Control of nonlinear mechatronics systems by using universal learning networks

Chun zhi Jin, Kotaro Hirasawa, Murata Junichi, Takayuki Furuzuki

研究成果: Conference contribution

1 引用 (Scopus)

抄録

Nonlinear elements such as friction, dead zone, backlash are mixed in most mechatronics systems, and these are factors that make control accuracy of systems decrease and cause an oscillation. It is difficult to deal with the problems of modeling and control of such systems using common sigmoidal neural networks because there exist nonsmooth nonlinearities in the systems, and there is no easy way to incorporate knowledge and experiences accumulated from past study. In this paper, a design method for nonlinear mechatronics control systems is proposed, in which both of the control object and its controller are represented by using a Universal Learning Network, and the network parameters are trained using a random search algorithm called RasID. In this approach, knowledge and experience about models and controllers are easily incorporated into the network including the nonlinear elements and their compensation elements expressed by non-differentiable functions. Some simulations of a nonlinear crane control system with dead-zone characteristic were carried out. The effectiveness of the proposed design method is illustrated via simulations.

元の言語English
ホスト出版物のタイトルProceedings of the IEEE International Conference on Systems, Man and Cybernetics
出版者IEEE
5
出版物ステータスPublished - 1999
外部発表Yes
イベント1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics' - Tokyo, Jpn
継続期間: 1999 10 121999 10 15

Other

Other1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics'
Tokyo, Jpn
期間99/10/1299/10/15

Fingerprint

Mechatronics
Control systems
Controllers
Cranes
Friction
Neural networks

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

これを引用

Jin, C. Z., Hirasawa, K., Junichi, M., & Furuzuki, T. (1999). Control of nonlinear mechatronics systems by using universal learning networks. : Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (巻 5). IEEE.

Control of nonlinear mechatronics systems by using universal learning networks. / Jin, Chun zhi; Hirasawa, Kotaro; Junichi, Murata; Furuzuki, Takayuki.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. 巻 5 IEEE, 1999.

研究成果: Conference contribution

Jin, CZ, Hirasawa, K, Junichi, M & Furuzuki, T 1999, Control of nonlinear mechatronics systems by using universal learning networks. : Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. 巻. 5, IEEE, 1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics', Tokyo, Jpn, 99/10/12.
Jin CZ, Hirasawa K, Junichi M, Furuzuki T. Control of nonlinear mechatronics systems by using universal learning networks. : Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. 巻 5. IEEE. 1999
Jin, Chun zhi ; Hirasawa, Kotaro ; Junichi, Murata ; Furuzuki, Takayuki. / Control of nonlinear mechatronics systems by using universal learning networks. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. 巻 5 IEEE, 1999.
@inproceedings{1c6d06f41a854038a64317181fc6c901,
title = "Control of nonlinear mechatronics systems by using universal learning networks",
abstract = "Nonlinear elements such as friction, dead zone, backlash are mixed in most mechatronics systems, and these are factors that make control accuracy of systems decrease and cause an oscillation. It is difficult to deal with the problems of modeling and control of such systems using common sigmoidal neural networks because there exist nonsmooth nonlinearities in the systems, and there is no easy way to incorporate knowledge and experiences accumulated from past study. In this paper, a design method for nonlinear mechatronics control systems is proposed, in which both of the control object and its controller are represented by using a Universal Learning Network, and the network parameters are trained using a random search algorithm called RasID. In this approach, knowledge and experience about models and controllers are easily incorporated into the network including the nonlinear elements and their compensation elements expressed by non-differentiable functions. Some simulations of a nonlinear crane control system with dead-zone characteristic were carried out. The effectiveness of the proposed design method is illustrated via simulations.",
author = "Jin, {Chun zhi} and Kotaro Hirasawa and Murata Junichi and Takayuki Furuzuki",
year = "1999",
language = "English",
volume = "5",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - Control of nonlinear mechatronics systems by using universal learning networks

AU - Jin, Chun zhi

AU - Hirasawa, Kotaro

AU - Junichi, Murata

AU - Furuzuki, Takayuki

PY - 1999

Y1 - 1999

N2 - Nonlinear elements such as friction, dead zone, backlash are mixed in most mechatronics systems, and these are factors that make control accuracy of systems decrease and cause an oscillation. It is difficult to deal with the problems of modeling and control of such systems using common sigmoidal neural networks because there exist nonsmooth nonlinearities in the systems, and there is no easy way to incorporate knowledge and experiences accumulated from past study. In this paper, a design method for nonlinear mechatronics control systems is proposed, in which both of the control object and its controller are represented by using a Universal Learning Network, and the network parameters are trained using a random search algorithm called RasID. In this approach, knowledge and experience about models and controllers are easily incorporated into the network including the nonlinear elements and their compensation elements expressed by non-differentiable functions. Some simulations of a nonlinear crane control system with dead-zone characteristic were carried out. The effectiveness of the proposed design method is illustrated via simulations.

AB - Nonlinear elements such as friction, dead zone, backlash are mixed in most mechatronics systems, and these are factors that make control accuracy of systems decrease and cause an oscillation. It is difficult to deal with the problems of modeling and control of such systems using common sigmoidal neural networks because there exist nonsmooth nonlinearities in the systems, and there is no easy way to incorporate knowledge and experiences accumulated from past study. In this paper, a design method for nonlinear mechatronics control systems is proposed, in which both of the control object and its controller are represented by using a Universal Learning Network, and the network parameters are trained using a random search algorithm called RasID. In this approach, knowledge and experience about models and controllers are easily incorporated into the network including the nonlinear elements and their compensation elements expressed by non-differentiable functions. Some simulations of a nonlinear crane control system with dead-zone characteristic were carried out. The effectiveness of the proposed design method is illustrated via simulations.

UR - http://www.scopus.com/inward/record.url?scp=17144461328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17144461328&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:17144461328

VL - 5

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

PB - IEEE

ER -