会员注册 | 登录 | 微信快捷登录 支付宝快捷登录 QQ登录 微博登录 | 帮助中心 人人文库renrendoc.com美如初恋!
站内搜索 百度文库

热门搜索: 直缝焊接机 矿井提升机 循环球式转向器图纸 机器人手爪发展史 管道机器人dwg 动平衡试验台设计

外文翻译--对有限元仿真数据的知识挖掘.doc外文翻译--对有限元仿真数据的知识挖掘.doc -- 5 元

宽屏显示 收藏 分享

资源预览需要最新版本的Flash Player支持。
您尚未安装或版本过低,建议您

翻译部分英文原文KNOWLEDGEDISCOVERYFROMFINITEELEMENTSIMULATIONDATAJILONGYIN,DAYONGLI,YINGCIftTNWANG,YINGHONGPENGInstituteofKnowledgebasedEngineering,SchoolofMechanical,ShanghaiJiaotongUniversity,Shanghai,200030,ChinaEMAILyinjilongsjtu,edu.cn,dylisjtu.edu.cn,yhpengsjtu.du.cnAbstractKnowledgebasedengineeringKBEandfiniteelementanalysisFEAhavebeenusedwidelyinsheetmetalformingarea.However,theacquisitionofknowledgekeepsbottleneckwhenbuildingknowledgebaseinKBE.Also,toproperlyunderstandtheresultsoftheFEAandconsequentlychoosetheappropriatedesign,alotofknowledgeandexperienceareneeded.FEAcangeneratemassivedata,inwhichlargeamountsofusefullyimplicitknowledgeishidden.Thus,knowledgeacquisitionfromthemisprospectivetoeasetheabovedifficultiesbyapplyingKnowledgeDiscoveryinDatabasesKDDtechnology.Inthisstudy,thecharacteristicsoftheFEAdataarediscussedfirstly.ThenaframeworkofknowledgediscoveryfromFEAdataisproposed.Correspondingly,adataminingalgorithmnamedfuzzyroughalgorithmisdevelopedtodealwiththeFEAsimulationdata.Finally,thestampingprocessofasquarecuppartwasstudiedasanexample.Theproposedknowledgediscoveryprocessisappliedtoobtainsomeuseful,implicitproductionruleswithefficiencymeasure.TheresultshowsthatknowledgediscoveryfromFEAsimulationdataisvaluable.KeywordsKnowledgediscoveryNumericalSimulationFuzzysetRoughsetRuleinduction1.IntroductionNowadays,KBEiswidelyusedinengineeringarea,whichintegratesartificialintelligencewithCAXsystemandconnectsengineeringdesignwithCAXsystemwithoutinterruption1.Greatly,aKnowledgeBasedEngineeringSystemsKBESperformancedependsonthescaleoftheknowledgebaseitpossesses.Knowledgeacquisitionremainsasthemaindifficultandcrucialproblem.Manualacquisitionneedshardworkofknowledgeengineersanddomainexperts,togetherwiththetightcorporationbetweenthem.Thequalityofacquiredknowledgeisusuallypoor.Therefore,thereisanurgentneedfornewknowledgeacquisitiontechniquesandtoolstoextractusefulknowledgefromtherapidlygrowingvolumesofdata.KDDisthenontrivialprocessofidentifying2valid,novel,potentiallyuseful,andultimatelyunderstandablepatternsindata.Itcanacquireimplicitandusefulknowledgeinlargescaledatasetsandhasmadegreatsuccessincommercialareas.Ithasexpandedtoengineeringdisciplines.TheoverallKDDprocessincludesdataselection,datapreprocessing,datatransformation,datamining,interpretationandevaluation,asshowninFigure1.Recently,numericalsimulationhasbecomethethirdmodeofsciencecomplementingtheoryandexperimentinalmostalloftheengineeringareas.FEAisthemostcommoncomputersimulationmethodinsheetmetalforminganalysis3.FEAsimulationsgeneratevastquantitiesofdata.TohelpthedesignersunderstandtheoutputofFEA,visualizationtechniquesareoftenusedtodisplaytheresults.However,thescaleoftheresultdataissolargethatvisualizationisfarfromsufficientresultdescription.Designershavetointerpretanalysisresultstodeterminewhetheradesignschemeisacceptable.Thisisalaboriousanderrorproneprocess,andrequiresasignificantamountofexperienceandexpertise.Ontheotherhand,themassiveresultdataimpliesmuchusefulknowledge,buttheyaresimplystoredawayondisksandneveranalyzedeffectively.SoextractingtheimplicitengineeringknowledgefromFEAresultsisverymeaningfulandurgent.Inthisstudy,thecharacteristicsoftheFEAdataarestudiedfirstly.ThenaframeworkforknowledgediscoveryfromFEAsimulationdataisproposed.Accordingtothecharacteristicsofthedata,afuzzyroughalgorithmisdeveloped.Finally,toverifythevalidityoftheframeworkandthealgorithm,thestampingprocessofasquarecupisanalyzedandtheconclusionisgiven.2.FrameworkofKnowledgeDiscoveryfromFEASimulationData2.1.CharacteristicsofFEASimulationDataThoughitisthesuccessofKDDincommercialareathatinterestsusinknowledgediscoveryfromFEAdata4,5,thereismuchdifferencebetweenthem.Firstly,simulationdataareusuallystoredinaflatfileorspecialformatdatabase,whilebusinessdataareoftenstoredincommercialdatabase6.TheaccessibilityandqueryofdataismoredifficultforFEAsimulationdatafilethanforcommercialdatabase.ToaccessthedatafromvariousCAXsystems,aspecialinterfacetoolkitmustbeused.Secondly,mostbusinessdatabasescontainstructureddataconsistingofwelldefinedfields.Eachvalueofthatattributeprovidesforthetargetlabel.However,FEAdataareintheformofmeshdatawithoutlabels.Valuesatameshpointarerealandcanbeelementcentered,nodecenteredoredgecentered7.Obviously,theyaresemistructuredorunstructured.Domainknowledgemustbeusedtoidentifythepatternfeature.Thirdly,unlikeinbusinessorproduction,thegenerationoftheFEAdatadoesnotrelyonexternaleventsandcanbecontrolledcompletely.ThusthedesignofexperimentsDOEcanbeappliedByDOEtechniques,fewersimulationdataisneededtoacquiremoreknowledge.Comparisonbetweensimulationsalsocanbemadetounderstandthedependenceofoutputdataonthedesignparameterspace.Therefore,amodifiedframeworkforknowledgediscoveryfromFEAsimulationdatamustbedevelopedandanappropriatedataminingalgorithmmustbedesignedtofitthecharacteristicsofFEAdata.2.2.TheProposedFrameworkAccordingtothecharacteristicsofFEAdata,amodifiedknowledgediscoveryframeworkisproposedasshowninFigure2.Thetotalframeworkiscomposedoffourpartsproductdesignanddevelopment,datacollection,knowledgediscovery,knowledgemanagementandreuse.Productdesignandprocessdevelopmentisthesequenceofactivitiestoturnopportunitiesandideasintosuccessfulproducts.Eachdesignwillbeexaminedbysimulationmethodorexperimentbeforeobtainingasuccessfulproduct.Tostudytherelationbetweenthedesignparametersandproductsperformance,DOEtechnologycanbeused.Intheiterativeprocessofproductdevelopment,largeamountofFEAsimulationdatarelatedtodesignparametersaregenerated.Thesedataareusuallystoredintoflatfilesorspecialformatdatabasesdispersedlyandcanbeusedasthedatasourceforknowledgediscovery.Duetothediversityofthedata,therefore,thesecondpartoftheframework,adatacollectorisusedtocollectthesedataandtransformsthemintoaunifieddatabase.ItshouldintegratevarioustoolstoexchangedataamongdifferentCAXCAD/CAEKAMsoftwareandknowledgediscoverysystem.Thethirdpartisknowledgediscovery,aniterativeprocessincludingfivebasicstepsdomainunderstanding,dataselectionandintegration,datapreprocessing,ruleinduction,knowledgeevaluationandinterpretation.Indomainunderstandingstage,everydatasetsconnotativemeaningandthemechanismbywhichtheyinteractshouldbeknownclearly.Theselecteddatawillbeusedandanalyzedtogiveananswertotheproblemunderconsideration.ToimprovethequalityofthedataforDMalgorithm,datapreprocessingmustbedone.Inruleinduction,intelligentmethodsareappliedinordertoextractdatapatterns.Productionrulesareselectedastheknowledgerepresentationforminthisstudyduetotheirmodularity,simplicityandexpandability.Thedataminingprocessmayberefinedandsomeofitsstepsbeiteratedseveraltimesbeforetheextractedknowledgecanbeused.Thefourthpartoftheframeisknowledgemanagementandreuse.Theminedknowledgeiscleanedupfirsttoeliminatetheredundancyandconflictsbeforestoringintoknowledgebase.Themindedknowledgecanbeappliedinthreeways.Firstly,itcanhelpdesignersunderstandsimulationresultclearly.Secondly,itcanbeusedasheuristicknowledgeinsearchingoptimaldesign.Thirdly,itcanbeusedasaknowledgeautoacquisitiontooltohelpknowledgeengineersinbuildingknowledgebase.Theframeworkitselfisalsoaniterativeprocess.Minedknowledgecanbereused,verifiedandrefreshedinthenextdesignloops.NewFEAsimulationdataaregeneratedandcanbeappendedintodatabaseasdatasourcefornextknowledgediscovery.Thus,theknowledgebasewillbecomemoreefficientandeasiertobeused.3.FuzzyroughsetsalgorithmTheroughsettheoryRSTproposedbyPawlakhasbeenusedwidelyinknowledgereasoningandknowledgeacquisition9.SincethebasicRSTalgorithmcanonlyhandlenominalfeatureindecisiontable,mostpreviousstudieshavejustshownhowbinaryorcrisptrainingdatamaybehandled10.ToapplyingtheRSTalgorithmonrealvaluedataset,discretizationoftenhastobeappliedasthepreprocessingsteptotransformthemintonominalfeaturespace11.Inthisstudy,animprovedalgorithmnamedfuzzyroughsetsalgorithmisdevelopedbyintegratingfuzzysettheorywithroughsettheory.ItcanactastheDMalgorithminknowledgediscoveryfromFEAsimulationdatatodealwithvarioustypesofdata.3.1.FuzzysetstheoryThefuzzysettheoryproposedbyZadehisconcernedwithquantifyingandreasoningusingnaturallanguageinwhichwordscanhaveambiguousmeanings11.LetUbeafiniteandnonemptysetcalleduniverse.AfuzzysetXinUisamembershipfunctionxux,whichtoeveryelementxinUassociatesarealnumberfromtheinterval0,I,andxuxisthegradeofmembershipofxinX.TheunionandintersectionoffuzzysetsXandYaredefinedasfollows,xyxyxUxMaxxx1,xyxyxUxMinxx21xyxxXxx3Fuzzynumbercanhandlesomeinaccurateinformationwithfuzzylanguagesuchastheforceisveryhigh,theformedpartisgood.3.2.RoughsetstheoryTheroughsettheorycanbetreatedasatoolfordatatableanalysisbyusingtheconceptsoflowerandupperapproximations.Consideringadecisiontable,SUAd,wheredAiscalledadecision
编号:201311171134095937    大小:578.19KB    格式:DOC    上传时间:2013-11-17
  【编辑】
5
关 键 词:
教育专区 外文翻译 精品文档 外文翻译
温馨提示:
1: 本站所有资源如无特殊说明,都需要本地电脑安装OFFICE2007和PDF阅读器。图纸软件为CAD,CAXA,PROE,UG,SolidWorks等.压缩文件请下载最新的WinRAR软件解压。
2: 本站的文档不包含任何第三方提供的附件图纸等,如果需要附件,请联系上传者。文件的所有权益归上传用户所有。
3.本站RAR压缩包中若带图纸,网页内容里面会有图纸预览,若没有图纸预览就没有图纸。
4. 未经权益所有人同意不得将文件中的内容挪作商业或盈利用途。
5. 人人文库网仅提供交流平台,并不能对任何下载内容负责。
6. 下载文件中如有侵权或不适当内容,请与我们联系,我们立即纠正。
7. 本站不保证下载资源的准确性、安全性和完整性, 同时也不承担用户因使用这些下载资源对自己和他人造成任何形式的伤害或损失。
  人人文库网所有资源均是用户自行上传分享,仅供网友学习交流,未经上传用户书面授权,请勿作他用。
0条评论

还可以输入200字符

暂无评论,赶快抢占沙发吧。

当前资源信息

4.0
 
(2人评价)
浏览:22次
英文资料库上传于2013-11-17

官方联系方式

客服手机:13961746681   
2:不支持迅雷下载,请使用浏览器下载   
3:不支持QQ浏览器下载,请用其他浏览器   
4:下载后的文档和图纸-无水印   
5:文档经过压缩,下载后原文更清晰   

相关资源

相关资源

相关搜索

教育专区   外文翻译   精品文档   外文翻译  
关于我们 - 网站声明 - 网站地图 - 友情链接 - 网站客服客服 - 联系我们
copyright@ 2015-2017 人人文库网网站版权所有
苏ICP备12009002号-5