Discrete-time CMAC NN control of feedback linearizable nonlinear systems under a persistence of excitation

The local structure of CR IAC neural networks (NN) result in better and fas ter controllers for nonlinear dynamical systems. A CMAC neural network-base d discrete-time controller which linearizes the unknown multiinput and mult ioutput (MIMO) nonlinear system through feedback is presented. Control acti on is defined in order to achieve tracking performance for this unknown non linear system. An efficient and localized weight addressing scheme for the CR IAC NN's is described using an appropriate choice of the B-spline recept ive field functions that form a basis, A uniform ultimate boundedness of th e closed-loop system is given in the sense of Lyapunov using the persistenc y of excitation (PE) condition. Simulation results are shown to demonstrate the theoretical conclusions.