Nonlinear predictive control based on a global model identified off-line

Author

Peng, H. ; Ozaki, T. ; Toyoda, Yoshiaki ; Haggan-Ozaki, V.

Author_Institution

Coll. of Inf. Eng., Central South Univ., Changsha, China

Volume

5

fYear

2002

fDate

2002

Firstpage

4197

Abstract

A model predictive control (MPC) strategy for the non-stationary nonlinear systems with operating point-dependent dynamics is presented. The MPC proposed does not require on-line parameters estimation, because its internal model is an off-line identified global (RBF-ARX.) model, which is a generalized ARX model with Gaussian radial basis function networks-based functional coefficients. The RBF-ARX model parameters are estimated using a quickly-convergent structured nonlinear parameter optimization method (SNPOM). The quadratic programming routines may be used to solve the MPC problem with constraints. Simulation study on a chemical process shows satisfactory modeling and control performance.

Keywords

nonlinear control systems; predictive control; quadratic programming; radial basis function networks; Gaussian radial basis function networks-based functional coefficients; chemical process; generalized ARX model; global model identified offline; nonlinear predictive control; nonstationary nonlinear systems; offline identified global model; operating point dependent dynamics; parameters estimation; quadratic programming; simulation study; structured nonlinear parameter optimization method; Mathematics; Neural networks; Nonlinear dynamical systems; Nonlinear systems; Parameter estimation; Predictive control; Predictive models; Quadratic programming; Sampling methods; Time varying systems;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference, 2002. Proceedings of the 2002

ISSN

0743-1619

Print_ISBN

0-7803-7298-0

Type

conf

DOI

10.1109/ACC.2002.1024590

Filename

1024590