基于小波熵和SVM的動(dòng)態(tài)電能質(zhì)量擾動(dòng)識(shí)別研究.pdf

1、華北電力大學(xué)（保定）碩士學(xué)位論文基于小波熵和SVM的動(dòng)態(tài)電能質(zhì)量擾動(dòng)識(shí)別研究姓名：王洪磊申請(qǐng)學(xué)位級(jí)別：碩士專業(yè)：電力系統(tǒng)及其自動(dòng)化指導(dǎo)教師：周明20071230華北電力人學(xué)碩十學(xué)位論文摘要摘要近年來(lái)，電能質(zhì)量擾動(dòng)檢測(cè)與識(shí)別已經(jīng)成為眾多領(lǐng)域普遍關(guān)注的問(wèn)題。本文主要探討了對(duì)各種典型動(dòng)念電能質(zhì)量擾動(dòng)的檢測(cè)與識(shí)別，提出了一種基于小波奇異熵和支持向量機(jī)相結(jié)合的動(dòng)態(tài)電能質(zhì)量擾動(dòng)識(shí)別的新方法。首先應(yīng)用小波包變換對(duì)電能質(zhì)量擾動(dòng)信號(hào)進(jìn)行降噪處理，然后利用

2、小波奇異熵對(duì)擾動(dòng)信號(hào)進(jìn)行特征提取，并采用基于支持向量機(jī)算法的模式識(shí)別分類器對(duì)特征向量進(jìn)行訓(xùn)練與識(shí)別。試驗(yàn)仿真結(jié)果表明了該方法具有抗噪性強(qiáng)、模型簡(jiǎn)單j泛化能力強(qiáng)、識(shí)別率高等優(yōu)點(diǎn)，是一種有效的電能質(zhì)量擾動(dòng)識(shí)別分析方法。關(guān)鍵詞：電能質(zhì)量，擾動(dòng)識(shí)別，小波熵，支持向量機(jī)，小波包降噪ABSTRACTInrecentyears，powerqualitydisturbancesdetectionandclassificationhasbecomeapr

3、oblemwhichattractstheconceminmanyfieldsThispapermainlydiscussestheVariousmodelsofdynamicpowerqualitydisturbancesdctectionandclassification，anoVelapproachondynamicpowerqualitydisturbanceclassificationbasedonwaveletsingula

4、rentropyandsupportVectormachineispresentedinthispaperAtfirstthewaVeletpackettransfomisappliedtoreducethenoiseofpowerqualitydisturbancesignalThenthewaVeletsingularentropyisusedtoextractthefeatureofdisturbancesigIlalAt1ast

5、thepattemrecogllitionclassifierbasedontheSVMalgorithmisusedtotrainandclassifytheeigenVectorThesimulationresultsshowthattheproposedmethodiseffcctiVeinpowerqualitydisturbancesclassificationwhichhasthepropertiesofpower如lant

6、inoiseperfomance，simplemodel，highrecognitionrateaIldhighgeneralizedperfo咖anceWangHonglei(PowcrSystem鋤dItsAutomation)DirectedbyProfZhouMingKEYWoRDS：powerquality’disturbanceclassification，waVeletentropy，SVM，waVeIetpacketno