Taking the advantage of Bayesian networks in dealing with the issue of uncertainty, this paper puts forward a fault diagnosis (FD) method based on Bayesian networks for electric equipment according to its fault characteristics of hierarchy, correlation and uncertainty. 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.%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.
展开▼
