Adaptive Tracking Control of Nonlinear Systems Using Neural Networks

Abstract

An adaptive neural network control strategy for a class of nonlinear system is proposed, which combines the technique in generalized predictive control theory and the gradient descent rule to accelerate learning and improve convergence with neural network’s capability of approximating to nonlinear function, Taking the neural network as a model of the system, control signals are directly obtained by minimizing the cumulative differences between a setpoint and output of the model. The effectiveness of the proposed control scheme is illustrated through simulations.