基于FMCN的电力系统输电线路跳闸故障诊断方法

来源期刊:中南大学学报(自然科学版)2011年第z1期

论文作者:冯健 李典阳 张超

文章页码:883 - 887

关键词:模糊最小最大神经网络;模式识别;故障诊断;电力系统

Key words:fuzzy min-max neural networks; pattern recognition; fault diagnosis; power system

摘    要:针对电力系统故障诊断中含有大量的不确定信息和实时性要求高的特点,本文基于模式分类的思想,将电力系统故障诊断视为模式识别问题,提出一种基于FMCN(Fuzzy min-max neural network classifier with compensatory neuron architecture)的电力系统输电线路跳闸故障诊断的新方法。该方法将电力系统保护动作和开关跳闸信息作为神经网络分类器的输入,与训练好的故障样本进行匹配即可得到故障类别,从而达到故障诊断的目的。此算法有利于降低分类的错误率,使复杂拓扑数据的分类更为精确,适合含有多种跳闸信息的输电线路的故障诊断。通过仿真分析验证了此方法的有效性。

Abstract: The fault diagnosis of power system contains a lot of uncertainty information and requests real-time, it is seen as pattern recognition problem based on pattern classification thoughts. A new method of the fault diagnosis in the tripping transmission lines of power system based on the algorithm of FMCN (Fuzzy min-max neural network classifier with compensatory neuron architecture) was proposed. The power system protection movement and switch tripping information is the input of neural network classifier, and the output of the classifier is fault category, so it will achieve the purpose of the fault diagnosis of power system. This algorithm is helpful for reducing the classification error rates, and is capable to approximate the complex topology of data more accurately. So it is suitable for fault diagnosis of a variety of tripping information in transmission lines. Finally, the simulation analysis shows that this method is effective.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号