis

作　　者：邵继业[1] 王日新[1] 徐敏强[1] 

机构地区：[1]哈尔滨工业大学航天学院,哈尔滨150001

出　　处：《吉林大学学报（工学版）》2010年第1期234-237,共4页Journal of Jilin University:Engineering and Technology Edition

基　　金：'863'国家高技术研究发展计划项目(2003AA735080)

摘　　要：把贝叶斯网络引入到模型诊断框架中,依据观测量,研究了一种建立系统贝叶斯网络观测模型的方法。利用网络观测模型,可计算系统诊断解的后验概率,从而找出系统最可能的故障组件。最后,以卫星两轴姿态控制系统为例,应用本文方法进行了分析。Model-based diagnosis describes a system using the structure and behavior model of the system. However, there exists uncertainty in model-based diagnosis because of the coupling relations among the faulty components. This model-based diagnosis method and de solve uncertainty. The posterior prob model to determine the most probab satellite was taken as an example to il paper incorporates Bayesian network into the framework of velops a Bayesian network model in terms of observations to abilities of diagnoses are computed using the Bayesian network le faulty component. An attitude control system of two-axis lustrate and validate the proposed method.

关 键 词：计算机应用 模型诊断 不确定性 贝叶斯网络 后验概率 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]