### Abstract

Language | English |
---|---|

Title of host publication | Control applications in marine systems 2001 (CAMS 2001) |

Subtitle of host publication | proceedings of IFAC conference on control applications in marine systems |

Editors | R. Katebi |

Place of Publication | Kidlington |

Pages | 83-88 |

Number of pages | 6 |

Publication status | Published - 2002 |

Event | IFAC Conference on Control Applications in Marine Systems - Glasgow, United Kingdom Duration: 18 Jul 2001 → 20 Jul 2001 |

### Publication series

Name | IFAC Proceedings Series |
---|---|

Publisher | Pergamon-Elsevier |

### Conference

Conference | IFAC Conference on Control Applications in Marine Systems |
---|---|

Country | United Kingdom |

City | Glasgow |

Period | 18/07/01 → 20/07/01 |

### Fingerprint

### Keywords

- neural networks
- system identification
- coupled ship dynamics

### Cite this

*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.

}

*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.

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