A quasi-ARX model incorporating neural network for control of nonlinear systems

Takayuki Furuzuki; Kotaro Hirasawa; Kousuke Kumamaru

A quasi-ARX model incorporating neural network for control of nonlinear systems

Takayuki Furuzuki, Kotaro Hirasawa, Kousuke Kumamaru

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Neural networks have been known as flexible nonlinear black-box models and have attracted much interest in control community. This paper introduces a new neural-network based prediction model for control of nonlinear systems. Distinctive features of the new model to the conventional neural-network based ones are that it has not only meaningful interpretation on part of its parameters but also is linear for the input variables. The former feature makes the parameter estimation easier and the latter allows deriving a nonlinear controller directly from the identified prediction model. The modeling and the parameter estimation are described in detail. The usefulness of the new model is demonstrated by applying it to control of two simulated nonlinear black-box systems.

Original language	English
Title of host publication	IFAC Proceedings Volumes (IFAC-PapersOnline)
Publisher	IFAC Secretariat
Pages	199-204
Number of pages	6
Volume	15
Edition	1
Publication status	Published - 2002
Externally published	Yes
Event	15th World Congress of the International Federation of Automatic Control, 2002 - Barcelona, Spain Duration: 2002 Jul 21 → 2002 Jul 26

Other

Other	15th World Congress of the International Federation of Automatic Control, 2002
Country	Spain
City	Barcelona
Period	02/7/21 → 02/7/26

Keywords

Neural network
Nonlinear control
Nonlinear model
Parameter estimation
System modeling

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

Fingerprint Dive into the research topics of 'A quasi-ARX model incorporating neural network for control of nonlinear systems'. Together they form a unique fingerprint.

Cite this

Furuzuki, T., Hirasawa, K., & Kumamaru, K. (2002). A quasi-ARX model incorporating neural network for control of nonlinear systems. In IFAC Proceedings Volumes (IFAC-PapersOnline) (1 ed., Vol. 15, pp. 199-204). IFAC Secretariat.

@inproceedings{680daaafd2814dfa97c9c57c59841ea7,

title = "A quasi-ARX model incorporating neural network for control of nonlinear systems",

abstract = "Neural networks have been known as flexible nonlinear black-box models and have attracted much interest in control community. This paper introduces a new neural-network based prediction model for control of nonlinear systems. Distinctive features of the new model to the conventional neural-network based ones are that it has not only meaningful interpretation on part of its parameters but also is linear for the input variables. The former feature makes the parameter estimation easier and the latter allows deriving a nonlinear controller directly from the identified prediction model. The modeling and the parameter estimation are described in detail. The usefulness of the new model is demonstrated by applying it to control of two simulated nonlinear black-box systems.",

keywords = "Neural network, Nonlinear control, Nonlinear model, Parameter estimation, System modeling",

author = "Takayuki Furuzuki and Kotaro Hirasawa and Kousuke Kumamaru",

year = "2002",

language = "English",

volume = "15",

pages = "199--204",

booktitle = "IFAC Proceedings Volumes (IFAC-PapersOnline)",

publisher = "IFAC Secretariat",

edition = "1",

note = "15th World Congress of the International Federation of Automatic Control, 2002 ; Conference date: 21-07-2002 Through 26-07-2002",

}

TY - GEN

T1 - A quasi-ARX model incorporating neural network for control of nonlinear systems

AU - Furuzuki, Takayuki

AU - Hirasawa, Kotaro

AU - Kumamaru, Kousuke

PY - 2002

Y1 - 2002

N2 - Neural networks have been known as flexible nonlinear black-box models and have attracted much interest in control community. This paper introduces a new neural-network based prediction model for control of nonlinear systems. Distinctive features of the new model to the conventional neural-network based ones are that it has not only meaningful interpretation on part of its parameters but also is linear for the input variables. The former feature makes the parameter estimation easier and the latter allows deriving a nonlinear controller directly from the identified prediction model. The modeling and the parameter estimation are described in detail. The usefulness of the new model is demonstrated by applying it to control of two simulated nonlinear black-box systems.

AB - Neural networks have been known as flexible nonlinear black-box models and have attracted much interest in control community. This paper introduces a new neural-network based prediction model for control of nonlinear systems. Distinctive features of the new model to the conventional neural-network based ones are that it has not only meaningful interpretation on part of its parameters but also is linear for the input variables. The former feature makes the parameter estimation easier and the latter allows deriving a nonlinear controller directly from the identified prediction model. The modeling and the parameter estimation are described in detail. The usefulness of the new model is demonstrated by applying it to control of two simulated nonlinear black-box systems.

KW - Neural network

KW - Nonlinear control

KW - Nonlinear model

KW - Parameter estimation

KW - System modeling

UR - http://www.scopus.com/inward/record.url?scp=84945540827&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945540827&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84945540827

VL - 15

SP - 199

EP - 204

BT - IFAC Proceedings Volumes (IFAC-PapersOnline)

PB - IFAC Secretariat

T2 - 15th World Congress of the International Federation of Automatic Control, 2002

Y2 - 21 July 2002 through 26 July 2002

ER -