Impedance model force control using a neural network-based effective stiffness estimator

F. Nagata, T. Mizobuchi, T. Hase, Z. Haga, Keigo Watanabe, Maki K. Habib

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In manufacturing industries of metallic molds, various NC machine tools are used. We have already proposed a desktop NC machine tool with compliance control capability to automatically cope with the finishing process of LED lens molds. The NC machine tool has an ability to control the polishing force acting between an abrasive tool and a workpiece. The force control method is called impedance model force control. The most effective gain is the desired damping of the impedance model. Ideally, the desired damping is calculated from the critical damping condition in consideration of the effective stiffness in force control system. However, there exists a problem that the effective stiffness of the NC machine tool has undesirable nonlinearity. The nonlinearity gives bad influences to the force control stability. In this paper, a fine tuning method of the desired damping is considered by using neural networks. The neural networks acquire the nonlinearity of effective stiffness. The promise is evaluated through an experiment.

Original languageEnglish
Title of host publicationProceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10
Pages697-700
Number of pages4
Publication statusPublished - 2010
Event15th International Symposium on Artificial Life and Robotics, AROB '10 - Beppu, Oita, Japan
Duration: Feb 4 2010Feb 6 2010

Other

Other15th International Symposium on Artificial Life and Robotics, AROB '10
CountryJapan
CityBeppu, Oita
Period2/4/102/6/10

Fingerprint

Force control
Machine tools
Damping
Stiffness
Neural networks
Molds
Compliance control
Polishing
Abrasives
Light emitting diodes
Lenses
Tuning
Control systems
Industry
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

Nagata, F., Mizobuchi, T., Hase, T., Haga, Z., Watanabe, K., & Habib, M. K. (2010). Impedance model force control using a neural network-based effective stiffness estimator. In Proceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10 (pp. 697-700)

Impedance model force control using a neural network-based effective stiffness estimator. / Nagata, F.; Mizobuchi, T.; Hase, T.; Haga, Z.; Watanabe, Keigo; Habib, Maki K.

Proceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10. 2010. p. 697-700.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nagata, F, Mizobuchi, T, Hase, T, Haga, Z, Watanabe, K & Habib, MK 2010, Impedance model force control using a neural network-based effective stiffness estimator. in Proceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10. pp. 697-700, 15th International Symposium on Artificial Life and Robotics, AROB '10, Beppu, Oita, Japan, 2/4/10.
Nagata F, Mizobuchi T, Hase T, Haga Z, Watanabe K, Habib MK. Impedance model force control using a neural network-based effective stiffness estimator. In Proceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10. 2010. p. 697-700
Nagata, F. ; Mizobuchi, T. ; Hase, T. ; Haga, Z. ; Watanabe, Keigo ; Habib, Maki K. / Impedance model force control using a neural network-based effective stiffness estimator. Proceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10. 2010. pp. 697-700
@inproceedings{932efd98aee54f3f891acbcb8e104edc,
title = "Impedance model force control using a neural network-based effective stiffness estimator",
abstract = "In manufacturing industries of metallic molds, various NC machine tools are used. We have already proposed a desktop NC machine tool with compliance control capability to automatically cope with the finishing process of LED lens molds. The NC machine tool has an ability to control the polishing force acting between an abrasive tool and a workpiece. The force control method is called impedance model force control. The most effective gain is the desired damping of the impedance model. Ideally, the desired damping is calculated from the critical damping condition in consideration of the effective stiffness in force control system. However, there exists a problem that the effective stiffness of the NC machine tool has undesirable nonlinearity. The nonlinearity gives bad influences to the force control stability. In this paper, a fine tuning method of the desired damping is considered by using neural networks. The neural networks acquire the nonlinearity of effective stiffness. The promise is evaluated through an experiment.",
author = "F. Nagata and T. Mizobuchi and T. Hase and Z. Haga and Keigo Watanabe and Habib, {Maki K.}",
year = "2010",
language = "English",
isbn = "9784990288044",
pages = "697--700",
booktitle = "Proceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10",

}

TY - GEN

T1 - Impedance model force control using a neural network-based effective stiffness estimator

AU - Nagata, F.

AU - Mizobuchi, T.

AU - Hase, T.

AU - Haga, Z.

AU - Watanabe, Keigo

AU - Habib, Maki K.

PY - 2010

Y1 - 2010

N2 - In manufacturing industries of metallic molds, various NC machine tools are used. We have already proposed a desktop NC machine tool with compliance control capability to automatically cope with the finishing process of LED lens molds. The NC machine tool has an ability to control the polishing force acting between an abrasive tool and a workpiece. The force control method is called impedance model force control. The most effective gain is the desired damping of the impedance model. Ideally, the desired damping is calculated from the critical damping condition in consideration of the effective stiffness in force control system. However, there exists a problem that the effective stiffness of the NC machine tool has undesirable nonlinearity. The nonlinearity gives bad influences to the force control stability. In this paper, a fine tuning method of the desired damping is considered by using neural networks. The neural networks acquire the nonlinearity of effective stiffness. The promise is evaluated through an experiment.

AB - In manufacturing industries of metallic molds, various NC machine tools are used. We have already proposed a desktop NC machine tool with compliance control capability to automatically cope with the finishing process of LED lens molds. The NC machine tool has an ability to control the polishing force acting between an abrasive tool and a workpiece. The force control method is called impedance model force control. The most effective gain is the desired damping of the impedance model. Ideally, the desired damping is calculated from the critical damping condition in consideration of the effective stiffness in force control system. However, there exists a problem that the effective stiffness of the NC machine tool has undesirable nonlinearity. The nonlinearity gives bad influences to the force control stability. In this paper, a fine tuning method of the desired damping is considered by using neural networks. The neural networks acquire the nonlinearity of effective stiffness. The promise is evaluated through an experiment.

UR - http://www.scopus.com/inward/record.url?scp=84866647300&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866647300&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84866647300

SN - 9784990288044

SP - 697

EP - 700

BT - Proceedings of the 15th International Symposium on Artificial Life and Robotics, AROB 15th'10

ER -