Support Vector Machine Networks for Friction Modeling

G. L. Wang; Y. F. Li; X. D. Bi

doi:10.1109/ACC.2003.1243752

Support Vector Machine Networks for Friction Modeling

G. L. Wang
, Y. F. Li
, X. D. Bi

Research output: Journal Publications and Reviews › RGC 22 - Publication in policy or professional journal

1 Citation (Scopus)

Abstract

This paper presents a novel model-free parameterization approach of friction modeling for servo-motion systems, where the static friction behavior is parameterized by Support Vector Machine networks. In training such network via SVM regression, the effort of accounting for the complexity variation of the static friction mapping is made in terms of varying smoothness and error-tolerance constraints. It is experimentally demonstrated that the proposed SVM networks can achieve satisfactory friction predictions.

Original language	English
Pages (from-to)	2833-2838
Journal	Proceedings of the American Control Conference
Volume	4
DOIs	https://doi.org/10.1109/ACC.2003.1243752
Publication status	Published - 2003
Event	2003 American Control Conference (ACC 2003) - The Adams Mark Hotel, Denver, United States Duration: 4 Jun 2003 → 6 Jun 2003 https://ieeexplore.ieee.org/xpl/conhome/8775/proceeding

Access Output

10.1109/ACC.2003.1243752

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{bb020cdc89ea42b488cd9cbd24438a5c,

title = "Support Vector Machine Networks for Friction Modeling",

abstract = "This paper presents a novel model-free parameterization approach of friction modeling for servo-motion systems, where the static friction behavior is parameterized by Support Vector Machine networks. In training such network via SVM regression, the effort of accounting for the complexity variation of the static friction mapping is made in terms of varying smoothness and error-tolerance constraints. It is experimentally demonstrated that the proposed SVM networks can achieve satisfactory friction predictions.",

author = "Wang, \{G. L.\} and Li, \{Y. F.\} and Bi, \{X. D.\}",

year = "2003",

doi = "10.1109/ACC.2003.1243752",

language = "English",

volume = "4",

pages = "2833--2838",

journal = "Proceedings of the American Control Conference",

issn = "0743-1619",

publisher = "IEEE",

note = "2003 American Control Conference (ACC 2003) ; Conference date: 04-06-2003 Through 06-06-2003",

url = "https://ieeexplore.ieee.org/xpl/conhome/8775/proceeding",

}

TY - JOUR

T1 - Support Vector Machine Networks for Friction Modeling

AU - Wang, G. L.

AU - Li, Y. F.

AU - Bi, X. D.

PY - 2003

Y1 - 2003

N2 - This paper presents a novel model-free parameterization approach of friction modeling for servo-motion systems, where the static friction behavior is parameterized by Support Vector Machine networks. In training such network via SVM regression, the effort of accounting for the complexity variation of the static friction mapping is made in terms of varying smoothness and error-tolerance constraints. It is experimentally demonstrated that the proposed SVM networks can achieve satisfactory friction predictions.

AB - This paper presents a novel model-free parameterization approach of friction modeling for servo-motion systems, where the static friction behavior is parameterized by Support Vector Machine networks. In training such network via SVM regression, the effort of accounting for the complexity variation of the static friction mapping is made in terms of varying smoothness and error-tolerance constraints. It is experimentally demonstrated that the proposed SVM networks can achieve satisfactory friction predictions.

UR - https://www.scopus.com/pages/publications/0142153031

UR - https://www.scopus.com/pages/publications/0142153031#tab=impact

U2 - 10.1109/ACC.2003.1243752

DO - 10.1109/ACC.2003.1243752

M3 - RGC 22 - Publication in policy or professional journal

SN - 0743-1619

VL - 4

SP - 2833

EP - 2838

JO - Proceedings of the American Control Conference

JF - Proceedings of the American Control Conference

T2 - 2003 American Control Conference (ACC 2003)

Y2 - 4 June 2003 through 6 June 2003

ER -

Support Vector Machine Networks for Friction Modeling

Abstract

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this