%0 Journal Article
%T 利用神经网络控制连续浇铸过程中的热传导
%A BOUHOUCHE Salah
%A LAHRECHE Malek
%A BAST Jurgen
%J 自动化学报
%P 701-706
%D 2008
%R 10.3724/SP.J.1004.2008.00701
%X ？Incontinuouscasting,thecooling-solidificationprocessmustbebasedontheadaptationofheattransfer,whichisdirectlyconnectedtocastingconditionssuchascastingspeed,castingtemperature,andcoolingparameters.Mostcontrolschemesarebasedonthestaticrelationbetweencastingspeedandwaterflowrateineachcoolingzone;thisconstitutesanopenloopthatdoesnotconsiderthedynamicsurfacetemperature,whichisanimportantparameterforthefinalslabquality.Insteelmaking,thecasting-speedchangesaffecttheglobalheattransfer.Anoptimaloperationrequiresanadjustmentoftheprocesscontrolvariables,i.e.,globalheattransfer.Alearningneuralnetwork(NN)allowstheidentificationandthecontrolofanonlinearheattransfermodelinthecontinuouscastingprocess.Aheattransfermodelwasdevelopedusingthedynamicheatbalance.Acomparisonbetweentheexperimentalopenloopresultsandthoseofthemodelsimulationisconsidered.Followingadaptation,themodelisusedforcontrollingtheslabsurfacetemperatureinclosedloop,usingNNtechnologyandPIDcontrollers.TheNNidentificationandcontrolstrategygivesastabletemperatureclosedloopcontrolcomparativelytotheconventionalPID.
%K Neuralnetworks
%K identification
%K control
%K heattransfer
%K continuouscasting
%U http://www.aas.net.cn/CN/abstract/abstract17898.shtml