A new-generation motion-control system for twin-hull vessels using a neural optimal controller

F. Kenevissi, M. Atlar, E. Mesbahi

Research output: Contribution to journalArticle

Abstract

A new ride control system using a neural optimal controller (NOC) is developed and applied to improve the heave and pitch motion responses of two twin-hull vessels operating in regular head seas. A time domain model for the vessel dynamics in the presence of active fin control is used to simulate the vessel and fin motion responses. An on-line switching procedure is introduced to select among a number of linear quadratic regulator optimal controllers, designed for different operating conditions of the vessel, to improve the system robustness. Although the on-line switching offered better robustness and performance characteristics, in between switching operating points, it still remained suboptimal. Therefore, an artificial neural network (ANN) controller was developed as an alternative and initially trained to emulate the same level of control at a number of design operating points, as a NOC. The advantage of this novel application is that practical difficulties in applying an on-line switching procedure are no longer present and, more importantly, the ANN has been capable of nonlinear generalization to give a near optimal solution away from the trained operating conditions.
Original languageEnglish
Pages (from-to)168-180
JournalMarine Technology/SNAME News
Volume40
Issue number3
Publication statusPublished - Jul 2003

Cite this

@article{e69d1d73b8e14601b7d56b34ed60983d,
title = "A new-generation motion-control system for twin-hull vessels using a neural optimal controller",
abstract = "A new ride control system using a neural optimal controller (NOC) is developed and applied to improve the heave and pitch motion responses of two twin-hull vessels operating in regular head seas. A time domain model for the vessel dynamics in the presence of active fin control is used to simulate the vessel and fin motion responses. An on-line switching procedure is introduced to select among a number of linear quadratic regulator optimal controllers, designed for different operating conditions of the vessel, to improve the system robustness. Although the on-line switching offered better robustness and performance characteristics, in between switching operating points, it still remained suboptimal. Therefore, an artificial neural network (ANN) controller was developed as an alternative and initially trained to emulate the same level of control at a number of design operating points, as a NOC. The advantage of this novel application is that practical difficulties in applying an on-line switching procedure are no longer present and, more importantly, the ANN has been capable of nonlinear generalization to give a near optimal solution away from the trained operating conditions.",
author = "F. Kenevissi and M. Atlar and E. Mesbahi",
year = "2003",
month = "7",
language = "English",
volume = "40",
pages = "168--180",
journal = "Marine Technology/SNAME News",
issn = "0025-3316",
publisher = "Society of Naval Architects and Marine Engineers",
number = "3",

}

A new-generation motion-control system for twin-hull vessels using a neural optimal controller. / Kenevissi, F.; Atlar, M.; Mesbahi, E.

In: Marine Technology/SNAME News, Vol. 40, No. 3, 07.2003, p. 168-180.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A new-generation motion-control system for twin-hull vessels using a neural optimal controller

AU - Kenevissi, F.

AU - Atlar, M.

AU - Mesbahi, E.

PY - 2003/7

Y1 - 2003/7

N2 - A new ride control system using a neural optimal controller (NOC) is developed and applied to improve the heave and pitch motion responses of two twin-hull vessels operating in regular head seas. A time domain model for the vessel dynamics in the presence of active fin control is used to simulate the vessel and fin motion responses. An on-line switching procedure is introduced to select among a number of linear quadratic regulator optimal controllers, designed for different operating conditions of the vessel, to improve the system robustness. Although the on-line switching offered better robustness and performance characteristics, in between switching operating points, it still remained suboptimal. Therefore, an artificial neural network (ANN) controller was developed as an alternative and initially trained to emulate the same level of control at a number of design operating points, as a NOC. The advantage of this novel application is that practical difficulties in applying an on-line switching procedure are no longer present and, more importantly, the ANN has been capable of nonlinear generalization to give a near optimal solution away from the trained operating conditions.

AB - A new ride control system using a neural optimal controller (NOC) is developed and applied to improve the heave and pitch motion responses of two twin-hull vessels operating in regular head seas. A time domain model for the vessel dynamics in the presence of active fin control is used to simulate the vessel and fin motion responses. An on-line switching procedure is introduced to select among a number of linear quadratic regulator optimal controllers, designed for different operating conditions of the vessel, to improve the system robustness. Although the on-line switching offered better robustness and performance characteristics, in between switching operating points, it still remained suboptimal. Therefore, an artificial neural network (ANN) controller was developed as an alternative and initially trained to emulate the same level of control at a number of design operating points, as a NOC. The advantage of this novel application is that practical difficulties in applying an on-line switching procedure are no longer present and, more importantly, the ANN has been capable of nonlinear generalization to give a near optimal solution away from the trained operating conditions.

M3 - Article

VL - 40

SP - 168

EP - 180

JO - Marine Technology/SNAME News

JF - Marine Technology/SNAME News

SN - 0025-3316

IS - 3

ER -