A new robust neural network controller designing method for nonlinear systems

H. Chen; K. Hirasawa; J. Hu; J. Murata

A new robust neural network controller designing method for nonlinear systems

H. Chen, K. Hirasawa, J. Hu, J. Murata

Section of Measurement and Control Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

A new designing method of a robust neural network controller against system environment changes using Universal Learning Network (ULN) is considered in this paper. With the introduced method, the worst values of system parameters can be searched as well as the optimization of controller parameters through a dual learning algorithm, which includes maximization and minimization procedures. Therefore, the robust controller can be obtained by minimizing the criterion function regarding the worst values of system parameters. Simulation results demonstrate that the system performance has been improved compared with the conventional method by using the proposed method.

Original language	English
Pages	497-502
Number of pages	6
Publication status	Published - Jan 1 2001
Event	International Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States Duration: Jul 15 2001 → Jul 19 2001

Other

Other	International Joint Conference on Neural Networks (IJCNN'01)
Country/Territory	United States
City	Washington, DC
Period	7/15/01 → 7/19/01

All Science Journal Classification (ASJC) codes

Software
Artificial Intelligence

Cite this

@conference{84d28cb1afba4055b6739613d46b781b,

title = "A new robust neural network controller designing method for nonlinear systems",

abstract = "A new designing method of a robust neural network controller against system environment changes using Universal Learning Network (ULN) is considered in this paper. With the introduced method, the worst values of system parameters can be searched as well as the optimization of controller parameters through a dual learning algorithm, which includes maximization and minimization procedures. Therefore, the robust controller can be obtained by minimizing the criterion function regarding the worst values of system parameters. Simulation results demonstrate that the system performance has been improved compared with the conventional method by using the proposed method.",

author = "H. Chen and K. Hirasawa and J. Hu and J. Murata",

year = "2001",

month = jan,

day = "1",

language = "English",

pages = "497--502",

note = "International Joint Conference on Neural Networks (IJCNN'01) ; Conference date: 15-07-2001 Through 19-07-2001",

}

TY - CONF

T1 - A new robust neural network controller designing method for nonlinear systems

AU - Chen, H.

AU - Hirasawa, K.

AU - Hu, J.

AU - Murata, J.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - A new designing method of a robust neural network controller against system environment changes using Universal Learning Network (ULN) is considered in this paper. With the introduced method, the worst values of system parameters can be searched as well as the optimization of controller parameters through a dual learning algorithm, which includes maximization and minimization procedures. Therefore, the robust controller can be obtained by minimizing the criterion function regarding the worst values of system parameters. Simulation results demonstrate that the system performance has been improved compared with the conventional method by using the proposed method.

AB - A new designing method of a robust neural network controller against system environment changes using Universal Learning Network (ULN) is considered in this paper. With the introduced method, the worst values of system parameters can be searched as well as the optimization of controller parameters through a dual learning algorithm, which includes maximization and minimization procedures. Therefore, the robust controller can be obtained by minimizing the criterion function regarding the worst values of system parameters. Simulation results demonstrate that the system performance has been improved compared with the conventional method by using the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=0034850560&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034850560&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0034850560

SP - 497

EP - 502

T2 - International Joint Conference on Neural Networks (IJCNN'01)

Y2 - 15 July 2001 through 19 July 2001

ER -

A new robust neural network controller designing method for nonlinear systems

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this