Title :
On-line implementation of a model predictive controller on a multivariable chemical process
Author :
Yu, D.L. ; Williams, D. ; Gomm, J.B.
Author_Institution :
Control Syst. Res. Group, Liverpool John Moores Univ., UK
Abstract :
An investigation into neural network model predictive control is described in this paper. The control strategy developed is applied to a laboratory process to control temperature, pH and dissolved oxygen. The main difficulties in control of this process are nonlinearity, coupling effects among variables and long time-delay in the heat exchanger. Parallel neural models are developed from real process data for the use with online model predictive control and off-line simulations. The online control results are demonstrated
Keywords :
chemical technology; coupling effects; dissolved oxygen control; heat exchanger; long time-delay; multivariable chemical process; neural network model predictive control; nonlinearity; off-line simulations; online model predictive control; pH control; parallel neural models; temperature control;
Conference_Titel :
Model Predictive Control: Techniques and Applications - Day 2 (Ref. No. 1999/096), IEE Two-Day Workshop on
Conference_Location :
London
DOI :
10.1049/ic:19990539