Multivariable system identification for dynamic discrete-time nonlinear system using genetic algorithm

Author

Ahmad, Rabiah ; Amaluddin, H.J. ; Hussain, M.A.

Author_Institution

Fac. of Mech. Eng., Universiti Teknologi Malaysia, Johor, Malaysia

Volume

5

fYear

2002

fDate

6-9 Oct. 2002

Abstract

Model structure selection based on a genetic algorithm, which was originally derived for single-input single-output (SISO) systems, is extended to multi-input multi-output (MIMO) dynamic discrete-time nonlinear systems. This paper studies the algorithm in identifying the model structure for a jacketed continuous stirred tank reactor or CSTR. The adequacy of the developed model is tested using one step ahead prediction and cross validation test.

Keywords

MIMO systems; discrete time systems; genetic algorithms; identification; multivariable control systems; nonlinear control systems; cross validation test; dynamic discrete-time nonlinear system; genetic algorithm; jacketed continuous stirred tank reactor; model structure selection; multi-input multi-output systems; multivariable system identification; one step ahead prediction; single-input single-output systems; Autoregressive processes; Continuous-stirred tank reactor; Genetic algorithms; Least squares methods; MIMO; Mathematical model; Nonlinear dynamical systems; Nonlinear systems; Polynomials; System identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2002 IEEE International Conference on

ISSN

1062-922X

Print_ISBN

0-7803-7437-1

Type

conf

DOI

10.1109/ICSMC.2002.1176409

Filename

1176409