基于粗糙集和小生境遗传算法的电网故障诊断规则提取

Rule Extraction for Power System Fault Diagnosis Based on the Combination of Rough Sets and Niche Genetic Algorithm

用粗糙集理论进行电网的故障诊断,关键是对知识表的约简。本文以粗糙集理论中的决策表为主要工具,首先将继电保护和断路器的动作信号作为对故障分类的条件属性集,故障区域作为对故障分类的决策属性,建立决策表,然后利用小生境遗传算法适合于进行多峰值函数优化的特点,提出了一种基于小生境遗传算法的粗糙集属性约简方法,用于求解决策表的多个约简,进而进行值约简后抽取出诊断规则。算例结果说明了本算法的正确性和可行性。

When using the rough set theory for power system fault diagnosis the reduction process of the decision table is the key. The paper presents the decision table of the rough set theory, takes the signals of protection relays and circuit breakers of all kinds of fault cases as condition attributes and makes fault sections as value attributes to build the decision table. Considering the highly efficient of the niche genetic algorithm for the optimization of multi-peak functions, a algorithm based on niche genetic algorithm is proposed to obtain more optimal reductions of the rough sets and then to extract diagnosis rules. The simulation result shows that the validity and feasibility of the proposed algorithm.