电力变压器故障诊断专家系统知识库建立和维护的粗糙集方法

A RS APPROACH TO FOUNDING AND MAINTAINING ES KNOWLEDGE BASE FOR FAULT DIAGNOSIS OF POWER TRANSFORMER

提出了一种变压器故障诊断专家系统知识库形成的粗糙集方法 ,以解决专家系统较难获取完备知识的瓶颈问题。该方法从历史故障数据所形成决策表的约简出发 ,通过计算规则的粗糙隶属度 ,形成不同简化层次上符合置信度要求的节点网络规则集。用变压器故障信息与知识库中相应节点的规则集进行匹配 ,即使在气相色谱分析数据不完备的情况下 ,也能得到正确的诊断结果。通过推理机和数据库 ,实现对知识库的动态维护。大量诊断实例表明 ,该专家系统有效、灵活 。

In order to resolve the bottleneck problem of obtaining complete knowledge of expert system,a Rough Set approach to founding knowledge base of an expert system for transformer fault diagnosis is proposed.From the reduction of decision table defined by history fault data,a series of nodes network rule sets,with suitable belief degree under different reductive levels,are developed by calculating the rough subjection degree of every rule.When the fault information of transformer is given,one can match the information to the rule sets of relative nodes.Even when the data of DGA is imperfect,the diagnosis results are correct.The knowledge base is maintained through reasoning machine and database.A lot of diagnosis examples show that the ES is quite efficient,flexible and fault tolerant.