基于贝叶斯网络模型的电子装备故障诊断研究  

Study on Fault Diagnosis of Electric Equipment Based on Bayesian Networks Model

作　　者：杜敏杰[1] 蔡金燕[1] 刘利民[1] 陈鹏[1] 

机构地区：[1]军械工程学院光学与电子工程系,河北石家庄050003

出　　处：《计算机测量与控制》2011年第11期2629-2631,共3页Computer Measurement &Control

摘　　要：针对电子装备故障的层次性、相关性、不确定性特点,结合贝叶斯网络在处理不确定性问题上的优点,提出了电子装备故障诊断的贝叶斯网络方法;研究了基于故障树分析和故障模式、影响、危害度信息的贝叶斯网络模型建立方法,分析了贝叶斯网络的故障预测和推理原理,确立了各底事件对故障诊断的重要度,形成了故障诊断的合理顺序,通过实例验证了上述方法的可行性和有效性;研究成果对复杂电子装备的故障诊断有借鉴意义。Taking the advantage of Bayesian networks in dealing with the issue of uncertainty, this paper puts forward a fault diagnosis （FD） melhod based on Bayesian networks for electric equipment according to its fault characteristics of hierarchy, correlation and uncertain ty. The methodology of modeling Bayesian networks based on the information of fault tree analysis and fault mode, effect and criticality analysis is studied and the principle of fault prediction and inference of Bayesian networks is analysed. Each basic event＇ s importance for FD is fixed and the reasonable sequence of FD is established. The validity and feasibility of above-mentioned method is verified by an instance and the results are useful to the fault diagnosis of complex electric equipment.

关 键 词：电子装备 故障诊断 贝叶斯网络 不确定性 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]