A quasi-ARMAX approach to modelling of non-linear systems

Takayuki Furuzuki, Kousuke Kumamaru, Kotaro Hirasawa

Research output: Contribution to journalArticle

46 Citations (Scopus)

Abstract

This paper proposes a class of quasi-ARMAX models for non-linear systems. Similar to ordinary non-linear ARMAX models, the quasi-ARMAX models are flexible black-box models, but they have various linearity properties similar to those of linear ARMAX models. A modelling scheme is introduced to construct models consisting of two parts: a macro-part and a kernel-part. By using Taylor expansion and other mathematical transformation techniques, it is first constructed as a class of quasi-ARMAX interfaces (macro-parts) that have various linearity properties but contain some complicated coefficients. MIMO neurofuzzy models (kernel-parts) are then introduced to represent the complicated coefficients. It is shown that the proposed quasi-ARMAX models have both good approximation ability and some easy-to-use properties. The proposed models-have been successfully applied to prediction, fault detection and adaptive control of non-linear systems.

Original languageEnglish
Pages (from-to)1754-1766
Number of pages13
JournalInternational Journal of Control
Volume74
Issue number18
DOIs
Publication statusPublished - 2001 Dec 15
Externally publishedYes

Fingerprint

Nonlinear systems
Macros
MIMO systems
Fault detection
Interfaces (computer)
Mathematical transformations

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

A quasi-ARMAX approach to modelling of non-linear systems. / Furuzuki, Takayuki; Kumamaru, Kousuke; Hirasawa, Kotaro.

In: International Journal of Control, Vol. 74, No. 18, 15.12.2001, p. 1754-1766.

Research output: Contribution to journalArticle

Furuzuki, Takayuki ; Kumamaru, Kousuke ; Hirasawa, Kotaro. / A quasi-ARMAX approach to modelling of non-linear systems. In: International Journal of Control. 2001 ; Vol. 74, No. 18. pp. 1754-1766.
@article{3c128f6c34024fbda12c74997b9136b2,
title = "A quasi-ARMAX approach to modelling of non-linear systems",
abstract = "This paper proposes a class of quasi-ARMAX models for non-linear systems. Similar to ordinary non-linear ARMAX models, the quasi-ARMAX models are flexible black-box models, but they have various linearity properties similar to those of linear ARMAX models. A modelling scheme is introduced to construct models consisting of two parts: a macro-part and a kernel-part. By using Taylor expansion and other mathematical transformation techniques, it is first constructed as a class of quasi-ARMAX interfaces (macro-parts) that have various linearity properties but contain some complicated coefficients. MIMO neurofuzzy models (kernel-parts) are then introduced to represent the complicated coefficients. It is shown that the proposed quasi-ARMAX models have both good approximation ability and some easy-to-use properties. The proposed models-have been successfully applied to prediction, fault detection and adaptive control of non-linear systems.",
author = "Takayuki Furuzuki and Kousuke Kumamaru and Kotaro Hirasawa",
year = "2001",
month = "12",
day = "15",
doi = "10.1080/00207170110089770",
language = "English",
volume = "74",
pages = "1754--1766",
journal = "International Journal of Control",
issn = "0020-7179",
publisher = "Taylor and Francis Ltd.",
number = "18",

}

TY - JOUR

T1 - A quasi-ARMAX approach to modelling of non-linear systems

AU - Furuzuki, Takayuki

AU - Kumamaru, Kousuke

AU - Hirasawa, Kotaro

PY - 2001/12/15

Y1 - 2001/12/15

N2 - This paper proposes a class of quasi-ARMAX models for non-linear systems. Similar to ordinary non-linear ARMAX models, the quasi-ARMAX models are flexible black-box models, but they have various linearity properties similar to those of linear ARMAX models. A modelling scheme is introduced to construct models consisting of two parts: a macro-part and a kernel-part. By using Taylor expansion and other mathematical transformation techniques, it is first constructed as a class of quasi-ARMAX interfaces (macro-parts) that have various linearity properties but contain some complicated coefficients. MIMO neurofuzzy models (kernel-parts) are then introduced to represent the complicated coefficients. It is shown that the proposed quasi-ARMAX models have both good approximation ability and some easy-to-use properties. The proposed models-have been successfully applied to prediction, fault detection and adaptive control of non-linear systems.

AB - This paper proposes a class of quasi-ARMAX models for non-linear systems. Similar to ordinary non-linear ARMAX models, the quasi-ARMAX models are flexible black-box models, but they have various linearity properties similar to those of linear ARMAX models. A modelling scheme is introduced to construct models consisting of two parts: a macro-part and a kernel-part. By using Taylor expansion and other mathematical transformation techniques, it is first constructed as a class of quasi-ARMAX interfaces (macro-parts) that have various linearity properties but contain some complicated coefficients. MIMO neurofuzzy models (kernel-parts) are then introduced to represent the complicated coefficients. It is shown that the proposed quasi-ARMAX models have both good approximation ability and some easy-to-use properties. The proposed models-have been successfully applied to prediction, fault detection and adaptive control of non-linear systems.

UR - http://www.scopus.com/inward/record.url?scp=0035895099&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035895099&partnerID=8YFLogxK

U2 - 10.1080/00207170110089770

DO - 10.1080/00207170110089770

M3 - Article

AN - SCOPUS:0035895099

VL - 74

SP - 1754

EP - 1766

JO - International Journal of Control

JF - International Journal of Control

SN - 0020-7179

IS - 18

ER -