A ROBUST ADAPTIVE TRACKING CONTROLLER USING NEURAL NETWORKS FOR A CLASS OF NONLINEAR-SYSTEMS

A neural network-based robust adaptive tracking control scheme is prop osed for a class of nonlinear systems. It is shown that, unlike most n eural control schemes using the back-propagation training technique, o ne hidden layer neural controller is designed in the Lyapunov sense, a nd the parameters of the neural controller are then adaptively adjuste d for the compensation of unknown dynamics and nonlinearities. Using t his scheme, not only strong robustness with respect to unknown dynamic s and nonlinearities can be obtained, but also asymptotic error conver gence between the plant output and the reference model output can be g uaranteed. A simulation example based on a one-link non-linear robotic manipulator is given in support of the proposed neural control scheme .