Picture of wind turbine against blue sky

Open Access research with a real impact...

The Strathprints institutional repository is a digital archive of University of Strathclyde research outputs.

The Energy Systems Research Unit (ESRU) within Strathclyde's Department of Mechanical and Aerospace Engineering is producing Open Access research that can help society deploy and optimise renewable energy systems, such as wind turbine technology.

Explore wind turbine research in Strathprints

Explore all of Strathclyde's Open Access research content

Neural networks for system identification of coupled ship dynamics

Martin, P. and Katebi, Reza and Yamamoto, I. and Daigo, K. and Kobayashi, E. and Matsuura, M. and Hashimoto, M. and Hirayama, H. and Okamoto, N. (2002) Neural networks for system identification of coupled ship dynamics. In: Control applications in marine systems 2001 (CAMS 2001). IFAC Proceedings Series . PERGAMON-ELSEVIER SCIENCE LTD, Kidlington, pp. 83-88. ISBN 0080432360

Full text not available in this repository. (Request a copy from the Strathclyde author)

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.