外文翻译Word格式.docx
《外文翻译Word格式.docx》由会员分享,可在线阅读,更多相关《外文翻译Word格式.docx(7页珍藏版)》请在冰豆网上搜索。
Thevariablefrequencyspeed-regulatingsystemwhichconsistsofaninductionmotorandageneralinverter,andcontrolledbyPLCiswidelyusedinindustrialfield.However,forthemultivariable,nonlinearandstronglycoupledinductionmotor,thecontrolperformanceisnotgoodenoughtomeettheneedsofspeed-regulating.Themathematicmodelofthevariablefrequencyspeed-regulatingsysteminvectorcontrolmodeispresentedanditsreversibilityhasbeenproved.Byconstructinganeuralnetworkinversesystemandcombiningitwiththevariablefrequencyspeed-regulatingsystem,apseudo-linearsystemiscompleted,andthenalinearclose-loopadjustorisdesignedtogethighperformance.UsingPLC,aneuralnetworkinversesystemcanberealizedinacturalsystem.Theresultsofexperimentshaveshownthattheperformancesofvariablefrequencyspeed-regulatingsystemcanbeimprovedgreatlyandthepracticabilityofneuralnetworkinversecontrolwastestified.
1.Citation:
Inrecentyears,withpowerelectronictechnology,microelectronictechnologyandmoderncontroltheoryinfiltratingintoACelectricdrivingsystem,invertershavebeenwidelyusedinspeed-regulatingofACmotor.Thevariablefrequencyspeed-regulatingsystemwhichconsistsofaninductionmotorandageneralinverterisusedtotaketheplaceofDCspeed-regulatingsystem.Becauseofterribleenvironmentandseveredisturbanceinindustrialfield,thechoiceofcontrollerisanimportantproblem.Somereference,Neuralnetworkinversecontrolwasrealizedbyusingindustrialcontrolcomputerandseveraldataacquisitioncards.Theadvantagesofindustrialcontrolcomputerarehighcomputationspeed,greatmemorycapacityandgoodcompatibilitywithothersoftwareetc.Butindustrialcontrolcomputeralsohassomedisadvantagesinindustrialapplicationsuchasinstabilityandfallibilityandworsecommunicationability.PLCcontrolsystemisspecialdesignedforindustrialenvironmentapplication,anditsstabilityandreliabilityaregood.PLCcontrolsystemcanbeeasilyintegratedintofieldbuscontrolsystemwiththehighabilityofcommunicationconfiguration,soitiswildlyusedinrecentyears,anddeeplywelcomed.Sincethesystemcomposedofnormalinverterandinductionmotorisacomplicatednonlinearsystem,traditionalPIDcontrolstrategycouldnotmeettherequirementforfurthercontrol.Therefore,howtoenhancecontrolperformanceofthissystemisveryurgent.
Theneuralnetworkinversesystem,isanovelcontrolmethodinrecentyears.Thebasicideaisthat:
foragivensystem,aninversesystemoftheoriginalsystemiscreatedbyadynamicneuralnetwork,andthecombinationsystemofinverseandobjectistransformedintoakindofdecouplingstandardizedsystemwithlinearrelationship.Subsequently,alinearclose-loopregulatorcanbedesignedtoachievehighcontrolperformance.Theadvantageofthismethodiseasilytoberealizedinengineering.Thelinearizationanddecouplingcontrolofnormalnonlinearsystemcanrealizeusingthismethod.
CombiningtheneuralnetworkinverseintoPLCcaneasilymakeuptheinsufficiencyofsolvingtheproblemsofnonlinearandcouplinginPLCcontrolsystem.Thiscombinationcanpromotetheapplicationofneuralnetworkintopracticetoachieveitfulleconomicandsocialbenefits.
Inthispaper,firstlytheneuralnetworkinversesystemmethodisintroduced,andmathematicmodelofthevariablefrequencyspeed-regulatingsysteminvectorcontrolmodeispresented.Thenareversibleanalysisofthesystemisperformed,andthemethodsandstepsaregiveninconstructingNN-inversesystemwithPLCcontrolsystem.Finally,themethodisverifiedinexperiments,andcomparedwithtraditionalPIcontrolandNN-inversecontrol.
2.NeuralNetworkInverseSystemControlMethod
Thebasicideaofinversecontrolmethodisthat:
foragivensystem,anα-thintegralinversesystemoftheoriginalsystemiscreatedbyfeedbackmethod,andcombiningtheinversesystemwithoriginalsystem,akindofdecouplingstandardizedsystemwithlinearrelationshipisobtained,whichisnamedasapseudolinearsystem.Subsequently,alinearclose-loopregulatorwillbedesignedtoachievehighcontrolmathematicmodelofthevariableperformance.
Inversesystemcontrolmethodwiththefeaturesofdirect,simpleandeasytounderstanddoesnotlikedifferentialgeometrymethod,whichisdiscussestheproblemsin"
geometrydomain"
.Themainproblemistheacquisitionoftheinversemodelintheapplications.Sincenon-linearsystemisacomplexsystem,anddesiredstrictanalyticalinverseisveryobtain,evenimpossible.Theengineeringapplicationofinversesystemcontroldoesn’tmeettheexpectations.Asneuralnetworkhasnon-linearapproximateability,especiallyfornonlinearcomplexitysystem,itbecomeswiththepowerfulexpectationstooltosolvetheproblem.a−thNNinversesystemintegratedinversesystemwithnon-linearabilityoftheneuralnetworkcanavoidthetroublesofinversesystemmethod.Thenitispossibletoapplyinversecontrolmethodtoacomplicatednon-linearsystem.a−thNNinversesystemmethodneedslesssysteminformationsuchastherelativeorderofsystem,anditiseasytoobtaintheinversemodelbyneuralnetworktraining.CascadingtheNNinversesystemwiththeoriginalsystem,apseudo-linearsystemiscompleted.Subsequently,alinearclose-loopregulatorwillbedesigned.
3.RealizationStepsofNeuralNetworkInverseSystem
3.1AcquisitionoftheInputandOutputTrainingSamples
Trainingsamplesareextremelyimportantinthereconstructionofneuralnetworkinversesystem.Itisnotonlyneedtoobtainthedynamicdataoftheoriginalsystem,butalsoneedtoobtainthestaticdate.Referencesignalshouldincludealltheworkregionoforiginalsystem,whichcanbeensuretheapproximateability.Firstlythestepofactuatingsignalisgivencorrespondingevery10HZform0HZto50HZ,andtheresponsesofopenloopareobtain.Secondlyarandomtanglesignalisinput,whichisarandomsignalcascadingonthestepofactuatingsignalevery10seconds,andthecloseloopresponsesisobtained.Basedontheseinputs,1600groupsshouldincludealltrainingsamplesaregotten.
3.2TheConstructionofNeuralNetwork
Astaticneuralnetworkandadynamicneuralnetworkcomposedofintegralisusedtoconstructtheinversesystem.Thestructureofstaticneuralnetworkis2neuronsininputlayer,3neuronsinoutputlayer,and12neuronsinhiddenlayer.Theexcitationfunctionofhiddenneuronismonotonicsmoothhyperbolictangentfunction.Theoutputlayeriscomposedofneuronwithlinearthresholdexcitationfunction.Thetrainingdatumarethecorrespondingspeedofopen-loop,close-loop,firstorderderivativeofthesespeed,andsettingreferencespeed.After50timestraining,thetrainingerrorofneuralnetworkachievesto0.001.Theweightandthresholdoftheneuralnetworkaresaved.Theinversemodelandadynamicneuralnetworkcomposedoforiginalsystemisobtained.
Inductionmotorvariablefrequencyspeed-regulatingsystemsuppliedbytheinverteroftrackingcurrentSPWMcanbeexpressedbynonlinearmodelind-qtwo-phaserotatingcoordinate.Themodelwassimplifiedasa3-ordernonlinear
model.Whentheinverterisrunninginvectormode,thevariabilityoffluxlinkagecanbeneglected(considering
the
flux
linkage
to
be
invariableness
and
equal
rating).
4.ExperimentsandResults
4.1HardwareoftheSystem
ThehardwaresystemincludesuppercomputerinstalledwithSupervisory&
ControlconfigurationsoftwareWinCC6.0,andS7-300PLCofSIEMENS,inverter,inductioninstalledwithmotorandControlPhotoelectriccoder.
PLCcontrollerchoosesS7-315-2DP,whichhasaPROFIBUS-DPinterfaceandaMPIinterface.SpeedacquisitionmoduleisFM350-1.WinCCisconnectedwiththeexperimentsystemS7-300byCP5611usingMPIprotocol.
ThetypeofinverterisMMVofSIEMENS.ItcancommunicatewithSIEMENSPLCbyUSSprotocol.ACB15moduleisaddedontheinverterinthissystem.
4.2SoftwareProgram
4.2.1CommunicationIntroduction
MPI(MultiPointInterface)isasimpleandinexpensivecommunicationstrategyusinginslowlyandnon-largedatatransformingfield.ThedatatransformingbetweenWinCCandPLCisnotlarge,sotheMPIchosen.
TheMMVinverterisconnectedtothePROFIBUSnetworkasaslavestation,whichismountedwithCB15PROFIBUSmodule.PPO1orPPO3datatypecanbechosen.Itpermitstosendthecontroldatadirectlytotheinverteraddresses,ortousethesystemfunctionblocksofSTEP7V5.2SFC14/15.
OPCcanefficientlyprovidedataintegralandintercommunication.Differenttypeserversandclientscanaccessdatasourcesofeachother.Comparingwiththetraditionalmodeofsoftwareandhardwaredevelopment,equipmentmanufacturersonlyneedtodeveloponedriver.Thiscanshortthedevelopmentcycle,savemanpowerresources,andsimplifythestructuretheexperimentsystemoftheentirecontrolsystem.
VarietydataofthesystemisneededintheneuralnetworktrainingofMatlab,whichcannotobtainbyreadingfromPLCorWinCCdirectly.SoOPCtechnologycanbeusedtoobtaintheneededdatabetweenWinCCandExce.SettingWinCCasOPCDAserver,anOPCclientisconstructedinExcelbyVBA.SystemrealtimedataisreadedandwritentoExcelbyWinCC,andthenthedatainExcelistransformtoMatlabforofflinetrainingtogettheinversesystemoforiginalsystem.
4.2.2ControlProgram
UsedSTLtoprogramthecommunicationanddataacquisitionandcontrolalgorithmsubroutineinSTEP7V5.2,velocitysample