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 |
Fingerprint
Keywords
- Neural network
- Nonlinear control
- Nonlinear model
- Parameter estimation
- System modeling
ASJC Scopus subject areas
- Control and Systems Engineering
Cite this
A quasi-ARX model incorporating neural network for control of nonlinear systems. / Furuzuki, Takayuki; Hirasawa, Kotaro; Kumamaru, Kousuke.
IFAC Proceedings Volumes (IFAC-PapersOnline). Vol. 15 1. ed. IFAC Secretariat, 2002. p. 199-204.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
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
ER -