A Predictive Analytics Method for the Avoidance of Ship Grounding in Real Operational Conditions

Ghalib Taimuri; Mingyang Zhang; Spyros Hirdaris

doi:10.5957/SMC-2022-012

A Predictive Analytics Method for the Avoidance of Ship Grounding in Real Operational Conditions

Ghalib Taimuri
, Mingyang Zhang
, Spyros Hirdaris

Department of Energy and Mechanical Engineering

Research output: Contribution to conference › Paper › Scientific › peer-review

4 Citations (Scopus)

Abstract

This paper presents a rapid method for the evaluation of ship grounding risk and the estimation of avoidance action in real operational conditions. The approach makes use of big data analytics from Automatic Identification System (AIS), nowcast and General Bathymetric Chart of the Oceans (GEBCO) to generate potential grounding scenarios. Following the identification of potential grounding scenarios, a Fluid Structure Interaction (FSI) model is adopted to simulate grounding avoidance actions that account for the influence of surrounding water and ship controlling devices in 6- DoF. Application for the case of a passenger ship operating under ice free conditions in the Gulf of Finland demonstrates the potential of the method for the development of improved decision support systems and operational practices.

Original language	English
DOIs	https://doi.org/10.5957/SMC-2022-012
Publication status	Published - 21 Sept 2022
MoE publication type	Not Eligible
Event	SNAME Maritime Convention - Houston, United States Duration: 26 Sept 2022 → 29 Sept 2022 https://web.cvent.com/event/742733d5-d310-4259-8003-0d1caacee4f8/summary

Conference

Conference	SNAME Maritime Convention
Abbreviated title	SMC
Country/Territory	United States
City	Houston
Period	26/09/2022 → 29/09/2022
Internet address	https://web.cvent.com/event/742733d5-d310-4259-8003-0d1caacee4f8/summary

Funding

All authors acknowledge funding received from the EU Horizon 2020 project on FLooding Accident REsponse (FLARE – Contract No. 814753) & Merenkulun Säätiö, Finland (https://www.merenkulunsaatio.fi/etusivu/).

UN SDGs

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

SDG 14 Life Below Water

Keywords

6-DoF maneuvering model
big data analytics
grounding risk
Gulf of Finland
machine learning
ship safety
simplified FSI

Access to Document

10.5957/SMC-2022-012

Cite this

@conference{4ae0c6903dac4002b48c5d928f3a6ac3,

title = "A Predictive Analytics Method for the Avoidance of Ship Grounding in Real Operational Conditions",

abstract = "This paper presents a rapid method for the evaluation of ship grounding risk and the estimation of avoidance action in real operational conditions. The approach makes use of big data analytics from Automatic Identification System (AIS), nowcast and General Bathymetric Chart of the Oceans (GEBCO) to generate potential grounding scenarios. Following the identification of potential grounding scenarios, a Fluid Structure Interaction (FSI) model is adopted to simulate grounding avoidance actions that account for the influence of surrounding water and ship controlling devices in 6- DoF. Application for the case of a passenger ship operating under ice free conditions in the Gulf of Finland demonstrates the potential of the method for the development of improved decision support systems and operational practices.",

keywords = "6-DoF maneuvering model, big data analytics, grounding risk, Gulf of Finland, machine learning, ship safety, simplified FSI",

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

note = "Funding Information: All authors acknowledge funding received from the EU Horizon 2020 project on FLooding Accident REsponse (FLARE – Contract No. 814753) \& Merenkulun S{\"a}{\"a}ti{\"o}, Finland (https://www.merenkulunsaatio.fi/etusivu/). Publisher Copyright: Copyright {\textcopyright} 2022 Society of Naval Architects and Marine Engineers (SNAME); SNAME Maritime Convention, SMC ; Conference date: 26-09-2022 Through 29-09-2022",

year = "2022",

month = sep,

day = "21",

doi = "10.5957/SMC-2022-012",

language = "English",

url = "https://web.cvent.com/event/742733d5-d310-4259-8003-0d1caacee4f8/summary",

}

TY - CONF

T1 - A Predictive Analytics Method for the Avoidance of Ship Grounding in Real Operational Conditions

AU - Taimuri, Ghalib

AU - Zhang, Mingyang

AU - Hirdaris, Spyros

N1 - Funding Information: All authors acknowledge funding received from the EU Horizon 2020 project on FLooding Accident REsponse (FLARE – Contract No. 814753) & Merenkulun Säätiö, Finland (https://www.merenkulunsaatio.fi/etusivu/). Publisher Copyright: Copyright © 2022 Society of Naval Architects and Marine Engineers (SNAME)

PY - 2022/9/21

Y1 - 2022/9/21

N2 - This paper presents a rapid method for the evaluation of ship grounding risk and the estimation of avoidance action in real operational conditions. The approach makes use of big data analytics from Automatic Identification System (AIS), nowcast and General Bathymetric Chart of the Oceans (GEBCO) to generate potential grounding scenarios. Following the identification of potential grounding scenarios, a Fluid Structure Interaction (FSI) model is adopted to simulate grounding avoidance actions that account for the influence of surrounding water and ship controlling devices in 6- DoF. Application for the case of a passenger ship operating under ice free conditions in the Gulf of Finland demonstrates the potential of the method for the development of improved decision support systems and operational practices.

AB - This paper presents a rapid method for the evaluation of ship grounding risk and the estimation of avoidance action in real operational conditions. The approach makes use of big data analytics from Automatic Identification System (AIS), nowcast and General Bathymetric Chart of the Oceans (GEBCO) to generate potential grounding scenarios. Following the identification of potential grounding scenarios, a Fluid Structure Interaction (FSI) model is adopted to simulate grounding avoidance actions that account for the influence of surrounding water and ship controlling devices in 6- DoF. Application for the case of a passenger ship operating under ice free conditions in the Gulf of Finland demonstrates the potential of the method for the development of improved decision support systems and operational practices.

KW - 6-DoF maneuvering model

KW - big data analytics

KW - grounding risk

KW - Gulf of Finland

KW - machine learning

KW - ship safety

KW - simplified FSI

UR - https://www.scopus.com/pages/publications/85133540519

U2 - 10.5957/SMC-2022-012

DO - 10.5957/SMC-2022-012

M3 - Paper

AN - SCOPUS:85133540519

T2 - SNAME Maritime Convention

Y2 - 26 September 2022 through 29 September 2022

ER -

A Predictive Analytics Method for the Avoidance of Ship Grounding in Real Operational Conditions

Abstract

Conference

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

FLARE: FLooding Accident REsponse

Cite this

A Predictive Analytics Method for the Avoidance of Ship Grounding in Real Operational Conditions

Abstract

Conference

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Projects

FLARE: FLooding Accident REsponse

Cite this