Predictive Control Based on Neural Networks of The Chemical Process

Author

Haichen Yu ; Zhijun Zhang

Author_Institution

Sch. of Electron. & Inf. Eng., Dalian Univ. of Technol., China

fYear

2006

fDate

7-11 Aug. 2006

Firstpage

1143

Lastpage

1147

Abstract

A predictive control algorithm based on neural networks is proposed for a class of highly nonlinear and uncertain systems. The predictive model is constructed by using feed-forward neural network in the algorithm, the Levenberg-Marquardt is incorporated into the back-propagation algorithm for training neural network off-line and modifying the predictive model online, The precision of model is raised and the control performance is improved significantly. The method is applied to control a CSTR reactor of nonlinear. The results illustrate effectiveness of the proposed approach.

Keywords

backpropagation; chemical reactors; feedforward neural nets; neurocontrollers; nonlinear systems; predictive control; process control; uncertain systems; CSTR reactor; Levenberg-Marquardt algorithm; backpropagation algorithm; chemical process; feedforward neural network; nonlinear system; predictive control; uncertain system; Chemical processes; Continuous-stirred tank reactor; Feedforward neural networks; Feedforward systems; Inductors; Neural networks; Prediction algorithms; Predictive control; Predictive models; Uncertain systems; neural networks; nonlinear; predictive control; reactor;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference, 2006. CCC 2006. Chinese

Conference_Location

Harbin

Print_ISBN

7-81077-802-1

Type

conf

DOI

10.1109/CHICC.2006.280528

Filename

4060259