Nonlinear model predictive control using neural networks

Author

Piché, Stephen ; Sayyar-Rodsari, Bijan ; Johnson, Doug ; Gerules, Mark

Author_Institution

Pavilion Technol., Austin, TX, USA

Volume

20

Issue

3

fYear

2000

fDate

6/1/2000 12:00:00 AM

Firstpage

53

Lastpage

62

Abstract

A neural-network-based technique for developing nonlinear dynamic models from empirical data for an model predictive control (MPC) algorithm is presented. These models can be derived for a wide variety of processes and can also be used efficiently in an MPC framework. The nonlinear MPC-based approach presented has been successfully implemented in a number of industrial applications in the refining, petrochemical, pulp and paper, power, and food industries. Performance of the controller on a nonlinear industrial process, a polyethylene reactor, and a simulated continuous stirred tank reactor is presented

Keywords

chemical industry; neurocontrollers; nonlinear control systems; predictive control; process control; continuous stirred tank reactor; model predictive control; neural networks; neurocontrol; nonlinear control systems; nonlinear dynamic models; polyethylene reactor; process control; Chemical industry; Food industry; Industrial control; Neural networks; Petrochemicals; Polyethylene; Prediction algorithms; Predictive control; Predictive models; Refining;

fLanguage

English

Journal_Title

Control Systems, IEEE

Publisher

ieee

ISSN

1066-033X

Type

jour

DOI

10.1109/37.845038

Filename

845038