Robust control of nonlinear systems for external disturbances using second order derivatives of universal learning network

As nonlinearity and complexity of a nonlinear system increase, it becomes 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 circumstances. But NN controllers may not work well under very different circumstances from those at learning stage. For example, NN controllers are usually made without considering disturbances because NN controllers do not have a means to suppress their influences. So, when disturbances exist, NN controllers do not work well. In this paper a robust control system design method for suppressing the disturbances is discussed using second order derivatives of universal learning network