粗糙集理论在变压器故障诊断专家系统中的应用研究

The Study of Rough Set Theory in Fault Diagnosis Expert System of Transformer

在传统的变压器故障诊断专家系统的基础上,为解决专家系统较难获取完备知识的瓶颈问题,提出了一种基于粗糙集理论的故障诊断专家系统.该系统从历史故障数据所形成的决策表出发,运用粗糙集理论进行约简,构建专家系统知识库模型.通过计算诊断规则粗糙度,确定诊断规则的置信程度.利用推理机和故障事例库,实现对知识库的动态维护.

Based on the analysis of the traditional expert system for fault diagnosis of transformer, in order to resolve the bottleneck problem of obtaining complete knowledge of expert system, a new expert system based on the rough set is proposed. Form the decision table defined by history fault data, the paper applies the reduction of decision table in rough set theory, builds the knowledge base model. The belief degree of diagnosis rules is determined by calculating the rough subjection degree of every rule. The knowledge base is maintained through reasoning and fault database. 