针对配电网规模庞大且发生故障后警报信息存在不确定性和不完整性的问题,提出了一种粗糙集结合Petri网进行分区域并行推理的配电网故障诊断方法.该方法先将配电网划分为多个独立的区域,对于各个区域分别建立故障决策表,再利用粗糙集对决策表进行属性优选和诊断规则提取,最后构建Petri网模型,通过Petri网的并行推理实现故障诊断.诊断实例证明了该方法不仅诊断快速准确,而且容错能力强、适应性好、灵活性高.%According to the huge size of distribution networks and the uncertainties and imperfections of the alarm information after fault, this paper proposes a fault diagnosis method of distribution networks by the regional parallel reasoning based on rough set and Petri nets. This method includes three steps. First, distribution network is divided into several independent areas, and then establish fault decision table for each area respectively. Second, a rough set is used to optimize and extract diagnosis rules. Finally, after constructing petri nets model, fault diagnosis is finished through parallel reasoning of Petri nets. Test proved that this method can diagnose the fault rapidly and accurately, and it has the batter fault tolerance and adaptability.
展开▼