




已閱讀5頁,還剩16頁未讀, 繼續(xù)免費(fèi)閱讀
版權(quán)說明:本文檔由用戶提供并上傳,收益歸屬內(nèi)容提供方,若內(nèi)容存在侵權(quán),請(qǐng)進(jìn)行舉報(bào)或認(rèn)領(lǐng)
文檔簡(jiǎn)介
翻譯部分英文原文:KNOWLEDGEDISCOVERYFROMFINITEELEMENTSIMULATIONDATAJI-LONGYIN,DA-YONGLI,YING-CIftTNWANG,YING-HONGPENGInstituteofKnowledge-basedEngineering,SchoolofMechanical,ShanghaiJiaotongUniversity,Shanghai,200030,ChinaE-MAIL:yinjilongsjtu,,,Abstract:Knowledge-basedengineering(KBE)andfiniteelementanalysis(FEA)havebeenusedwidelyinsheetmetalformingarea.However,theacquisitionofknowledgekeepsbottleneckwhenbuildingknowledgebaseinKBE.Also,toproperlyunderstandtheresultsoftheFEAandconsequentlychoosetheappropriatedesign,alotofknowledgeandexperienceareneeded.FEAcangeneratemassivedata,inwhichlargeamountsofusefullyimplicitknowledgeishidden.Thus,knowledgeacquisitionfromthemisprospectivetoeasetheabovedifficultiesbyapplyingKnowledgeDiscoveryinDatabases(KDD)technology.Inthisstudy,thecharacteristicsoftheFEAdataarediscussedfirstly.ThenaframeworkofknowledgediscoveryfromFEAdataisproposed.Correspondingly,adata-miningalgorithmnamedfuzzy-roughalgorithmisdevelopedtodealwiththeFEAsimulationdata.Finally,thestampingprocessofasquare-cuppartwasstudiedasanexample.Theproposedknowledgediscoveryprocessisappliedtoobtainsomeuseful,implicitproductionruleswithefficiencymeasure.TheresultshowsthatknowledgediscoveryfromFEAsimulationdataisvaluable.Keywords:Knowledgediscovery;NumericalSimulation;Fuzzyset;Roughset;Ruleinduction1.IntroductionNowadays,KBEiswidelyusedinengineeringarea,whichintegratesartificialintelligencewithCAXsystemandconnectsengineeringdesignwithCAXsystemwithoutinterruption1.Greatly,aKnowledge-BasedEngineeringSystems(KBES)performancedependsonthescaleoftheknowledgebaseitpossesses.Knowledgeacquisitionremainsasthemaindifficultandcrucialproblem.Manualacquisitionneedshardworkofknowledgeengineersanddomainexperts,togetherwiththetightcorporationbetweenthem.Thequalityofacquiredknowledgeisusuallypoor.Therefore,thereisanurgentneedfornewknowledgeacquisitiontechniquesandtoolstoextractusefulknowledgefromtherapidlygrowingvolumesofdata.KDDisthenon-trivialprocessofidentifying2valid,novel,potentiallyuseful,andultimatelyunderstandablepatternsindata.Itcanacquireimplicitandusefulknowledgeinlarge-scaledatasetsandhasmadegreatsuccessincommercialareas.Ithasexpandedtoengineeringdisciplines.TheoverallKDDprocessincludesdataselection,datapreprocessing,datatransformation,datamining,interpretationandevaluation,asshowninFigure1.Recently,numericalsimulationhasbecomethethirdmodeofsciencecomplementingtheoryandexperimentinalmostalloftheengineeringareas.FEAisthemostcommoncomputersimulationmethodinsheetmetalforminganalysis3.FEAsimulationsgeneratevastquantitiesofdata.TohelpthedesignersunderstandtheoutputofFEA,visualizationtechniquesareoftenusedtodisplaytheresults.However,thescaleoftheresultdataissolargethatvisualizationisfarfromsufficientresultdescription.Designershavetointerpretanalysisresultstodeterminewhetheradesignschemeisacceptable.Thisisalaboriousanderror-proneprocess,andrequiresasignificantamountofexperienceandexpertise.Ontheotherhand,themassiveresultdataimpliesmuchusefulknowledge,buttheyaresimplystoredawayondisksandneveranalyzedeffectively.SoextractingtheimplicitengineeringknowledgefromFEAresultsisverymeaningfulandurgent.Inthisstudy,thecharacteristicsoftheFEAdataarestudiedfirstly.ThenaframeworkforknowledgediscoveryfromFEAsimulationdataisproposed.Accordingtothecharacteristicsofthedata,afuzzy-roughalgorithmisdeveloped.Finally,toverifythevalidityoftheframeworkandthealgorithm,thestampingprocessofasquarecupisanalyzedandtheconclusionisgiven.2.FrameworkofKnowledgeDiscoveryfromFEASimulationData2.1.CharacteristicsofFEASimulationDataThoughitisthesuccessofKDDincommercialareathatinterestsusinknowledgediscoveryfromFEAdata4,5,thereismuchdifferencebetweenthem.Firstly,simulationdataareusuallystoredinaflatfileorspecialformatdatabase,whilebusinessdataareoftenstoredincommercialdatabase6.TheaccessibilityandqueryofdataismoredifficultforFEAsimulationdatafilethanforcommercialdatabase.ToaccessthedatafromvariousCAXsystems,aspecialinterfacetoolkitmustbeused.Secondly,mostbusinessdatabasescontainstructureddataconsistingofwell-definedfields.Eachvalueofthatattributeprovidesforthetargetlabel.However,FEAdataareintheformofmeshdatawithoutlabels.Valuesatameshpointarerealandcanbeelement-centered,node-centeredoredge-centered7.Obviously,theyaresemi-structuredorunstructured.Domainknowledgemustbeusedtoidentifythepatternfeature.Thirdly,unlikeinbusinessorproduction,thegenerationoftheFEAdatadoesnotrelyonexternaleventsandcanbecontrolledcompletely.Thusthedesignofexperiments(DOE)canbeappliedByDOEtechniques,fewersimulationdataisneededtoacquiremoreknowledge.Comparisonbetweensimulationsalsocanbemadetounderstandthedependenceofoutputdataonthedesignparameterspace.Therefore,amodifiedframeworkforknowledgediscoveryfromFEAsimulationdatamustbedevelopedandanappropriatedata-miningalgorithmmustbedesignedtofitthecharacteristicsofFEAdata.2.2.TheProposedFrameworkAccordingtothecharacteristicsofFEAdata,amodifiedknowledgediscoveryframeworkisproposedasshowninFigure2.Thetotalframeworkiscomposedoffourparts:productdesignanddevelopment,data-collection,knowledgediscovery,knowledgemanagementandreuse.Productdesignandprocessdevelopmentisthesequenceofactivitiestoturnopportunitiesandideasintosuccessfulproducts.Eachdesignwillbeexaminedbysimulationmethodorexperimentbeforeobtainingasuccessfulproduct.Tostudytherelationbetweenthedesignparametersandproductsperformance,DOEtechnologycanbeused.Intheiterativeprocessofproductdevelopment,largeamountofFEAsimulationdatarelatedtodesignparametersaregenerated.Thesedataareusuallystoredintoflatfilesorspecialformatdatabasesdispersedlyandcanbeusedasthedatasourceforknowledgediscovery.Duetothediversityofthedata,therefore,thesecondpartoftheframework,adatacollectorisusedtocollectthesedataandtransformsthemintoaunifieddatabase.ItshouldintegratevarioustoolstoexchangedataamongdifferentCAX(CAD/CAEKAM)softwareandknowledgediscoverysystem.Thethirdpartisknowledgediscovery,aniterativeprocessincludingfivebasicsteps:domainunderstanding,dataselectionandintegration,datapre-processing,ruleinduction,knowledgeevaluationandinterpretation.Indomainunderstandingstage,everydatasetsconnotativemeaningandthemechanismbywhichtheyinteractshouldbeknownclearly.Theselecteddatawillbeusedandanalyzedtogiveananswertotheproblemunderconsideration.ToimprovethequalityofthedataforDMalgorithm,datapre-processingmustbedone.Inruleinduction,intelligentmethodsareappliedinordertoextractdatapatterns.Productionrulesareselectedastheknowledgerepresentationforminthisstudyduetotheirmodularity,simplicityandexpandability.Thedataminingprocessmayberefinedandsomeofitsstepsbeiteratedseveraltimesbeforetheextractedknowledgecanbeused.Thefourthpartoftheframeisknowledgemanagementandreuse.Theminedknowledgeiscleanedupfirsttoeliminatetheredundancyandconflictsbeforestoringintoknowledgebase.Themindedknowledgecanbeappliedinthreeways.Firstly,itcanhelpdesignersunderstandsimulationresultclearly.Secondly,itcanbeusedasheuristicknowledgeinsearchingoptimaldesign.Thirdly,itcanbeusedasaknowledgeauto-acquisitiontooltohelpknowledgeengineersinbuildingknowledgebase.Theframeworkitselfisalsoaniterativeprocess.Minedknowledgecanbereused,verifiedandrefreshedinthenextdesignloops.NewFEAsimulationdataaregeneratedandcanbeappendedintodatabaseasdatasourcefornextknowledgediscovery.Thus,theknowledgebasewillbecomemoreefficientandeasiertobeused.3.Fuzzy-roughsetsalgorithmTherough-settheory(RST)proposedbyPawlakhasbeenusedwidelyinknowledgereasoningandknowledgeacquisition9.SincethebasicRSTalgorithmcanonlyhandlenominalfeatureindecisiontable,mostpreviousstudieshavejustshownhowbinaryorcrisptrainingdatamaybehandled10.ToapplyingtheRSTalgorithmonrealvaluedataset,discretizationoftenhastobeappliedasthepreprocessingsteptotransformthemintonominalfeaturespace11.Inthisstudy,animprovedalgorithmnamedfuzzy-roughsetsalgorithmisdevelopedbyintegra
溫馨提示
- 1. 本站所有資源如無特殊說明,都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請(qǐng)下載最新的WinRAR軟件解壓。
- 2. 本站的文檔不包含任何第三方提供的附件圖紙等,如果需要附件,請(qǐng)聯(lián)系上傳者。文件的所有權(quán)益歸上傳用戶所有。
- 3. 本站RAR壓縮包中若帶圖紙,網(wǎng)頁內(nèi)容里面會(huì)有圖紙預(yù)覽,若沒有圖紙預(yù)覽就沒有圖紙。
- 4. 未經(jīng)權(quán)益所有人同意不得將文件中的內(nèi)容挪作商業(yè)或盈利用途。
- 5. 人人文庫(kù)網(wǎng)僅提供信息存儲(chǔ)空間,僅對(duì)用戶上傳內(nèi)容的表現(xiàn)方式做保護(hù)處理,對(duì)用戶上傳分享的文檔內(nèi)容本身不做任何修改或編輯,并不能對(duì)任何下載內(nèi)容負(fù)責(zé)。
- 6. 下載文件中如有侵權(quán)或不適當(dāng)內(nèi)容,請(qǐng)與我們聯(lián)系,我們立即糾正。
- 7. 本站不保證下載資源的準(zhǔn)確性、安全性和完整性, 同時(shí)也不承擔(dān)用戶因使用這些下載資源對(duì)自己和他人造成任何形式的傷害或損失。
最新文檔
- 火鍋餐飲行業(yè)2025年火鍋餐飲市場(chǎng)競(jìng)爭(zhēng)力研究報(bào)告
- 智能家居系統(tǒng)集成項(xiàng)目在2025年智能家居租賃市場(chǎng)的應(yīng)用可行性分析
- 老齡化趨勢(shì)下2025年老年長(zhǎng)期照護(hù)服務(wù)模式與社區(qū)養(yǎng)老機(jī)構(gòu)服務(wù)模式創(chuàng)新報(bào)告
- 食品添加劑在食品色澤改善中的安全性評(píng)估與合規(guī)性分析報(bào)告
- 2025年元宇宙社交平臺(tái)界面設(shè)計(jì)創(chuàng)新與實(shí)踐案例分析報(bào)告
- 醫(yī)療行業(yè)大數(shù)據(jù)隱私保護(hù)在2025年醫(yī)療數(shù)據(jù)安全風(fēng)險(xiǎn)評(píng)估與控制策略中的應(yīng)用報(bào)告
- 有機(jī)食品市場(chǎng)細(xì)分領(lǐng)域投資機(jī)會(huì)與風(fēng)險(xiǎn)評(píng)估報(bào)告
- 2025年醫(yī)藥企業(yè)研發(fā)外包(CRO)與臨床試驗(yàn)國(guó)際化合作報(bào)告001
- 2025年國(guó)際教育交流項(xiàng)目學(xué)生跨文化心理調(diào)適與心理健康研究報(bào)告
- 2025年北京市燕山區(qū)七下英語期中達(dá)標(biāo)檢測(cè)試題含答案
- 2024年山東省夏季普通高中學(xué)業(yè)水平合格考試歷史試卷
- 園藝論文開題報(bào)告范文
- 數(shù)據(jù)質(zhì)量管理實(shí)施手冊(cè)
- 林業(yè)工程開工申請(qǐng)
- 清華大學(xué)《大學(xué)物理》各章節(jié)習(xí)題庫(kù)及答案合集
- 《設(shè)備找正找平》課件
- 2024年度小紅書商業(yè)MCN機(jī)構(gòu)經(jīng)營(yíng)洞察報(bào)告
- 寵物醫(yī)院服務(wù)行業(yè)可行性分析報(bào)告
- 輸液港的輸液與維護(hù)
- 口腔科護(hù)理人文關(guān)懷
- 高等教育信息化建設(shè)方案
評(píng)論
0/150
提交評(píng)論