A new robust neural network controller designing method for nonlinear systems

A new design method of robust neural network controller against system environment changes using a universal learning network is considered. With the introduced method, the worst values of system parameters can be searched as well as the optimization of controller parameters through a dual learning algorithm, which includes maximization and minimization procedures. Therefore, the robust controller can be obtained by minimizing the criterion function regarding the worst values of system parameters. Simulation results demonstrate that the system performance has been improved compared with the conventional method by using the proposed method