Improved multivariable nonlinear system control based on differential predictive cost function

Author

Zhang, Yan ; Li, Lina ; Yang, Peng ; Li, Yongfu ; Liu, Pinjie

Author_Institution

Dept. of Autom., Hebei Univ. of Technol., Tianjin

fYear

2008

fDate

25-27 June 2008

Firstpage

6968

Lastpage

6972

Abstract

A new predictive control algorithm based on single neural network for a kind of MIMO nonlinear systems is presented. In the control process, only one RBF network is used to calculate the multi-step-ahead predictive outputs. To overcome the drawbacks of the traditional cost function, a new multi-step predictive cost function with differential part is constructed. This strategy can accelerate the process of receding horizon optimization and reduce the influence caused by model error, disturbance and uncertainty to the controller. Simulation and application show the effectiveness and great performance.

Keywords

MIMO systems; multivariable control systems; neurocontrollers; nonlinear control systems; predictive control; radial basis function networks; MIMO nonlinear systems; RBF network; differential predictive cost function; multistep-ahead predictive outputs; multivariable nonlinear system control; receding horizon optimization; single neural network; Control systems; Cost function; MIMO; Neural networks; Nonlinear control systems; Nonlinear systems; Prediction algorithms; Predictive control; Process control; Radial basis function networks; RBF network; multivariable system; nonlinear system; predictive control;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on

Conference_Location

Chongqing

Print_ISBN

978-1-4244-2113-8

Electronic_ISBN

978-1-4244-2114-5

Type

conf

DOI

10.1109/WCICA.2008.4594573

Filename

4594573