预览加载中，请您耐心等待几秒...

基于KPCA-SOM网络的列控RBC系统故障诊断方法（英文）.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KPCA-SOM网络的列控RBC系统故障诊断方法（英文） Title:FaultDiagnosisMethodforTrainControlRBCSystemBasedonKPCA-SOMNetwork Abstract: Thereliabilityandsafetyofrailwaytransportationsystemsheavilyrelyontheproperfunctioningofthetraincontrolsystem.TheRadioBlockCenter(RBC)isacrucialcomponentofthetraincontrolsystemresponsibleforensuringthesafeandefficientoperationoftrains.However,theRBCsystemispronetofaultsandfailures,whichcanhavesevereconsequencesifnotdetectedandresolvedpromptly.Therefore,thedevelopmentofaneffectivefaultdiagnosismethodfortheRBCsystemisofutmostimportance. ThispaperproposesanovelfaultdiagnosismethodfortheRBCsystembasedonthecombinationofKernelPrincipalComponentAnalysis(KPCA)andSelf-OrganizingMaps(SOM)network.TheKPCAtechniqueisappliedtoextracttherelevantfeaturesfromthecollecteddata,whiletheSOMnetworkisusedforclusteringandclassification. ThefirststepoftheproposedmethodinvolvescollectingandpreprocessingthedatafromvarioussensorsandsubsystemsoftheRBCsystem.Thecollecteddataconsistsofmultiplevariables,includingtrainpositions,speeds,andcommunicationstatuses.ThepreprocessingphaseincludesdatanormalizationanddimensionalityreductionusingKPCAtotransformthehigh-dimensionaldataintoareducedfeaturespace. Inthesecondstep,thepreprocesseddataisinputtotheSOMnetwork.TheSOMnetworkistrainedusingunsupervisedlearningtocreateatopologicalmapoftheinputdata.EachneuronintheSOMrepresentsacluster,andthedistancebetweenneuronsindicatesthesimilaritybetweenthecorrespondingdatainstances.ByanalyzingthetrainedSOM,potentialfaultpatternscanbeidentified. Thethirdstepinvolvestheclassificationofthedetectedfaultpatterns.Forthispurpose,asetofknownfaultpatternsisdefinedandassociatedwithspecificneuronsontheSOM.Newinstancesarethenclassifiedbasedonthedistancetotheassociatedneurons,enablingtheidentificationofthespecificfaulttype. Toevaluatetheperformanceoftheproposedfaultdiagnosismethod,experimentsareconductedusingreal-worlddatafromanRBCsystem.TheresultsdemonstratetheeffectivenessandaccuracyoftheKPCA-SOMnetworkindetectingandcla