电力系统保护与控制2012，Vol.40Issue(7)：43-49,7.
基于概率神经网络的广域后备保护故障判别研究
Fault identification for wide area backup protection based on probabilistic neural network
摘要
Abstract
Information of each node is collected by wide-area backup protection to determine the fault components of some regional power grid. In this paper, a new method of fault identification for wide area backup protection is proposed by using PNN which has good ability of classification and fault-tolerance. The line fault directional component, the measurement element of distance protection paragraph II and the status of main protection are taken as PNN network's input, and the state information matrix for all fault is made as the training sample to train PNN network; then the state information vector of some random failure is used as the testing sample, and a large number of simulation experiments are made to simulate different fault identification results with inaccurate information. The results of experiments show that wide area backup protection based on PNN has good ability of fault-tolerance and high accuracy.关键词
广域后备保护/元件状态信息/PNN网络/故障判别/容错性Key words
wide area backup protection/ device status information/ PNN network/ fault identification-, fault tolerance performance分类
信息技术与安全科学引用本文复制引用
吴浩,李群湛,夏焰坤,刘炜..基于概率神经网络的广域后备保护故障判别研究[J].电力系统保护与控制,2012,40(7):43-49,7.基金项目
人工智能四川省重点实验室项目(2010RY005) （2010RY005）
