Title :
Neural network-based successive one-step-ahead control of nonlinear systems
Author :
Ma, X. ; Loh, R.N.K.
Author_Institution :
Center for Robotics & Adv. Autom., Oakland Univ., Rochester, MI, USA
fDate :
29 June-1 July 1994
Abstract :
In this paper, a new controller is designed for a class of nonlinear systems. With the proposed method, a nonlinear model is formulated in such a way that a successive one-step-ahead controller can be designed based on the one-step-ahead principle. A neural network version of the new controller is also developed so as to handle situations where the proposed model is not attainable. Computer simulations are presented to show the effectiveness of the new methods.
Keywords :
backpropagation; intelligent control; neural nets; neurocontrollers; nonlinear systems; backpropagation; neural network; neurocontrol; nonlinear model; nonlinear systems; successive one-step-ahead control; Automatic control; Backpropagation; Computer simulation; Control systems; Design automation; Neural networks; Nonlinear control systems; Nonlinear systems; Predictive models; Robotics and automation;
Conference_Titel :
American Control Conference, 1994
Print_ISBN :
0-7803-1783-1
DOI :
10.1109/ACC.1994.752452
