模糊贝叶斯网的变压器故障诊断

摘要

目前油中溶解气体的三比值法是变压器故障诊断的有效方法之一.变压器故障诊断中的信息具有随机性和不确定性的特点,文中提出一种基于模糊贝叶斯网络的变压器故障诊断方法.该方法利用贝叶斯表达知识灵活,处理不确定性与关联性问题能力强,模糊集能有效表达模糊事件和信息的特点,利用隶属函数模糊化三比值的分割空间,模糊贝叶斯网络推理获得故障类型.实例证明,该方法在信息不完备条件下诊断准确率高,为变压器故障诊断提供了一条新的理论依据.%Dissolved gas analysis (DGA) is the most effective and convenient method in transformer fault diagnosis. Due to the randomness and uncertainty of power transformer fault diagnosis data, a novel specific transformer fault diagnosis method based on Fuzzy Bayesian network is proposed in this paper. It uses in the method that the Bayesian network satisfactory capacity of knowledge representation and strong solving ability to deal with uncertain facts, the Fuzzy set can represent fuzzy knowledge and fuzzy event. First, the segmentation spaces of three ratio methods are processed fuzzily using a membership function, then, the fault type is diagnosed by theory of fuzzy Bayesian networks. Finally, the correctness and effectiveness of this method are validated by the result of practical fault diagnosis examples, and a novel method is provided for the diagnosis of the fault transformer.