Neural networks for system identification of coupled ship dynamics

P. Martin, Reza Katebi, I. Yamamoto, K. Daigo, E. Kobayashi, M. Matsuura, M. Hashimoto, H. Hirayama, N. Okamoto

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

Abstract

System identification of coupled ship dynamics is problematic with standard least squares methods due to the non-linear, multivariable nature of the system. Neural Networks have therefore been applied to this problem, as they are particularly suitable for approximating non-linear, multivariable functions. In this paper, results of identification with Neural Networks are given for a ship motion simulation based on a standard mathematical model, and for real data collected from a 1/50(th) scale model of the system. The method is seen to be successful at various operating points, and ideas for extension of the work are discussed.
LanguageEnglish
Title of host publicationControl applications in marine systems 2001 (CAMS 2001)
Subtitle of host publicationproceedings of IFAC conference on control applications in marine systems
EditorsR. Katebi
Place of PublicationKidlington
Pages83-88
Number of pages6
Publication statusPublished - 2002
EventIFAC Conference on Control Applications in Marine Systems - Glasgow, United Kingdom
Duration: 18 Jul 200120 Jul 2001

Publication series

NameIFAC Proceedings Series
PublisherPergamon-Elsevier

Conference

ConferenceIFAC Conference on Control Applications in Marine Systems
CountryUnited Kingdom
CityGlasgow
Period18/07/0120/07/01

Fingerprint

Identification (control systems)
Ships
Neural networks
Mathematical models

Keywords

  • neural networks
  • system identification
  • coupled ship dynamics

Cite this

Martin, P., Katebi, R., Yamamoto, I., Daigo, K., Kobayashi, E., Matsuura, M., ... Okamoto, N. (2002). Neural networks for system identification of coupled ship dynamics. In R. Katebi (Ed.), Control applications in marine systems 2001 (CAMS 2001) : proceedings of IFAC conference on control applications in marine systems (pp. 83-88). (IFAC Proceedings Series). Kidlington.
Martin, P. ; Katebi, Reza ; Yamamoto, I. ; Daigo, K. ; Kobayashi, E. ; Matsuura, M. ; Hashimoto, M. ; Hirayama, H. ; Okamoto, N. / Neural networks for system identification of coupled ship dynamics. Control applications in marine systems 2001 (CAMS 2001) : proceedings of IFAC conference on control applications in marine systems . editor / R. Katebi. Kidlington, 2002. pp. 83-88 (IFAC Proceedings Series).
@inproceedings{4bf9ddea9ffb4d3eacea3f6057b4faba,
title = "Neural networks for system identification of coupled ship dynamics",
abstract = "System identification of coupled ship dynamics is problematic with standard least squares methods due to the non-linear, multivariable nature of the system. Neural Networks have therefore been applied to this problem, as they are particularly suitable for approximating non-linear, multivariable functions. In this paper, results of identification with Neural Networks are given for a ship motion simulation based on a standard mathematical model, and for real data collected from a 1/50(th) scale model of the system. The method is seen to be successful at various operating points, and ideas for extension of the work are discussed.",
keywords = "neural networks, system identification, coupled ship dynamics",
author = "P. Martin and Reza Katebi and I. Yamamoto and K. Daigo and E. Kobayashi and M. Matsuura and M. Hashimoto and H. Hirayama and N. Okamoto",
year = "2002",
language = "English",
isbn = "0080432360",
series = "IFAC Proceedings Series",
publisher = "Pergamon-Elsevier",
pages = "83--88",
editor = "R. Katebi",
booktitle = "Control applications in marine systems 2001 (CAMS 2001)",

}

Martin, P, Katebi, R, Yamamoto, I, Daigo, K, Kobayashi, E, Matsuura, M, Hashimoto, M, Hirayama, H & Okamoto, N 2002, Neural networks for system identification of coupled ship dynamics. in R Katebi (ed.), Control applications in marine systems 2001 (CAMS 2001) : proceedings of IFAC conference on control applications in marine systems . IFAC Proceedings Series, Kidlington, pp. 83-88, IFAC Conference on Control Applications in Marine Systems , Glasgow, United Kingdom, 18/07/01.

Neural networks for system identification of coupled ship dynamics. / Martin, P.; Katebi, Reza; Yamamoto, I.; Daigo, K.; Kobayashi, E.; Matsuura, M.; Hashimoto, M.; Hirayama, H.; Okamoto, N.

Control applications in marine systems 2001 (CAMS 2001) : proceedings of IFAC conference on control applications in marine systems . ed. / R. Katebi. Kidlington, 2002. p. 83-88 (IFAC Proceedings Series).

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

TY - GEN

T1 - Neural networks for system identification of coupled ship dynamics

AU - Martin, P.

AU - Katebi, Reza

AU - Yamamoto, I.

AU - Daigo, K.

AU - Kobayashi, E.

AU - Matsuura, M.

AU - Hashimoto, M.

AU - Hirayama, H.

AU - Okamoto, N.

PY - 2002

Y1 - 2002

N2 - System identification of coupled ship dynamics is problematic with standard least squares methods due to the non-linear, multivariable nature of the system. Neural Networks have therefore been applied to this problem, as they are particularly suitable for approximating non-linear, multivariable functions. In this paper, results of identification with Neural Networks are given for a ship motion simulation based on a standard mathematical model, and for real data collected from a 1/50(th) scale model of the system. The method is seen to be successful at various operating points, and ideas for extension of the work are discussed.

AB - System identification of coupled ship dynamics is problematic with standard least squares methods due to the non-linear, multivariable nature of the system. Neural Networks have therefore been applied to this problem, as they are particularly suitable for approximating non-linear, multivariable functions. In this paper, results of identification with Neural Networks are given for a ship motion simulation based on a standard mathematical model, and for real data collected from a 1/50(th) scale model of the system. The method is seen to be successful at various operating points, and ideas for extension of the work are discussed.

KW - neural networks

KW - system identification

KW - coupled ship dynamics

M3 - Conference contribution book

SN - 0080432360

T3 - IFAC Proceedings Series

SP - 83

EP - 88

BT - Control applications in marine systems 2001 (CAMS 2001)

A2 - Katebi, R.

CY - Kidlington

ER -

Martin P, Katebi R, Yamamoto I, Daigo K, Kobayashi E, Matsuura M et al. Neural networks for system identification of coupled ship dynamics. In Katebi R, editor, Control applications in marine systems 2001 (CAMS 2001) : proceedings of IFAC conference on control applications in marine systems . Kidlington. 2002. p. 83-88. (IFAC Proceedings Series).