毕设外文翻译

整理文档很辛苦,赏杯茶钱您下走!

免费阅读已结束,点击下载阅读编辑剩下 ...

阅读已结束,您可以下载文档离线阅读编辑

资源描述

英文翻译题目:通过分析变压器中溶解气体而进行故障诊断的专家系统姓名:宋日成学院:工学院专业:自动化班级:自动化112班学号:32211218指导教师:陆静职称:讲师2015年3月14日南京农业大学教务处制AnExpertSystemforTransformerFaultDiagnosisUsingDissolvedGasAnalysisW.S.Chan·Y.L.Xu·X.L.Ding·W.J.DaiReceived:9November2005/Accepted:11August2006/Publishedonline:7September2006©Springer-Verlag2006AbstractInordertoautomatethetransformerfaultdiagnosis,improvetheaccuracyofjudgment,theintroductionofartificialintelligenceexpertsystemfaultdiagnosis.Thesystemisbasedonfuzzyreasoningconfidencebyobservingtheinformation,theuseofknowledgetoreachaconclusion.Testprovedthismethodreducestherandomnessofjudgment,improveddiagnosis.Keywords:ExpertSystemTransformerTroubleshooting1IntroductionThepowertransformerisamajorapparatusinapowersystem,anditscorrectfunctioningisvitaltosystemoperations.Inordertominimizesystemoutages,manydeviceshaveevolvedtomonitortheserviceabilityofpowertransformers.Thesedevices,suchas,Buchholzrelaysordifferentialrelays,respondonlytoaseverepowerfailurerequiringimmediateremovalofthetransformerfromservice,inwhichcase,outagesareinevitable.Thus,preventivetechniquesforearlydetectionfaultstoavoidoutageswouldbevaluable.Inthisway,analysisofthemixtureofthefaultygasesdissolvedininsulationoilofpowertransformerhasreceivedworldwiderecognitionasaneffectivemethodforthedetectionofincipientfaults.ManyresearchersandelectricalutilitieshavereportedontheirexperienceanddevelopedinterpretativecriteriaonthebasisofDGA.However,criteriatendtovaryfromutilitytoutility.Eachapproachhaslimitationsandnoneofthemhasafirmmathematicaldescription.Therefore,transformerdiagnosisisstillintheheuristicstage.Forthisreason,knowledge-basedprogrammingisasuitableapproachtoimplementinsuchadiagnosticproblem.BasedontheinterpretationofDGA,aprototypeofanexpertsystemfordiagnosisofsuspectedtransformerfaultsandtheirmaintenanceproceduresisproposed.Thesignificantsourceinthisknowledgebaseisthegasratiomethod.Somelimitationsofthisapproachareovercomebyincorporatingthediagnosticprocedureandthesyntheticexpertisemethod.Furthermore,databasesadoptedfromTPCSgasrecordsoftransformersareincorporatedintotheexpertsystemtoincreasethepracticalperformance.Uncertaintyofdiagnosisismanagedbyusingfuzzysetconcepts.Thisexpertsystemisconstructedwithrulebasedknowledgerepresentation,sinceitcanbeexpressedbyexperts.Theexpertsystembuildingtool,KnowledgeEngineeringSystem(KES),isusedinthedevelopmentoftheknowledgesystembecause,ithasexcellentman-machineinterfacethatprovidessuggestions.Moreover,itsinferencestrategyissimilartotheMYCIN.Afamousrule-basedexpertsystemusedformedicaldiagnosis.Theuncertaintyofhumanqualitativediagnosticexpertise,e.g.,keygasanalysis,andanotherquantitativeimprecision,suchas,normsthresholdandgasratioboundariesetc.,aresmoothedbyappropriatefuzzymodels.Withtheresultsofsuchimplementation,differentcertaintyfactorswillbeassignedtothecorrespondingexpertisevariables.Bothevent-driven(forwardchaining)andgoal-driven(backwardchaining)inferencesareusedintheinferenceenginetoimprovetheinferenceefficiency.Todemonstratethefeasibilityoftheproposedexpertsystem,aroundhundredsofTPChistoricalgasrecordshavebeentested.Itisfoundthatmoreappropriatefaultytypesandmaintenancesuggestionscansupportthemaintenancepersonalstoincreasetheperformanceoftransformerdiagnosis.2.DEVELOPMENTOFDIAGNOSISANDINTERPRETATIONLikemanydiagnosticproblems,diagnosisofanoil-immersedpowertransformerisaskilledtask.Atransformermayfunctionwellexternallywithmonitors,whilesomeincipientdeteriorationmayoccurinternallytocauseafatalprobleminthelatterdevelopment.AccordingtoaJapaneseexperience,nearly80%ofallfaultsresultfromincipientdeteriorations.Therefore,faultsshouldbeidentifiedandavoidedattheearliestpossiblestagebysomepredictivemaintenancetechnique.DGAisoneofthemostpopulartechniquesforthisproblem.Faultgasesintransformersaregenerallyproducedbyoildegradationandotherinsulatingmaterials,e.g.,celluloseandpaper.Theoretically,ifanincipientoractivefaultispresent,theindividualdissolvedgasconcentration,gassingrate,totalcombustiblegas(TCG)andcellulosedegradationareallsignificantlyincreased.Byusinggaschromatographytoanalyzethegasdissolvedinatransformer'sinsulatingoil,itbecomesfeasibletojudgetheincipientfaulttypes.Thisstudyisconcernedwiththefollowingrepresentativecombustiblegases;hydrogen(H2),methane(C2H2),ethane(C2H6),ethylene(C2H4),acetylene(C2H2)andcarbonmonoxide(C0).ManyinterpretativemethodsbasedonDGAtodiagnosethenatureofincipientdeteriorationhavebeenreported.Evenundernormaltransformeroperationalconditions,someofthesegasesmaybeformedinside.Thus,itisnecessarytobuildconcentrationnormsfromasufficientlylargesamplingtoassessthestatistics.TPCinvestigatedgasdatafrompowertransformerstoconstructitscriteria.Thedevelopedknowledgebaseinthispaperispartiallybasedonthesedata.Ontheotherhand,Dornerburgdevelopedamethodtojudgedifferentfaultsbyratingpairsofconcentrationsofgases,e.g.,CH/H,CH/C2H4,withapproximatelyequalsolubilityandfusioncoefficients.Rogersestablishedmarecomprehensiveratiocodestointerpretthethermalfaulttypeswiththeoreticalthermodynamicassessments.Thisgasr

1 / 11
下载文档,编辑使用

©2015-2020 m.777doc.com 三七文档.

备案号:鲁ICP备2024069028号-1 客服联系 QQ:2149211541

×
保存成功