Publication detail

Comparison of Offline Identification Methods on Bounded AutoRegressive Polynomial Models

LEBEDA, A. PIVOŇKA, P.

Original Title

Comparison of Offline Identification Methods on Bounded AutoRegressive Polynomial Models

English Title

Comparison of Offline Identification Methods on Bounded AutoRegressive Polynomial Models

Type

conference paper

Language

en

Original Abstract

In this paper we focused on methods for offline identification of bounded autoregressive polynomials models. Firstly we used classical least square (LS) method for identification. Secondly we used total least square (TLS) method and thirdly we used gradient based method Levenberg-Marquardt for identification. Bounded AR polynomial models are basically nonlinear in parameters but the models can be modified to linear dependencies on parameters if bounding function is irreversible. Levenberg-Marquardt method was applied to unmodified bounded AR polynomial models. Input/Output data was generated from the model of isothermal continuous stirred-tank reactor with and without additive noise. Finally all methods are compared on one-step and multi-step predictions.

English abstract

In this paper we focused on methods for offline identification of bounded autoregressive polynomials models. Firstly we used classical least square (LS) method for identification. Secondly we used total least square (TLS) method and thirdly we used gradient based method Levenberg-Marquardt for identification. Bounded AR polynomial models are basically nonlinear in parameters but the models can be modified to linear dependencies on parameters if bounding function is irreversible. Levenberg-Marquardt method was applied to unmodified bounded AR polynomial models. Input/Output data was generated from the model of isothermal continuous stirred-tank reactor with and without additive noise. Finally all methods are compared on one-step and multi-step predictions.

Keywords

LS, TLS, nonlinear, polynomial, identification

RIV year

2014

Released

28.05.2014

ISBN

978-1-4799-3527-7

Book

15th International Carpathian Control Conference - ICCC 2014

Pages from

301

Pages to

305

Pages count

5

Documents

BibTex


@inproceedings{BUT107114,
  author="Aleš {Lebeda} and Petr {Pivoňka}",
  title="Comparison of Offline Identification Methods on Bounded AutoRegressive Polynomial Models",
  annote="In this paper we focused on methods for offline identification of bounded autoregressive polynomials models. Firstly we used classical least square (LS) method for identification. Secondly we used total least square (TLS) method and thirdly we used gradient based method Levenberg-Marquardt for identification. Bounded AR polynomial models are basically nonlinear in parameters but the models can be modified to linear dependencies on parameters if bounding function is irreversible. Levenberg-Marquardt method was applied to unmodified bounded AR polynomial models. Input/Output data was generated from the model of isothermal continuous stirred-tank reactor with and without additive noise. Finally all methods are compared on one-step and multi-step predictions.",
  booktitle="15th International Carpathian Control Conference - ICCC 2014",
  chapter="107114",
  howpublished="electronic, physical medium",
  year="2014",
  month="may",
  pages="301--305",
  type="conference paper"
}