Neural Network based estimation of friction coefficient of wheel and rail

Tibor Gajdar, I. Rudas, Yoshihiro Suda

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

18 Citations (Scopus)

Abstract

The number of modern control theory applications in vehicle dynamics are emerging and have led to great progress in vehicle stability, handling and ride comfort. However, some of the parameters needed for control applications are difficult to measure on line. Such examples are the wheel/rail contact forces, attack angles of wheelsets and the friction coefficient μ between wheel and rail of railway vehicles. Other areas where the adequate knowledge of adhesion is vital are the electric drive and adhesion control systems of locomotive drive systems, since as the result of changing friction coefficient wheel spinning, slipping can occur, which can cause faulty operation and overloading of traction units. In order to cope with this problem, this paper presents different methods to estimate the friction coefficient μ, based on Neural network estimation and a computational method.

Original languageEnglish
Title of host publicationIEEE International Conference on Intelligent Engineering Systems, Proceedings, INES
PublisherIEEE
Pages315-318
Number of pages4
Publication statusPublished - 1997
EventProceedings of the 1997 International Conference on Intelligent Engineering Systems, INES - Budapest, Hungary
Duration: Sep 15 1997Sep 17 1997

Other

OtherProceedings of the 1997 International Conference on Intelligent Engineering Systems, INES
CityBudapest, Hungary
Period9/15/979/17/97

Fingerprint

Rails
Wheels
Friction
Neural networks
Adhesion
Electric drives
Locomotives
Angle of attack
Computational methods
Control theory
Control systems

ASJC Scopus subject areas

  • Engineering(all)
  • Materials Science(all)

Cite this

Gajdar, T., Rudas, I., & Suda, Y. (1997). Neural Network based estimation of friction coefficient of wheel and rail. In IEEE International Conference on Intelligent Engineering Systems, Proceedings, INES (pp. 315-318). IEEE.

Neural Network based estimation of friction coefficient of wheel and rail. / Gajdar, Tibor; Rudas, I.; Suda, Yoshihiro.

IEEE International Conference on Intelligent Engineering Systems, Proceedings, INES. IEEE, 1997. p. 315-318.

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

Gajdar, T, Rudas, I & Suda, Y 1997, Neural Network based estimation of friction coefficient of wheel and rail. in IEEE International Conference on Intelligent Engineering Systems, Proceedings, INES. IEEE, pp. 315-318, Proceedings of the 1997 International Conference on Intelligent Engineering Systems, INES, Budapest, Hungary, 9/15/97.
Gajdar T, Rudas I, Suda Y. Neural Network based estimation of friction coefficient of wheel and rail. In IEEE International Conference on Intelligent Engineering Systems, Proceedings, INES. IEEE. 1997. p. 315-318
Gajdar, Tibor ; Rudas, I. ; Suda, Yoshihiro. / Neural Network based estimation of friction coefficient of wheel and rail. IEEE International Conference on Intelligent Engineering Systems, Proceedings, INES. IEEE, 1997. pp. 315-318
@inproceedings{095d63be3b8b4a36bf790c77bd5bd963,
title = "Neural Network based estimation of friction coefficient of wheel and rail",
abstract = "The number of modern control theory applications in vehicle dynamics are emerging and have led to great progress in vehicle stability, handling and ride comfort. However, some of the parameters needed for control applications are difficult to measure on line. Such examples are the wheel/rail contact forces, attack angles of wheelsets and the friction coefficient μ between wheel and rail of railway vehicles. Other areas where the adequate knowledge of adhesion is vital are the electric drive and adhesion control systems of locomotive drive systems, since as the result of changing friction coefficient wheel spinning, slipping can occur, which can cause faulty operation and overloading of traction units. In order to cope with this problem, this paper presents different methods to estimate the friction coefficient μ, based on Neural network estimation and a computational method.",
author = "Tibor Gajdar and I. Rudas and Yoshihiro Suda",
year = "1997",
language = "English",
pages = "315--318",
booktitle = "IEEE International Conference on Intelligent Engineering Systems, Proceedings, INES",
publisher = "IEEE",

}

TY - GEN

T1 - Neural Network based estimation of friction coefficient of wheel and rail

AU - Gajdar, Tibor

AU - Rudas, I.

AU - Suda, Yoshihiro

PY - 1997

Y1 - 1997

N2 - The number of modern control theory applications in vehicle dynamics are emerging and have led to great progress in vehicle stability, handling and ride comfort. However, some of the parameters needed for control applications are difficult to measure on line. Such examples are the wheel/rail contact forces, attack angles of wheelsets and the friction coefficient μ between wheel and rail of railway vehicles. Other areas where the adequate knowledge of adhesion is vital are the electric drive and adhesion control systems of locomotive drive systems, since as the result of changing friction coefficient wheel spinning, slipping can occur, which can cause faulty operation and overloading of traction units. In order to cope with this problem, this paper presents different methods to estimate the friction coefficient μ, based on Neural network estimation and a computational method.

AB - The number of modern control theory applications in vehicle dynamics are emerging and have led to great progress in vehicle stability, handling and ride comfort. However, some of the parameters needed for control applications are difficult to measure on line. Such examples are the wheel/rail contact forces, attack angles of wheelsets and the friction coefficient μ between wheel and rail of railway vehicles. Other areas where the adequate knowledge of adhesion is vital are the electric drive and adhesion control systems of locomotive drive systems, since as the result of changing friction coefficient wheel spinning, slipping can occur, which can cause faulty operation and overloading of traction units. In order to cope with this problem, this paper presents different methods to estimate the friction coefficient μ, based on Neural network estimation and a computational method.

UR - http://www.scopus.com/inward/record.url?scp=0031336992&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031336992&partnerID=8YFLogxK

M3 - Conference contribution

SP - 315

EP - 318

BT - IEEE International Conference on Intelligent Engineering Systems, Proceedings, INES

PB - IEEE

ER -