预览加载中，请您耐心等待几秒...

基于稀疏自编码和极限学习机的局部放电模式识别.docx

预览
1/2
2/2

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

基于稀疏自编码和极限学习机的局部放电模式识别 Title:LocalDischargePatternRecognitionBasedonSparseAutoencoderandExtremeLearningMachine Abstract: Localdischargepatternrecognitionplaysacrucialroleinthediagnosisandmonitoringofelectricalpowersystems.Thispaperproposesanovelapproachforlocaldischargepatternrecognitionusingtwopopularmachinelearningtechniques:sparseautoencoder(SAE)andextremelearningmachine(ELM).TheSAEisemployedtolearnthesalientfeaturesoftheinputdata,andtheELMisusedasaclassifierfordischargepatternrecognition.Theexperimentalresultsdemonstratethatthisproposedapproachachieveshighaccuracyandrobustnessinidentifyingvariousdischargepatterns,makingitapromisingsolutioninthefieldofelectricalpowersystems. 1.Introduction Electricpowersystemsarepronetolocaldischargephenomena,whichcanleadtoequipmentfailures,systembreakdowns,andevensafetyhazards.Detectingandrecognizinglocaldischargepatternsisofutmostimportanceforpreventivemaintenanceandreal-timemonitoringofpowersystems.Traditionalapproachesrelyonexpertknowledgeandmanualanalysis,whicharetime-consumingandsubjective.Withtherapidadvancesinmachinelearningandpatternrecognition,thereisagrowinginterestindevelopingautomatedsystemsforlocaldischargepatternrecognition. 2.RelatedWork Previousresearchhasexploredvarioustechniquesforlocaldischargepatternrecognition,includingartificialneuralnetworks(ANN),supportvectormachines(SVM),anddeeplearningmodels.However,thesemethodshavelimitations,suchasslowconvergenceandhighcomputationalcomplexity.Thisstudyaimstoovercometheselimitationsbycombiningtheadvantagesofsparseautoencoderandextremelearningmachine. 3.Methodology 3.1SparseAutoencoder(SAE) Sparseautoencoderisatypeofunsupervisedlearningalgorithmthatcanlearnefficientrepresentationsofinputdata.Itconsistsofanencoder,whichmapstheinputdataintoahiddenrepresentation,andadecoder,whichreconstructstheinputdatafromthehiddenrepresentation.TheSAEencouragessparsityinthehiddenrepresentation,whichhelpsincapturingthesalientfeaturesoftheinputdata. 3.2ExtremeLearningMachine(ELM) Extremele