Force modeling of inhomogeneous material using unsupervised learning and model identification

Chen Zhao; Heinz Ulbrich

doi:10.1109/ROBIO.2009.4913191

Force modeling of inhomogeneous material using unsupervised learning and model identification

Chen Zhao, Heinz Ulbrich

Chair of Applied Mechanics

Technical University of Munich

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

In this paper a force modeling method for inhomogeneous materials is introduced. This modeling method is based on samples during haptic operations, for instance presses. Using biomimetic unsupervised learning, the model is primarily identified, including the distribution and material parameters of the inhomogeneous regions, and in this learning the parameter initial estimation, the principal component analysis, the cluster analysis and the quadratic discriminant analysis are applied. Then the material parameters and boundaries of the different regions are accurately optimized using the Gauss-Newton algorithm. Further more the modeling method is tested and verified by a set of simulations. In addition, the suggestions and prospect of the modeling method are also given.

Original language	English
Title of host publication	2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008
Publisher	IEEE Computer Society
Pages	1319-1324
Number of pages	6
ISBN (Print)	9781424426799
DOIs	https://doi.org/10.1109/ROBIO.2009.4913191
State	Published - 2009
Event	2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008 - Bangkok, Thailand Duration: 21 Feb 2009 → 26 Feb 2009

Publication series

Name	2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008

Conference

Conference	2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008
Country/Territory	Thailand
City	Bangkok
Period	21/02/09 → 26/02/09

Keywords

Finite element method
Force model
Inhomogeneous material
Parameter identification
Unsupervised learning

Access to Document

10.1109/ROBIO.2009.4913191

Cite this

Zhao, C., & Ulbrich, H. (2009). Force modeling of inhomogeneous material using unsupervised learning and model identification. In 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008 (pp. 1319-1324). Article 4913191 (2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008). IEEE Computer Society. https://doi.org/10.1109/ROBIO.2009.4913191

@inproceedings{dfbe4b7679ac48ebac736d3e23baff52,

title = "Force modeling of inhomogeneous material using unsupervised learning and model identification",

abstract = "In this paper a force modeling method for inhomogeneous materials is introduced. This modeling method is based on samples during haptic operations, for instance presses. Using biomimetic unsupervised learning, the model is primarily identified, including the distribution and material parameters of the inhomogeneous regions, and in this learning the parameter initial estimation, the principal component analysis, the cluster analysis and the quadratic discriminant analysis are applied. Then the material parameters and boundaries of the different regions are accurately optimized using the Gauss-Newton algorithm. Further more the modeling method is tested and verified by a set of simulations. In addition, the suggestions and prospect of the modeling method are also given.",

keywords = "Finite element method, Force model, Inhomogeneous material, Parameter identification, Unsupervised learning",

author = "Chen Zhao and Heinz Ulbrich",

year = "2009",

doi = "10.1109/ROBIO.2009.4913191",

language = "English",

isbn = "9781424426799",

series = "2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008",

publisher = "IEEE Computer Society",

pages = "1319--1324",

booktitle = "2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008",

note = "2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008 ; Conference date: 21-02-2009 Through 26-02-2009",

}

Zhao, C & Ulbrich, H 2009, Force modeling of inhomogeneous material using unsupervised learning and model identification. in 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008., 4913191, 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008, IEEE Computer Society, pp. 1319-1324, 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008, Bangkok, Thailand, 21/02/09. https://doi.org/10.1109/ROBIO.2009.4913191

Force modeling of inhomogeneous material using unsupervised learning and model identification. / Zhao, Chen; Ulbrich, Heinz.
2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008. IEEE Computer Society, 2009. p. 1319-1324 4913191 (2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Force modeling of inhomogeneous material using unsupervised learning and model identification

AU - Zhao, Chen

AU - Ulbrich, Heinz

PY - 2009

Y1 - 2009

N2 - In this paper a force modeling method for inhomogeneous materials is introduced. This modeling method is based on samples during haptic operations, for instance presses. Using biomimetic unsupervised learning, the model is primarily identified, including the distribution and material parameters of the inhomogeneous regions, and in this learning the parameter initial estimation, the principal component analysis, the cluster analysis and the quadratic discriminant analysis are applied. Then the material parameters and boundaries of the different regions are accurately optimized using the Gauss-Newton algorithm. Further more the modeling method is tested and verified by a set of simulations. In addition, the suggestions and prospect of the modeling method are also given.

AB - In this paper a force modeling method for inhomogeneous materials is introduced. This modeling method is based on samples during haptic operations, for instance presses. Using biomimetic unsupervised learning, the model is primarily identified, including the distribution and material parameters of the inhomogeneous regions, and in this learning the parameter initial estimation, the principal component analysis, the cluster analysis and the quadratic discriminant analysis are applied. Then the material parameters and boundaries of the different regions are accurately optimized using the Gauss-Newton algorithm. Further more the modeling method is tested and verified by a set of simulations. In addition, the suggestions and prospect of the modeling method are also given.

KW - Finite element method

KW - Force model

KW - Inhomogeneous material

KW - Parameter identification

KW - Unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=70349189041&partnerID=8YFLogxK

U2 - 10.1109/ROBIO.2009.4913191

DO - 10.1109/ROBIO.2009.4913191

M3 - Conference contribution

AN - SCOPUS:70349189041

SN - 9781424426799

T3 - 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008

SP - 1319

EP - 1324

BT - 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008

PB - IEEE Computer Society

T2 - 2008 IEEE International Conference on Robotics and Biomimetics, ROBIO 2008

Y2 - 21 February 2009 through 26 February 2009

ER -

Force modeling of inhomogeneous material using unsupervised learning and model identification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this