A ship digital twin for safe and sustainable ship operations

Mingyang Zhang; Spyros Hirdaris; Nikolaos Tsoulakos

A ship digital twin for safe and sustainable ship operations

Mingyang Zhang, Spyros Hirdaris, Nikolaos Tsoulakos

LASKARIDIS SHIPPING COMPANY LTD.

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Abstract › Scientific › vertaisarvioitu

70 Lataukset (Pure)

Abstrakti

This paper presents a novel digital twin that can predict ship motions and fuel consumption in real operational conditions. The analysis is based on two optimal Deep Learning Models (DLM) namely (a) a transformer neural network used for the analysis of ship motions and (b) a Long Short-Term Memory (LSTM) network for the
prediction of ship fuel consumption. Comparisons of results against sea trial data suggest that subject to further testing and validation DLM could be used as part of a digital twin framework for safe and sustainable ship operations.

Alkuperäiskieli	Englanti
Sivut	71 - 74
Sivumäärä	5
Tila	Julkaistu - 20 lokak. 2023
OKM-julkaisutyyppi	Ei sovellu
Tapahtuma	BUILding a DIgital Twin: requirements, methods, and applications - CNR Headquarters, Piazzale Aldo Moro, 7, 00185 , Rome, Italia Kesto: 19 lokak. 2023 → 20 lokak. 2023 http://inm.cnr.it/buildit2023/

Workshop

Workshop	BUILding a DIgital Twin
Lyhennettä	BUILD IT
Maa/Alue	Italia
Kaupunki	Rome
Ajanjakso	19/10/2023 → 20/10/2023
www-osoite	http://inm.cnr.it/buildit2023/

YK:n kestävän kehityksen tavoitteet

Tämä tuotos edistää seuraavia kestävän kehityksen tavoitteita:

Pääsy asiakirjaan

23_zhangFinal published version, 295 KB

Muut tiedostot ja linkit

Link to the book of abstracts page

RETROFIT55: Retrofit solutions to achieve 55% ghg reduction by 2030
Remes, H. (Vastuullinen tutkija)
01/01/2023 → 31/12/2025
Projekti: EU: Framework programmes funding

Siteeraa tätä

@conference{91a4109f96104ce1b536217ba70160e0,

title = "A ship digital twin for safe and sustainable ship operations",

abstract = "This paper presents a novel digital twin that can predict ship motions and fuel consumption in real operational conditions. The analysis is based on two optimal Deep Learning Models (DLM) namely (a) a transformer neural network used for the analysis of ship motions and (b) a Long Short-Term Memory (LSTM) network for theprediction of ship fuel consumption. Comparisons of results against sea trial data suggest that subject to further testing and validation DLM could be used as part of a digital twin framework for safe and sustainable ship operations.",

keywords = "digital twins, ship motions, ship fuel consumption, big data science, deep learning",

author = "Mingyang Zhang and Spyros Hirdaris and Nikolaos Tsoulakos",

year = "2023",

month = oct,

day = "20",

language = "English",

pages = "71 -- 74",

note = "BUILding a DIgital Twin : requirements, methods, and applications, BUILD IT ; Conference date: 19-10-2023 Through 20-10-2023",

url = "http://inm.cnr.it/buildit2023/",

}

TY - CONF

T1 - A ship digital twin for safe and sustainable ship operations

AU - Zhang, Mingyang

AU - Hirdaris, Spyros

AU - Tsoulakos, Nikolaos

PY - 2023/10/20

Y1 - 2023/10/20

N2 - This paper presents a novel digital twin that can predict ship motions and fuel consumption in real operational conditions. The analysis is based on two optimal Deep Learning Models (DLM) namely (a) a transformer neural network used for the analysis of ship motions and (b) a Long Short-Term Memory (LSTM) network for theprediction of ship fuel consumption. Comparisons of results against sea trial data suggest that subject to further testing and validation DLM could be used as part of a digital twin framework for safe and sustainable ship operations.

AB - This paper presents a novel digital twin that can predict ship motions and fuel consumption in real operational conditions. The analysis is based on two optimal Deep Learning Models (DLM) namely (a) a transformer neural network used for the analysis of ship motions and (b) a Long Short-Term Memory (LSTM) network for theprediction of ship fuel consumption. Comparisons of results against sea trial data suggest that subject to further testing and validation DLM could be used as part of a digital twin framework for safe and sustainable ship operations.

KW - digital twins

KW - ship motions

KW - ship fuel consumption

KW - big data science

KW - deep learning

UR - http://inm.cnr.it/buildit2023/

M3 - Abstract

SP - 71

EP - 74

T2 - BUILding a DIgital Twin

Y2 - 19 October 2023 through 20 October 2023

ER -

A ship digital twin for safe and sustainable ship operations

Abstrakti

Workshop

YK:n kestävän kehityksen tavoitteet

Pääsy asiakirjaan

Muut tiedostot ja linkit

Sormenjälki

Projektit

RETROFIT55: Retrofit solutions to achieve 55% ghg reduction by 2030

Siteeraa tätä