direct adaptive control of nonaffine nonlinear system using multilayer neural networks

direct adaptive control of nonaffine nonlinear system using multilayer neural networks

ID:46775253

大小:601.37 KB

页数:9页

时间:2019-11-27

direct adaptive control of nonaffine nonlinear system using multilayer neural networks_第1页
direct adaptive control of nonaffine nonlinear system using multilayer neural networks_第2页
direct adaptive control of nonaffine nonlinear system using multilayer neural networks_第3页
direct adaptive control of nonaffine nonlinear system using multilayer neural networks_第4页
direct adaptive control of nonaffine nonlinear system using multilayer neural networks_第5页
资源描述:

《direct adaptive control of nonaffine nonlinear system using multilayer neural networks》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、414IEEETRANSACTIONSONNEURALNETWORKS,VOL.16,NO.2,MARCH2005DirectAdaptiveControllerforNonaffineNonlinearSystemsUsingSelf-StructuringNeuralNetworksJang-HyunPark,Sung-HoeHuh,Seong-HwanKim,Sam-JunSeo,andGwi-TaeParkAbstract—Adirectadaptivestate-feedbackcontrolleris

2、pro-controlmethodsareroughlydividedintotwocategories,oneisposedforhighlynonlinearsystems.Weconsideruncertainoradirectadaptivecontrolandtheotherisanindirectadaptiveill-definednonaffinenonlinearsystemsandemployaneuralnet-control.work(NN)withflexiblestructure,i.e.

3、,anonlinevariationoftheInthedirectadaptivecontrolmethod[12]–[14],theoutputnumberofneurons.TheNNapproximatesandadaptivelycancelsanunknownplantnonlinearity.AcontrollawandadaptivelawsofaNNbecomesacontrolinput,andanoptimalcontrollerisfortheweightsinthehiddenlaye

4、randoutputlayeroftheNNareobtainedbyadaptation.Intheindirectone[7]–[11],[18],NNsestablishedsothatthewholeclosed-loopsystemisstableinthearecombinedwiththeinput-outputlinearizationscheme,andsenseofLyapunov.Moreover,thetrackingerrorisguaranteedtoestimatetheunkno

5、wnnonlinearitiesofthecontrolledsystem.beuniformlyasymptoticallystable(UAS)ratherthanuniformlyThen,anadaptiveinput-outputlinearizingcontrolinputisgen-ultimatelybounded(UUB)withtheaidofanadditionalrobusti-fyingcontrolterm.Theproposedcontrolalgorithmisrelativel

6、yeratedusingtheestimates.Inallofthem,thecontrolinputandsimpleandrequiresnorestrictiveconditionsonthedesigncon-adaptivelawsfortheweightsoftheNNshavebeendesignedstantsforthestability.Theefficiencyoftheproposedschemeisforthewholeclosed-loopsystemtobestableinthes

7、enseofshownthroughthesimulationofasimplenonaffinenonlinearLyapunov.system.Inevitably,reconstructionerrorsmustoccurifthestructureofIndexTerms—Neuralnetwork(NN),nonaffinenonlineartheNN(thenumberofhiddenlayersandneurons)isnotinfin-system,robustadaptivecontrol.itel

8、yrich,andtheseerrorsareintroducedintotheclosed-loopsystemanddeterioratethestability.Tocompensateforthere-I.INTRODUCTIONconstructionerrors,themethodofaddingaslidingmodeinputtermiswidelyused[9],[1

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。