Title :
Application of adaptive neural model-based control
Author :
Mills, Peter M. ; Zomaya, Albert Y. ; Tadé, Moses O.
Author_Institution :
CRA Adv. Tech. Dev., Cannington, WA, Australia
Abstract :
Previous work extending identification using neural networks to the online adaptive case has resulted in poor performance. The work presented in this paper demonstrates a powerful method for implementing an adaptive neural network model of nonlinear process dynamics for control. This adaptive method has been amalgamated with a multistep nonlinear predictive control technique. The performance of this controller is demonstrated, and evaluated, using two simulated realistic processes
Keywords :
adaptive control; chemical industry; feedforward neural nets; identification; multivariable control systems; nonlinear control systems; predictive control; process control; transfer functions; adaptive multivariable control; adaptive neural identification; adaptive neural model-based control; chemical industry; evaporator process control; history stack adaptation; multistep nonlinear predictive control; nonlinear process dynamics; transfer function; Adaptive control; Adaptive systems; Australia; Convergence; Industrial control; Milling machines; Neural networks; Predictive control; Predictive models; Programmable control;
Conference_Titel :
Decision and Control, 1993., Proceedings of the 32nd IEEE Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-7803-1298-8
DOI :
10.1109/CDC.1993.325706
