A deep learning method for the prediction of 6-DoF ship motions in real conditions

Mingyang Zhang; Ghalib Taimuri; Jinfen Zhang; Spyros Hirdaris

doi:10.1177/14750902231157852

A deep learning method for the prediction of 6-DoF ship motions in real conditions

Mingyang Zhang, Ghalib Taimuri, Jinfen Zhang, Spyros Hirdaris

Wuhan University of Technology

Research output: Contribution to journal › Article › Scientific › peer-review

42 Citations (Scopus)

364 Downloads (Pure)

Abstract

This paper presents a deep learning method for the prediction of ship motions in 6 Degrees of Freedom (DoF). Big data streams of Automatic Identification System (AIS), now-cast, and bathymetry records are used to extract motion trajectories and idealise environmental conditions. A rapid Fluid-Structure Interaction (FSI) model is used to generate ship motions that account for the influence of surrounding water and ship-controlling devices. A transformer neural network that accounts for the influence of operational conditions on ship dynamics is validated by learning the data streams corresponding to ship voyages and hydro-meteorological conditions between two ports in the Gulf of Finland. Predictions for a ship turning circle and motion dynamics between these two ports show that the proposed method can capture the influence of operational conditions on seakeeping and manoeuvring.

Original language	English
Pages (from-to)	887-905
Number of pages	19
Journal	Proceedings of the Institution of Mechanical Engineers. Part M: Journal of Engineering for the Maritime Environment
Volume	237
Issue number	4
Early online date	11 Mar 2023
DOIs	https://doi.org/10.1177/14750902231157852
Publication status	Published - Nov 2023
MoE publication type	A1 Journal article-refereed

Keywords

Ship motions
Big data
Fluid-Structure Interactions
Deep learning
Gulf of Finland

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1177/14750902231157852Licence: CC BY-NC

zhang-et-al-2023-a-deep-learning-method-for-the-prediction-of-6-dof-ship-motions-in-real-conditionsFinal published version, 12.1 MBLicence: CC BY-NC

Cite this

@article{075c60c353fb494e82b41a89822169fd,

title = "A deep learning method for the prediction of 6-DoF ship motions in real conditions",

abstract = "This paper presents a deep learning method for the prediction of ship motions in 6 Degrees of Freedom (DoF). Big data streams of Automatic Identification System (AIS), now-cast, and bathymetry records are used to extract motion trajectories and idealise environmental conditions. A rapid Fluid-Structure Interaction (FSI) model is used to generate ship motions that account for the influence of surrounding water and ship-controlling devices. A transformer neural network that accounts for the influence of operational conditions on ship dynamics is validated by learning the data streams corresponding to ship voyages and hydro-meteorological conditions between two ports in the Gulf of Finland. Predictions for a ship turning circle and motion dynamics between these two ports show that the proposed method can capture the influence of operational conditions on seakeeping and manoeuvring.",

keywords = "Ship motions, Big data, Fluid-Structure Interactions, Deep learning, Gulf of Finland",

author = "Mingyang Zhang and Ghalib Taimuri and Jinfen Zhang and Spyros Hirdaris",

note = "| openaire: EC/H2020/814753/EU//FLARE",

year = "2023",

month = nov,

doi = "10.1177/14750902231157852",

language = "English",

volume = "237",

pages = "887--905",

journal = "Proceedings of the Institution of Mechanical Engineers. Part M: Journal of Engineering for the Maritime Environment",

issn = "1475-0902",

publisher = "SAGE Publications",

number = "4",

}

A deep learning method for the prediction of 6-DoF ship motions in real conditions. / Zhang, Mingyang; Taimuri, Ghalib; Zhang, Jinfen et al.
In: Proceedings of the Institution of Mechanical Engineers. Part M: Journal of Engineering for the Maritime Environment, Vol. 237, No. 4, 11.2023, p. 887-905.

Research output: Contribution to journal › Article › Scientific › peer-review

TY - JOUR

T1 - A deep learning method for the prediction of 6-DoF ship motions in real conditions

AU - Zhang, Mingyang

AU - Taimuri, Ghalib

AU - Zhang, Jinfen

AU - Hirdaris, Spyros

N1 - | openaire: EC/H2020/814753/EU//FLARE

PY - 2023/11

Y1 - 2023/11

N2 - This paper presents a deep learning method for the prediction of ship motions in 6 Degrees of Freedom (DoF). Big data streams of Automatic Identification System (AIS), now-cast, and bathymetry records are used to extract motion trajectories and idealise environmental conditions. A rapid Fluid-Structure Interaction (FSI) model is used to generate ship motions that account for the influence of surrounding water and ship-controlling devices. A transformer neural network that accounts for the influence of operational conditions on ship dynamics is validated by learning the data streams corresponding to ship voyages and hydro-meteorological conditions between two ports in the Gulf of Finland. Predictions for a ship turning circle and motion dynamics between these two ports show that the proposed method can capture the influence of operational conditions on seakeeping and manoeuvring.

AB - This paper presents a deep learning method for the prediction of ship motions in 6 Degrees of Freedom (DoF). Big data streams of Automatic Identification System (AIS), now-cast, and bathymetry records are used to extract motion trajectories and idealise environmental conditions. A rapid Fluid-Structure Interaction (FSI) model is used to generate ship motions that account for the influence of surrounding water and ship-controlling devices. A transformer neural network that accounts for the influence of operational conditions on ship dynamics is validated by learning the data streams corresponding to ship voyages and hydro-meteorological conditions between two ports in the Gulf of Finland. Predictions for a ship turning circle and motion dynamics between these two ports show that the proposed method can capture the influence of operational conditions on seakeeping and manoeuvring.

KW - Ship motions

KW - Big data

KW - Fluid-Structure Interactions

KW - Deep learning

KW - Gulf of Finland

UR - http://www.scopus.com/inward/record.url?scp=85149943237&partnerID=8YFLogxK

U2 - 10.1177/14750902231157852

DO - 10.1177/14750902231157852

M3 - Article

SN - 1475-0902

VL - 237

SP - 887

EP - 905

JO - Proceedings of the Institution of Mechanical Engineers. Part M: Journal of Engineering for the Maritime Environment

JF - Proceedings of the Institution of Mechanical Engineers. Part M: Journal of Engineering for the Maritime Environment

IS - 4

ER -

A deep learning method for the prediction of 6-DoF ship motions in real conditions

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

FLARE: FLooding Accident REsponse

Cite this

A deep learning method for the prediction of 6-DoF ship motions in real conditions

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Projects

FLARE: FLooding Accident REsponse

Cite this