基于事例和规则混合推理的变电站故障诊断系统

故障诊断是保证电力系统安全运行的重要手段,目前多采用基于规则推理的专家系统,但其知识获取困难,自学习能力差,很难适应电网发展的要求.文中介绍了基于事例推理(CBR)和基于规则推理(RBR)的混合推理的变电站故障诊断专家系统.该系统采用CBR方法确定故障情况,再利用规则评价继电保护和开关的动作情况.事例库包括用RBR系统自动生成的基本事例库及无确定规则的特殊事例,在使用中还可不断地增加新事例以提高系统判断复杂故障的能力.由于采用了混合推理,系统故障诊断快速可靠,动作评价准确,自学习能力也得到很大提高,可减轻运行人员的工作量.

A SUBSTATION FAULT DIAGNOSIS SYSTEM BASED ON CASE-BASED REASONING AND RULE-BASED REASONING

Fault diagnosis is an important way to ensure the secure operation of power system. Currently the case-based reasoning expert systems are mostly adopted, but their knowledge acquiring and self-learning ability is weak. It is difficult for them to meet the need of power system development. A substation fault diagnosis system based on case-based reasoning (CBR) and rule-based reasoning (RBR) is proposed. It diagnoses the fault using CBR and analyzes the operations of protectors and breakers using RBR. The case database is composed of two parts: some are automatically created by RBR and the others are special cases that the system gradually adds to improve the ability to judge complex faults. Based on mixed reasoning, the system can diagnose the fault accurately and self-learning is greatly improved, therefore, the burden of operators can be relieved.