摘要
在分析高压输电线路故障诊断方法的基础上,利用径向基函数(RBF)网络适于求解模式识别问题的优势,建造了基于RBF网络的高压输电线路故障诊断模型结构,来实现高压输电线路的故障诊断。同时采用基于优化原理的HCM算法实现聚类过程,来确定RBF网络的隐含层节点数,使网络的利用效率较高。仿真分析及容错性测试结果表明,该法能有效地实现高压输电线路系统的故障诊断,且在网络的训练速度及对畸变输入信息的容错能力方面都优于传统的BP神经网络(BPNN),对实时信息处理系统有一定适用性。
On the basis of analyzing the methods of accomplishing high voltage transmission line fault diagnosis, this paper proposes to adopt RBF network to complete high voltage transmission line fault diagnosis by using radial basis function network's capability of being adapt to solving pattern recognition problem, and builds a RBF network model structure used for transmission line fault diagnosis. Meanwhile optimization theory based HCM clustering algorithm is used to cluster sample data to determine the number of node of hidden layer, so that the efficiency of RBF network in use is high. By simulation analysis and test for fault tolerance of network, the results show that the method in this paper not only can accomplish correct fault diagnosis for high voltage transmission line but also has higher fault tolerance performance for distorted input signal than BPNN, therefore, it has a practical application value for real time information processing system.
出处
《高电压技术》
EI
CAS
CSCD
北大核心
2005年第6期81-84,共4页
High Voltage Engineering
基金
天津大学留学回国人员基金资助项目(200447)
关键词
高压输电线路
RBF网络
故障诊断
HCM聚类算法
high voltage transmission line
RBF network
fault diagnosis
HCM clustering algorithm