Нейроуправление нелинейным динамическим объектом с использованием метода обобщенного управления с предсказанием

Abstract

In the given paper, utilizing a predictive neuro-controller for providing high performance characteristics of a nonlinear dynamic object control system is proposed. For the controller design, efficient implementation of generalized predictive control is applied by utilizing a multi-layer feedforward neural network as a nonlinear model of the control object. A chart of the control system is developed, the controller synthesis and the system modeling made.