基于人工神经网络的CVT的研究  

Research of CVT Based on Artificial Neural Networks

作　　者：马朝华[1] 杨育霞[1] 

机构地区：[1]郑州大学电气工程学院,河南450002

出　　处：《微计算机信息》2007年第17期282-284,共3页Control & Automation

基　　金：河南省教育厅自然基金项目(2006470007)

摘　　要：电容式电压互感器(capacitor voltage transformers,CVT)由于其体积小、重量轻、维护工作量少、运行可靠,且兼有高频载波通道耦合设备的复用功能,所以得到大量的应用。但由于其电路固有的特性,在输入信号发生突变时,其二次侧的输出不能很快的跟随一次电压的变化,出现了一个瞬变过程,此瞬变过程能导致继电保护装置误动作。本文基于人工神经网络的方法,提出并建立了用来修正CVT二次侧波形失真的神经网络模型。给出了这一方法详细的设计步骤,通过对模型进行状态检验的结果表明,提出的模型算法是正确的。　Because of capacitor voltage transformers（CVT）smaller size , lighter weight ,less maintenance, higher operation reliability and combination function of carrier channel coupling equipment ,the capacitive potential transformer has widely used in power system .Due to the circuit inherent characteristics of CVT, with the sudden change of the input signal of the CVT, the primary voltage can not been quickly tracked by the CVT output ,so that a transient response will be made. Capacitive voltage transformer transient can cause protective relay misoperation. Details of the design procedure and the results of performance studies with the proposed method are given in the paper. Performance studies results show that the proposed algorithm is accurate.

关 键 词：人工神经网络 电容式电压互感器 瞬变响应 

分 类 号：TP273.5[自动化与计算机技术—检测技术与自动化装置]