Tổng hợp điều khiển cho hệ phi tuyến động có tải thay đổi

Abstract

Non-linear dynamical systems are difficult to control due to the model uncertainties and external disturbances (that may occur in these systems). This paper addresses the problem of modeling and on-line direct inverse controlling method using neural networks for a given class of nonlinear systems. The design procedure involves the integration of identification and neural control for an imprecisely known plant. A new recurrent neural network approach for on-line adaptive control is presented. A dynamic learning algorithm for the recurrent neutral network has been developed with faster convergence and improved steady-state performance for the neural networks structure. New control scheme for noise canceller in case of change in load or control parameter. On-line simulation studies for selected process with the proposed control are presented and discussed using two-link robot arm to demonstrate the performance of the proposed strategy.