Robust learning control using universal learning network

Masanao Ohbayashi, Kotaro Hirasawa, Junichi Murata, Masaaki Harada

Research output: Contribution to conferencePaper

13 Citations (Scopus)

Abstract

Characteristics of control system design using Universal Learning Network(U.L.N.) are that a system to be controlled and a controller are both constructed by U.L.N. and that the controller is best tuned through learning. U.L.N. has the same generalization ability as N.N.. So the controller constructed by U.L.N. is able to control the system in a favorable way under the condition different from the condition of the control system at learning stage. But stability can not be realized sufficiently. In this paper, we propose a robust learning control method using U.L.N. and second order derivatives of U.L.N.. The proposed method can realize better performance and robustness than the commonly used Neural Network. Robust learning control considered here is defined as follows. Even though initial values of node outputs change from those at learning, the control system is able to reduce its influence to other node outputs and can control the system in a preferable way as in the case of no variation.

Original languageEnglish
Pages2208-2213
Number of pages6
Publication statusPublished - Jan 1 1996
EventProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA
Duration: Jun 3 1996Jun 6 1996

Other

OtherProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
CityWashington, DC, USA
Period6/3/966/6/96

Fingerprint

Control systems
Controllers
Systems analysis
Derivatives
Neural networks

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Ohbayashi, M., Hirasawa, K., Murata, J., & Harada, M. (1996). Robust learning control using universal learning network. 2208-2213. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .

Robust learning control using universal learning network. / Ohbayashi, Masanao; Hirasawa, Kotaro; Murata, Junichi; Harada, Masaaki.

1996. 2208-2213 Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .

Research output: Contribution to conferencePaper

Ohbayashi, M, Hirasawa, K, Murata, J & Harada, M 1996, 'Robust learning control using universal learning network' Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, 6/3/96 - 6/6/96, pp. 2208-2213.
Ohbayashi M, Hirasawa K, Murata J, Harada M. Robust learning control using universal learning network. 1996. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .
Ohbayashi, Masanao ; Hirasawa, Kotaro ; Murata, Junichi ; Harada, Masaaki. / Robust learning control using universal learning network. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .6 p.
@conference{9539932fa57549f2a41a0ec8b3217787,
title = "Robust learning control using universal learning network",
abstract = "Characteristics of control system design using Universal Learning Network(U.L.N.) are that a system to be controlled and a controller are both constructed by U.L.N. and that the controller is best tuned through learning. U.L.N. has the same generalization ability as N.N.. So the controller constructed by U.L.N. is able to control the system in a favorable way under the condition different from the condition of the control system at learning stage. But stability can not be realized sufficiently. In this paper, we propose a robust learning control method using U.L.N. and second order derivatives of U.L.N.. The proposed method can realize better performance and robustness than the commonly used Neural Network. Robust learning control considered here is defined as follows. Even though initial values of node outputs change from those at learning, the control system is able to reduce its influence to other node outputs and can control the system in a preferable way as in the case of no variation.",
author = "Masanao Ohbayashi and Kotaro Hirasawa and Junichi Murata and Masaaki Harada",
year = "1996",
month = "1",
day = "1",
language = "English",
pages = "2208--2213",
note = "Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) ; Conference date: 03-06-1996 Through 06-06-1996",

}

TY - CONF

T1 - Robust learning control using universal learning network

AU - Ohbayashi, Masanao

AU - Hirasawa, Kotaro

AU - Murata, Junichi

AU - Harada, Masaaki

PY - 1996/1/1

Y1 - 1996/1/1

N2 - Characteristics of control system design using Universal Learning Network(U.L.N.) are that a system to be controlled and a controller are both constructed by U.L.N. and that the controller is best tuned through learning. U.L.N. has the same generalization ability as N.N.. So the controller constructed by U.L.N. is able to control the system in a favorable way under the condition different from the condition of the control system at learning stage. But stability can not be realized sufficiently. In this paper, we propose a robust learning control method using U.L.N. and second order derivatives of U.L.N.. The proposed method can realize better performance and robustness than the commonly used Neural Network. Robust learning control considered here is defined as follows. Even though initial values of node outputs change from those at learning, the control system is able to reduce its influence to other node outputs and can control the system in a preferable way as in the case of no variation.

AB - Characteristics of control system design using Universal Learning Network(U.L.N.) are that a system to be controlled and a controller are both constructed by U.L.N. and that the controller is best tuned through learning. U.L.N. has the same generalization ability as N.N.. So the controller constructed by U.L.N. is able to control the system in a favorable way under the condition different from the condition of the control system at learning stage. But stability can not be realized sufficiently. In this paper, we propose a robust learning control method using U.L.N. and second order derivatives of U.L.N.. The proposed method can realize better performance and robustness than the commonly used Neural Network. Robust learning control considered here is defined as follows. Even though initial values of node outputs change from those at learning, the control system is able to reduce its influence to other node outputs and can control the system in a preferable way as in the case of no variation.

UR - http://www.scopus.com/inward/record.url?scp=0029728598&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029728598&partnerID=8YFLogxK

M3 - Paper

SP - 2208

EP - 2213

ER -