夾具設(shè)計(jì)外文翻譯-采用遺傳算法優(yōu)化加工夾具定位和加緊位置

附錄MachiningfixturelocatingandclampingpositionoptimizationusinggeneticalgorithmsNecmettinKaya*DepartmentofMechanicalEngineering,UludagUniversity,Go¨ru¨kle,Bursa16059,TurkeyReceived8July2004;accepted26May2005Availableonline6September2005AbstractDeformationoftheworkpiecemaycausedimensionalproblemsinmachining.Supportsandlocatorsareusedinordertoreducetheerrorcausedbyelasticdeformationoftheworkpiece.Theoptimizationofsupport,locatorandclamplocationsisacriticalproblemtominimizethegeometricerrorinworkpiecemachining.Inthispaper,theapplicationofgeneticalgorithms(GAs)tothefixturelayoutoptimizationispresentedtohandlefixturelayoutoptimizationproblem.Ageneticalgorithmbasedapproachisdevelopedtooptimisefixturelayoutthroughintegratingafiniteelementcoderunninginbatchmodetocomputetheobjectivefunctionvaluesforeachgeneration.Casestudiesaregiventoillustratetheapplicationofproposedapproach.Chromosomelibraryapproachisusedtodecreasethetotalsolutiontime.DevelopedGAkeepstrackofpreviouslyanalyzeddesigns;thereforethenumbersoffunctionevaluationsaredecreasedabout93%.Theresultsofthisapproachshowthatthefixturelayoutoptimizationproblemsaremulti-modalproblems.Optimizeddesignsdonothaveanyapparentsimilaritiesalthoughtheyprovideverysimilarperformances.Keywords:Fixturedesign;Geneticalgorithms;Optimization1.IntroductionFixturesareusedtolocateandconstrainaworkpieceduringamachiningoperation,minimizingworkpieceandfixturetoolingdeflectionsduetoclampingandcuttingforcesarecriticaltoensuringaccuracyofthemachiningoperation.Traditionally,machiningfixturesaredesignedandmanufacturedthroughtrial-and-error,whichprovetobebothexpensiveandtime-consumingtothemanufacturingprocess.Toensureaworkpieceismanufacturedaccordingtospecifieddimensionsandtolerances,itmustbeappropriatelylocatedandclamped,makingitimperativetodeveloptoolsthatwilleliminatecostlyandtime-consumingtrial-and-errordesigns.Properworkpiecelocationandfixturedesignarecrucialtoproductqualityintermsofprecision,accuracyandfinishofthemachinedpart.Theoretically,the3-2-1locatingprinciplecansatisfactorilylocateallprismaticshapedworkpieces.Thismethodprovidesthemaximumrigiditywiththeminimumnumberoffixtureelements.Topositionapartfromakinematicpointofviewmeansconstrainingthesixdegreesoffreedomofafreemovingbody(threetranslationsandthreerotations).Threesupportsarepositionedbelowtheparttoestablishthelocationoftheworkpieceonitsverticalaxis.Locatorsareplacedontwoperipheraledgesandintendedtoestablishthelocationoftheworkpieceonthexandyhorizontalaxes.Properlylocatingtheworkpieceinthefixtureisvitaltotheoverallaccuracyandrepeatabilityofthemanufacturingprocess.Locatorsshouldbepositionedasfarapartaspossibleandshouldbeplacedonmachinedsurfaceswhereverpossible.Supportsareusuallyplacedtoencompassthecenterofgravityofaworkpieceandpositionedasfarapartaspossibletomaintainitsstability.Theprimaryresponsibilityofaclampinfixtureistosecurethepartagainstthelocatorsandsupports.Clampsshouldnotbeexpectedtoresistthecuttingforcesgeneratedinthemachiningoperation.Foragivennumberoffixtureelements,themachiningfixturesynthesisproblemisthefindingoptimallayoutorpositionsofthefixtureelementsaroundtheworkpiece.Inthispaper,amethodforfixturelayoutoptimizationusinggeneticalgorithmsispresented.Theoptimizationobjectiveistosearchfora2Dfixturelayoutthatminimizesthemaximumelasticdeformationatdifferentlocationsoftheworkpiece.ANSYSprogramhasbeenusedforcalculatingthedeflectionofthepartunderclampingandcuttingforces.Twocasestudiesaregiventoillustratetheproposedapproach.2.ReviewofrelatedworksFixturedesignhasreceivedconsiderableattentioninrecentyears.However,littleattentionhasbeenfocusedontheoptimumfixturelayoutdesign.MenassaandDeVries[1]usedFEAforcalculatingdeflectionsusingtheminimizationoftheworkpiecedeflectionatselectedpointsasthedesigncriterion.Thedesignproblemwastodeterminethepositionofsupports.MeyerandLiou[2]presentedanapproachthatuseslinearprogrammingtechniquetosynthesizefixturesfordynamicmachiningconditions.Solutionfortheminimumclampingforcesandlocatorforcesisgiven.LiandMelkote[3]usedanonlinearprogrammingmethodtosolvethelayoutoptimizationproblem.Themethodminimizesworkpiecelocationerrorsduetolocalizedelasticdeformationoftheworkpiece.RoyandLiao[4]developedaheuristicmethodtoplanforthebestsupportingandclampingpositions.Taoetal.[5]presentedageometricalreasoningmethodologyfordeterminingtheoptimalclampingpointsandclampingsequenceforarbitrarilyshapedworkpieces.LiaoandHu[6]presentedasystemforfixtureconfigurationanalysisbasedonadynamicmodelwhichanalysesthefixture–workpiecesystemsubjecttotime-varyingmachiningloads.Theinfluenceofclampingplacementisalsoinvestigated.LiandMelkote[7]presentedafixturelayoutandclampingforceoptimalsynthesisapproachthataccountsforworkpiecedynamicsduringmachining.Acombinedfixturelayoutandclampingforceoptimizationprocedurepresented.Theyusedthecontactelasticitymodelingmethodthataccountsfortheinfluenceofworkpiecerigidbodydynamicsduringmachining.Amaraletal.[8]usedANSYStoverifyfixturedesignintegrity.Theyemployed3-2-1method.TheoptimizationanalysisisperformedinANSYS.Tanetal.[9]describedthemodeling,analysisandverificationofoptimalfixturingconfigurationsbythemethodsofforceclosure,optimizationandfiniteelementmodeling.Mostoftheabovestudiesuselinearornonlinearprogrammingmethodswhichoftendonotgiveglobaloptimumsolution.Allofthefixturelayoutoptimizationproceduresstartwithaninitialfeasiblelayout.Solutionsfromthesemethodsaredependingontheinitialfixturelayout.Theydonotconsiderthefixturelayoutoptimizationonoverallworkpiecedeformation.TheGAshasbeenproventobeusefultechniqueinsolvingoptimizationproblemsinengineering[10–12].Fixturedesignhasalargesolutionspaceandrequiresasearchtooltofindthebestdesign.FewresearchershaveusedtheGAsforfixturedesignandfixturelayoutproblems.Kumaretal.[13]haveappliedbothGAsandneuralnetworksfordesigningafixture.Marcelin[14]hasusedGAstotheoptimizationofsupportpositions.Vallapuzhaetal.[15]presentedGAbasedoptimizationmethodthatusesspatialcoordinatestorepresentthelocationsoffixtureelements.FixturelayoutoptimizationprocedurewasimplementedusingMATLABandthegeneticalgorithmtoolbox.HYPERMESHandMSC/NASTRANwereusedforFEmodel.Vallapuzhaetal.[16]presentedresultsofanextensiveinvestigationintotherelativeeffectivenessofvariousoptimizationmethods.TheyshowedthatcontinuousGAyieldedthebestqualitysolutions.LiandShiu[17]determinedtheoptimalfixtureconfigurationdesignforsheetmetalassemblyusingGA.MSC/NASTRANhasbeenusedforfitnessevaluation.Liao[18]presentedamethodtoautomaticallyselecttheoptimalnumbersoflocatorsandclampsaswellastheiroptimalpositionsinsheetmetalassemblyfixtures.KrishnakumarandMelkote[19]developedafixturelayoutoptimizationtechniquethatusestheGAtofindthefixturelayoutthatminimizesthedeformationofthemachinedsurfaceduetoclampingandmachiningforcesovertheentiretoolpath.Locatorandclamppositionsarespecifiedbynodenumbers.Abuilt-infiniteelementsolverwasdeveloped.Someofthestudiesdonotconsidertheoptimizationofthelayoutforentiretoolpathandchipremovalisnottakenintoaccount.Someofthestudiesusednodenumbersasdesignparameters.Inthisstudy,aGAtoolhasbeendevelopedtofindtheoptimallocatorandclamppositionsin2Dworkpiece.DistancesfromthereferenceedgesasdesignparametersareusedratherthanFEAnodenumbers.FitnessvaluesofrealencodedGAchromosomesareobtainedfromtheresultsofFEA.ANSYShasbeenusedforFEAcalculations.Achromosomelibraryapproachisusedinordertodecreasethesolutiontime.DevelopedGAtoolistestedontwotestproblems.Twocasestudiesaregiventoillustratethedevelopedapproach.Maincontributionsofthispapercanbesummarizedasfollows:(1)developedaGAcodeintegratedwithacommercialfiniteelementsolver;(2)GAuseschromosomelibraryinordertodecreasethecomputationtime;(3)realdesignparametersareusedratherthanFEAnodenumbers;(4)chipremovalistakenintoaccountwhiletoolforcesmovingontheworkpiece.3.GeneticalgorithmconceptsGeneticalgorithmswerefirstdevelopedbyJohnHolland.Goldberg[10]publishedabookexplainingthetheoryandapplicationexamplesofgeneticalgorithmindetails.Ageneticalgorithmisarandomsearchtechniquethatmimicssomemechanismsofnaturalevolution.Thealgorithmworksonapopulationofdesigns.Thepopulationevolvesfromgenerationtogeneration,graduallyimprovingitsadaptationtotheenvironmentthroughnaturalselection;fitterindividualshavebetterchancesoftransmittingtheircharacteristicstolatergenerations.Inthealgorithm,theselectionofthenaturalenvironmentisreplacedbyartificialselectionbasedonacomputedfitnessforeachdesign.Thetermfitnessisusedtodesignatethechromosome’schancesofsurvivalanditisessentiallytheobjectivefunctionoftheoptimizationproblem.Thechromosomesthatdefinecharacteristicsofbiologicalbeingsarereplacedbystringsofnumericalvaluesrepresentingthedesignvariables.GAisrecognizedtobedifferentthantraditionalgradientbasedoptimizationtechniquesinthefollowingfourmajorways[10]:1.GAsworkwithacodingofthedesignvariablesandparametersintheproblem,ratherthanwiththeactualparametersthemselves.2.GAsmakesuseofpopulation-typesearch.Manydifferentdesignpointsareevaluatedduringeachiterationinsteadofsequentiallymovingfromonepointtothenext.3.GAsneedsonlyafitnessorobjectivefunctionvalue.Noderivativesorgradientsarenecessary.4.GAsuseprobabilistictransitionrulestofindnewdesignpointsforexplorationratherthanusingdeterministicrulesbasedongradientinformationtofindthesenewpoints.4.Approach4.1.FixturepositioningprinciplesInmachiningprocess,fixturesareusedtokeepworkpiecesinadesirablepositionforoperations.Themostimportantcriteriaforfixturingareworkpiecepositionaccuracyandworkpiecedeformation.Agoodfixturedesignminimizesworkpiecegeometricandmachiningaccuracyerrors.Anotherfixturingrequirementisthatthefixturemustlimitdeformationoftheworkpiece.Itisimportanttoconsiderthecuttingforcesaswellastheclampingforces.Withoutadequatefixturesupport,machiningoperationsdonotconformtodesignedtolerances.Finiteelementanalysisisapowerfultoolintheresolutionofsomeoftheseproblems[22].Commonlocatingmethodforprismaticpartsis3-2-1method.Thismethodprovidesthemaximumrigiditywiththeminimumnumberoffixtureelements.Aworkpiecein3Dmaybepositivelylocatedbymeansofsixpointspositionedsothattheyrestrictninedegreesoffreedomoftheworkpiece.Theotherthreedegreesoffreedomareremovedbyclampelements.Anexamplelayoutfor2Dworkpiecebased3-2-1locatingprincipleisshowninFig.4.Fig.4.3-2-1locatinglayoutfor2DprismaticworkpieceThenumberoflocatingfacesmustnotexceedtwosoastoavoidaredundantlocation.Basedonthe3-2-1fixturingprincipletherearetwolocatingplanesforaccuratelocationcontainingtwoandonelocators.Therefore,therearemaximumoftwosideclampingsagainsteachlocatingplane.Clampingforcesarealwaysdirectedtowardsthelocatorsinordertoforcetheworkpiecetocontactalllocators.Theclampingpointshouldbepositionedoppositethepositioningpointstopreventtheworkpiecefrombeingdistortedbytheclampingforce.Sincethemachiningforcestravelalongthemachiningarea,itisnecessarytoensurethatthereactionforcesatlocatorsarepositiveforallthetime.Anynegativereactionforceindicatesthattheworkpieceisfreefromfixtureelements.Inotherwords,lossofcontactortheseparationbetweentheworkpieceandfixtureelementmighthappenwhenthereactionforceisnegative.Positivereactionforcesatthelocatorsensurethattheworkpiecemaintainscontactwithallthelocatorsfromthebeginningofthecuttotheend.Theclampingforcesshouldbejustsufficienttoconstrainandlocatetheworkpiecewithoutcausingdistortionordamagetotheworkpiece.Clampingforceoptimizationisnotconsideredinthispaper.4.2.GeneticalgorithmbasedfixturelayoutoptimizationapproachInrealdesignproblems,thenumberofdesignparameterscanbeverylargeandtheirinfluenceontheobjectivefunctioncanbeverycomplicated.Theobjectivefunctionmustbesmoothandaprocedureisneededtocomputegradients.Geneticalgorithmsstronglydifferinconceptionfromothersearchmethods,includingtraditionaloptimizationmethodsandotherstochasticmethods[23].ByapplyingGAstofixturelayoutoptimization,anoptimalorgroupofsub-optimalsolutionscanbeobtained.Inthisstudy,optimumlocatorandclamppositionsaredeterminedusinggeneticalgorithms.Theyareideallysuitedforthefixturelayoutoptimizationproblemsincenodirectanalyticalrelationshipexistsbetweenthemachiningerrorandthefixturelayout.SincetheGAdealswithonlythedesignvariablesandobjectivefunctionvalueforaparticularfixturelayout,nogradientorauxiliaryinformationisneeded[19].TheflowchartoftheproposedapproachisgiveninFig.5.FixturelayoutoptimizationisimplementedusingdevelopedsoftwarewritteninDelphilanguagenamedGenFix.DisplacementvaluesarecalculatedinANSYSsoftware[24].TheexecutionofANSYSinGenFixissimplydonebyWinExecfunctioninDelphi.TheinteractionbetweenGenFixandANSYSisimplementedinfoursteps:(1)Locatorandclamppositionsareextractedfrombinarystringasrealparameters.(2)TheseparametersandANSYSinputbatchfile(modeling,solutionandpostprocessingcommands)aresenttoANSYSusingWinExecfunction.(3)Displacementvaluesarewrittentoatextfileaftersolution.(4)GenFixreadsthisfileandcomputesfitnessvalueforcurrentlocatorandclamppositions.Inordertoreducethecomputationtime,chromosomesandfitnessvaluesarestoredinalibraryforfurtherevaluation.GenFixfirstchecksifcurrentchromosome’sfitnessvaluehasbeencalculatedbefore.Ifnot,locatorpositionsaresenttoANSYS,otherwisefitnessvaluesaretakenfromthelibrary.Duringgeneratingoftheinitialpopulation,everychromosomeischeckedwhetheritisfeasibleornot.Iftheconstraintisviolated,itiseliminatedandnewchromosomeiscreated.Thisprocesscreatesentirelyfeasibleinitialpopulation.Thisensuresthatworkpieceisstableundertheactionofclampingandcuttingforcesforeverychromosomeintheinitialpopulation.ThewrittenGAprogramwasvalidatedusingtwotestcases.ThefirsttestcaseusesHimmelblaufunction[21].Inthesecondtestcase,theGAprogramwasusedtooptimisethesupportpositionsofabeamunderuniformloading.5.FixturelayoutoptimizationcasestudiesThefixturelayoutoptimizationproblemisdefinedas:findingthepositionsofthelocatorsandclamps,sothatworkpiecedeformationatspecificregionisminimized.Notethatnumberoflocatorsandclampsarenotdesignparameter,sincetheyareknownandfixedforthe3-2-1locatingscheme.Hence,thedesignparametersareselectedaslocatorandclamppositions.Frictionisnotconsideredinthispaper.Twocasestudiesaregiventoillustratetheproposedapproach.6.ConclusionInthispaper,anevolutionaryoptimizationtechniqueoffixturelayoutoptimizationispresented.ANSYShasbeenusedforFEcalculationoffitnessvalues.ItisseenthatthecombinedgeneticalgorithmandFEmethodapproachseemstobeapowerfulapproachforpresenttypeproblems.GAapproachisparticularlysuitedforproblemswheretheredoesnotexistawell-definedmathematicalrelationshipbetweentheobjectivefunctionandthedesignvariables.TheresultsprovethesuccessoftheapplicationofGAsforthefixturelayoutoptimizationproblems.Inthisstudy,themajorobstacleforGAapplicationinfixturelayoutoptimizationisthehighcomputationcost.Re-meshingoftheworkpieceisrequiredforeverychromosomeinthepopulation.But,usagesofchromosomelibrary,thenumberofFEevaluationsaredecreasedfrom6000to415.Thisresultsinatremendousgainincomputationalefficiency.Theotherwaytodecreasethesolutiontimeistousedistributedcomputationinalocalareanetwork.Theresultsofthisapproachshowthatthefixturelayoutoptimizationproblemsaremulti-modalproblems.Optimizeddesignsdonothaveanyapparentsimilaritiesalthoughtheyprovideverysimilarperformances.Itisshownthatfixturelayoutproblemsaremulti-modalthereforeheuristicrulesforfixturedesignshouldbeusedinGAtoselectbestdesignamongothers.Fig.5.TheflowchartoftheproposedmethodologyandANSYSinterface.采用遺傳算法優(yōu)化加工夾具定位和加緊位置摘要：工件變形的問(wèn)題可能導(dǎo)致機(jī)械加工中的空間問(wèn)題。支撐和定位器是用于減少工件彈性變形引起的誤差。支撐、定位器的優(yōu)化和夾具定位是最大限度的減少幾何在工件加工中的誤差的一個(gè)關(guān)鍵問(wèn)題。本文應(yīng)用夾具布局優(yōu)化遺傳算法〔GAs〕來(lái)處理夾具布局優(yōu)化問(wèn)題。遺傳算法的方法是基于一種通過(guò)整合有限的運(yùn)行于批處理模式的每一代的目標(biāo)函數(shù)值的元素代碼的方法，用于來(lái)優(yōu)化夾具布局。給出的個(gè)案研究說(shuō)明已開(kāi)發(fā)的方法的應(yīng)用。采用染色體文庫(kù)方法減少整體解決問(wèn)題的時(shí)間。已開(kāi)發(fā)的遺傳算法保持跟蹤先前的分析設(shè)計(jì)，因此先前的分析功能評(píng)價(jià)的數(shù)量降低大約93%。結(jié)果說(shuō)明，該方法的夾具布局優(yōu)化問(wèn)題是多模式的問(wèn)題。優(yōu)化設(shè)計(jì)之間沒(méi)有任何明顯的相似之處，雖然它們提供非常相似的表現(xiàn)。關(guān)鍵詞：夾具設(shè)計(jì)；遺傳算法；優(yōu)化1.引言?shī)A具用來(lái)定位和束縛機(jī)械操作中的工件，減少由于對(duì)確保機(jī)械操作準(zhǔn)確性的夾緊方案和切削力造成的工件和夾具的變形。傳統(tǒng)上，加工夾具是通過(guò)反復(fù)試驗(yàn)法來(lái)設(shè)計(jì)和制造的，這是一個(gè)既造價(jià)高又耗時(shí)的制造過(guò)程。為確保工件按規(guī)定尺寸和公差來(lái)制造，工件必須給予適當(dāng)?shù)亩ㄎ缓蛫A緊以確保有必要開(kāi)發(fā)工具來(lái)消除高造價(jià)和耗時(shí)的反復(fù)試驗(yàn)設(shè)計(jì)方法。適當(dāng)?shù)墓ぜㄎ缓蛫A具設(shè)計(jì)對(duì)于產(chǎn)品質(zhì)量的精密度、準(zhǔn)確度和機(jī)制件的完飾是至關(guān)重要的。從理論上說(shuō)，3-2-1定位原那么對(duì)于定位所有的棱柱形零件是很令人滿意的。該方法具有最大的剛性與最少量的夾具元件。從動(dòng)力學(xué)觀點(diǎn)來(lái)看定位零件意味著限制了自由移動(dòng)物體的六自由度〔三個(gè)平動(dòng)自由度和三個(gè)旋轉(zhuǎn)自由度〕。在零件下部設(shè)置三個(gè)支撐來(lái)建立工件在垂直軸方向的定位。在兩個(gè)外圍邊緣放置定位器旨在建立工件在水平x軸和y軸的定位。正確定位夾具的工件對(duì)于制造過(guò)程的全面準(zhǔn)確性和重復(fù)性是至關(guān)重要的。定位器應(yīng)該盡可能的遠(yuǎn)距離的分開(kāi)放置并且應(yīng)該放在任何可能的加工面上。放置的支撐器通常用來(lái)包圍工件的重力中心并且盡可能的將其分開(kāi)放置以維持其穩(wěn)定性。夾具夾子的首要任務(wù)是固定夾具以抵抗定位器和支撐器。不應(yīng)該要求夾子對(duì)抗加工操作中的切削力。對(duì)于給定數(shù)量的夾具元件，加工夾具合成的問(wèn)題是尋找?jiàn)A具優(yōu)化布局或工件周?chē)鷬A具元件的位置。本篇文章提出一種優(yōu)化夾具布局遺傳算法。優(yōu)化目標(biāo)是研究一個(gè)二維夾具布局使工件不同位置上最大的彈性變形最小化。ANSYS程序以用于計(jì)算工件變形情況下夾緊力和切削力。本文給出兩個(gè)實(shí)例來(lái)說(shuō)明給出的方法。2.回憶相關(guān)工程結(jié)構(gòu)最近幾年夾具設(shè)計(jì)問(wèn)題受到越來(lái)越多的重視。然而，很少有注意力集中于優(yōu)化夾具布局設(shè)計(jì)。Menassa和Devries用FEA計(jì)算變形量使設(shè)計(jì)準(zhǔn)那么要求的位點(diǎn)的工件變形最小化。設(shè)計(jì)問(wèn)題是確定支撐器位置。Meyer和Liou提出一個(gè)方法就是使用線性編程技術(shù)合成動(dòng)態(tài)編程條件中的夾具。給出了使夾緊力和定位力最小化的解決方案。Li和Melkote用非線性規(guī)劃方法解決布局優(yōu)化問(wèn)題。這個(gè)方法使工件位置誤差最小化歸于工件的局部彈性變形。Roy和Liao開(kāi)發(fā)出一種啟發(fā)式方法來(lái)方案最好的支撐和夾緊位置。Tao等人提出一個(gè)幾何推理的方法來(lái)確定最優(yōu)夾緊點(diǎn)和任意形狀工件的夾緊順序。Liao和Hu提出一種夾具結(jié)構(gòu)分析系統(tǒng)這個(gè)系統(tǒng)基于動(dòng)態(tài)模型分析受限于時(shí)變加工負(fù)載的夾具—工件系統(tǒng)。本文也調(diào)查了夾緊位置的影響。Li和Melkote提出夾具布局和夾緊力最優(yōu)合成方法幫我們解釋加工過(guò)程中的工件動(dòng)力學(xué)。本文提出一個(gè)夾具布局和夾緊力優(yōu)化結(jié)合的程序。他們用接觸彈性建模方法解釋工件剛體動(dòng)力學(xué)在加工期間的影響。Amaral等人用ANSYS驗(yàn)證夾具設(shè)計(jì)的完整性。他們用3-2-1方法。ANSYS提出優(yōu)化分析。Tan等人通過(guò)力鎖合、優(yōu)化與有限建模方法描述了建模、優(yōu)化夾具的分析與驗(yàn)證。以上大局部的研究使用線性和非線性編程方式這通常不會(huì)給出全局最優(yōu)解決方案。所有的夾具布局優(yōu)化程序開(kāi)始于一個(gè)初始可行布局。這些方法給出的解決方案在很大程度上取決于初始夾具布局。他們沒(méi)有考慮到工件夾具布局優(yōu)化對(duì)整體的變形。GAs已被證明在解決工程中優(yōu)化問(wèn)題是有用的。夾具設(shè)計(jì)具有巨大的解決空間并需要搜索工具找到最好的設(shè)計(jì)。一些研究人員曾使用GAs解決夾具設(shè)計(jì)及夾具布局問(wèn)題。Kumar等人用GAs和神經(jīng)網(wǎng)絡(luò)設(shè)計(jì)夾具。Marcelin已經(jīng)將GAs用于支撐位置的優(yōu)化。Vallapuzha等人提出基于優(yōu)化方法的GA，它采用空間坐標(biāo)來(lái)表示夾具元件的位置。夾具布局優(yōu)化程序設(shè)計(jì)的實(shí)現(xiàn)是使用MATLAB和遺傳算法工具箱。HYPERMESH和MSC/NASTRAN用于FE模型。Vallapuzha等人提出一些結(jié)果關(guān)于一個(gè)廣泛調(diào)查不同優(yōu)化方法的相對(duì)有效性。他們的研究說(shuō)明連續(xù)遺傳算法提出了最優(yōu)質(zhì)的解決方案。Li和Shiu使用遺傳算法確定了夾具設(shè)計(jì)最優(yōu)配置的金屬片。MSC/NASTRAN已經(jīng)用于適應(yīng)度值評(píng)價(jià)。Liao提出自動(dòng)選擇最正確夾子和夾鉗的數(shù)目以及它們?cè)诮饘倨系膴A具中的最優(yōu)位置。Krishnakumar和Melkote開(kāi)發(fā)了一種夾具布局優(yōu)化技術(shù)，它是利用遺傳算法找到了夾具布局，由于整個(gè)刀具路徑中的夾緊力和加工力使加工外表變形量最小化。通過(guò)節(jié)點(diǎn)編號(hào)使定位器和夾具位置特殊化。一個(gè)內(nèi)置的有限元求解器研制成功。一些研究沒(méi)考慮到整個(gè)刀具路徑的優(yōu)化布局以及磨屑去除。一些研究采用節(jié)點(diǎn)編號(hào)作為設(shè)計(jì)參數(shù)。在本研究中，開(kāi)發(fā)GA工具用于尋找在二維工件中的最優(yōu)定位器和夾緊位置。使用參考邊緣的距離作為設(shè)計(jì)參數(shù)而不是用FEA節(jié)點(diǎn)編號(hào)。真正編碼遺傳算法的染色體的健康指數(shù)是從FEA結(jié)果中獲得的。ANSSYS用于FEA計(jì)算。用染色體文庫(kù)的方法是為了減少解決問(wèn)題的時(shí)間。用兩個(gè)問(wèn)題測(cè)試已開(kāi)發(fā)的遺傳算法工具。給出的兩個(gè)實(shí)例說(shuō)明了這個(gè)開(kāi)發(fā)的方法。本論文的主要奉獻(xiàn)可以概括為以下幾個(gè)方面：開(kāi)發(fā)了遺傳算法編碼結(jié)合商業(yè)有限元素求解；遺傳算法采用染色體文庫(kù)以降低計(jì)算時(shí)間；使用真正的設(shè)計(jì)參數(shù)，而不是有限元節(jié)點(diǎn)數(shù)字；當(dāng)工具在工件中移動(dòng)時(shí)考慮磨屑去除工具。3.遺傳算法概念遺傳算法最初由JohnHolland開(kāi)發(fā)。Goldberg出版了一本書(shū)，解釋了這個(gè)理論和遺傳算法應(yīng)用實(shí)例的詳細(xì)說(shuō)明。遺傳算法是一種隨機(jī)搜索方法，它模擬一些自然演化的機(jī)制。該算法用于種群設(shè)計(jì)。種群從一代到另一代演化，通過(guò)自然選擇逐漸提高了適應(yīng)