摘要
以变电站的开关继电保护信息为基础,提出了一种基于粗糙集理论和神经网络理论的变电站故障诊断方法。即利用粗糙集理论的知识约简和处理不确定信息的能力,对变电站的故障诊断知识进行分层挖掘,实行属性优选,再运用神经网络对故障诊断知识进行模式识别。变电站故障诊断实例表明了该方法能有效地缩小问题求解规模,且具有较强的抗干扰能力。
Based on the information of circuit breakers and protection devices, a rough set theory and neural network theory based substation fault diagnosis method is proposed, i.e., using the ability of knowledge reduction and processing indeterminate information of rough set theory, the hierarchical mining of substation＇s fault diagnosis knowledge is carried out and optimal seeking of attributes is performed, then applying fault diagnosis knowledge the fault mode is identified by recursive neural networks. Actual examples show that the proposed method possesses good anti-interference ability and can effectively reduce the scale of solution.
出处
《电网技术》
EI
CSCD
北大核心
2005年第16期66-70,共5页
Power System Technology
关键词
变电站
粗糙集
递归神经网络
故障诊断
电力系统
Substation
Rough sets. Recursive neural networks
Fault diagnosis
Power system
