Neural networks of adaptive inverse control systems

摘要

One neural network, (NN), is used for the adaptive inverse control of nonlinear systems. To adjust the identifier parameters, a method uses a compromised function to establish the performance of the identifier, is proposed. The main objective is to combine the performance error and the tracking errors. Also a reasonable control action is achieved for a nearly unstable system. Simulation results are included to demonstrate the potential of the proposed method for linear, nonlinear and nearly unstable systems.