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.
Original 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
Country/TerritoryUnited Kingdom
CityGlasgow
Period18/07/0120/07/01

Keywords

  • neural networks
  • system identification
  • coupled ship dynamics

Fingerprint

Dive into the research topics of 'Neural networks for system identification of coupled ship dynamics'. Together they form a unique fingerprint.

Cite this