Robust Control of a Nonlinear Dynamical System for Changes of External Inputs Using Second Order Derivative of Universal Learning Network

Abstract

As the nonlinearity and complexity of a nonlinear system increase, it may be more difficult to construct a controller by the mathematical control theory. In such cases, it is very effective to construct the controller by using Neural Network(NN), because NNs have capabilities of coping with the nonlinearity and complexity of the nonlinear systems. NN controllers are constructed through learning to minimize a criterion function under certain environments of the system. But NN contollers may not work well under a very different environment from the environment at learning stage. In other words, for example, NN controllers are usually made without considering the changes of the environment because NN controllers do not have a means to supress their influences. So, in case that the environment changes, NN controllers do not work well. In this paper a robust control system design method for the changes of the external inputs to the system is discussed using second order derivatives of Universal Learning Network.