Iterative learning neural networks control with disturbances estimation for nonlinear systems

This paper deals with P-type iterative learning neural networks control (ILNNC) to solve the trajectory tracking problem for multi input multi output (MIMO) nonlinear systems with unknown varying iteration disturbance. The proposed controller takes the advantages of using just the proportional action and can be applied to nonlinear systems without using the global Lipchitz condition. Thus, the unknown norm bounded function is approximated by a radial basis function neural networks (RBFNN).The unknown disturbances at each iteration are adjusted with a disturbance estimation law. The asymptotic stability of the closed-loop system is guaranteed analytically using the Lyapunov theory over the whole finite time. Finally, a numerical example on nonlinear system is given to show the effectiveness of the proposed method.