基于Hopfield神经网络的谐波电流提取方法  

A Detecting Approach of Harmonic Current Based on Continued Hopfield Neutral Network

作　　者：孙改平[1] 杨尔滨[1] 王俊宇[1] 

机构地区：[1]上海电力学院电力与自动化工程学院,上海200090

出　　处：《上海电力学院学报》2012年第5期409-412,共4页Journal of Shanghai University of Electric Power

基　　金：上海市教育委员会重点学科建设资助项目(J51301);上海市高校选拔培养优秀青年教师科研专项基金(sdl09003)

摘　　要：针对电网中谐波电流的特点及要求,提出了一种基于连续型Hopfied神经网络的谐波电流检测算法,并建立了相应的模型.通过分析发现该方法具有较高的准确性和较快的响应速度,以及良好的动态跟踪特性,同时也指出了该模型的不足,并提出了相关建议.A detecting method of the harmonic current in the power system based on continued Hopfield neutral networks is proposed, and the relevant circuit model is built. Analysis reveals that this method has a high level of accuracy and a fast response as well as the feature of dynamic tracking. Finally, the limitations of the method are pointed out and some suggestions offered.

关 键 词：谐波电流 连续型HOPFIELD神经网络 检测 幅值 相位 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构] TM477[自动化与计算机技术—计算机科学与技术]