Neural Network Based Robust Controller for Trajectory Tracking of Underwater Vehicles

(整期优先)网络出版时间:2007-02-12
/ 1
Arobustneuralnetworkcontroller(NNC)ispresentedfortrackingcontrolofunderwatervehicleswithuncertainties.ThecontrollerisobtainedbyusingbacksteppingtechniqueandLyapunovfunctiondesignincombinationwithneuralnetworkidentification.Modelingerrorsandenvironmentaldisturbancesareconsideredinthemathematicalmodel.Atwo-layerneuralnetworkisintroducedtocompensatethemodelingerrors,whileH∞controlstrategyisusedtoachievetheL2-gainperformance.Theuniformlyultimatelybounded(UUB)stabilitiesoftrackingerrorsandNNweightsareguaranteedthroughtheproposedcontroller.Anon-lineNNweightstuningalgorithmisalsoproposed.Goodperformancesofthetrackingcontrolsystemareillustratedbytheresultsofnumericalsimulations.