Prediction of Full-Scale Propulsion Power using Artificial Neural Networks

Benjamin Pjedsted Pedersen; Jan Larsen

Prediction of Full-Scale Propulsion Power using Artificial Neural Networks

Benjamin Pjedsted Pedersen, Jan Larsen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Full scale measurements of the propulsion power, ship speed, wind speed and direction, sea and air temperature from four different loading conditions, together with hind cast data of wind and sea properties; and noon report data has been used to train an Artificial Neural Network for prediction of propulsion power. The model was optimized using a double cross validation procedure. The network was able to predict the propulsion power with accuracy between 0.8-1.7% using onboard measurement system data and 7% from manually acquired noon reports.

Original language	English
Title of host publication	COMPIT '09 : 8th International Conference on Computer and IT Applications in the Maritime Industries
Place of Publication	Budapest, 10-12 May 2009
Publication date	2009
Pages	537-550
Publication status	Published - 2009
Event	Prediction of Full-Scale Propulsion Power using Artificial Neural Networks - Budapest Duration: 1 Jan 2009 → …

Conference

Conference	Prediction of Full-Scale Propulsion Power using Artificial Neural Networks
City	Budapest
Period	01/01/2009 → …

Keywords

propulsion
vessel
fuel consumption
ship
performance
Artificial neural networks

Access to Document

http://www.compit.info

OpenUrl availability

Full text

Cite this

@inproceedings{cbae6932559c4e8188f2127f601eac42,

title = "Prediction of Full-Scale Propulsion Power using Artificial Neural Networks",

abstract = "Full scale measurements of the propulsion power, ship speed, wind speed and direction, sea and air temperature from four different loading conditions, together with hind cast data of wind and sea properties; and noon report data has been used to train an Artificial Neural Network for prediction of propulsion power. The model was optimized using a double cross validation procedure. The network was able to predict the propulsion power with accuracy between 0.8-1.7% using onboard measurement system data and 7% from manually acquired noon reports.",

keywords = "propulsion, vessel, fuel consumption, ship, performance, Artificial neural networks",

author = "Pedersen, {Benjamin Pjedsted} and Jan Larsen",

year = "2009",

language = "English",

pages = "537--550",

booktitle = "COMPIT '09",

note = "Prediction of Full-Scale Propulsion Power using Artificial Neural Networks ; Conference date: 01-01-2009",

}

Pedersen, BP & Larsen, J 2009, Prediction of Full-Scale Propulsion Power using Artificial Neural Networks. in COMPIT '09: 8th International Conference on Computer and IT Applications in the Maritime Industries. Budapest, 10-12 May 2009, pp. 537-550, Prediction of Full-Scale Propulsion Power using Artificial Neural Networks, Budapest, 01/01/2009. <http://www.compit.info>

Prediction of Full-Scale Propulsion Power using Artificial Neural Networks. / Pedersen, Benjamin Pjedsted; Larsen, Jan.
COMPIT '09: 8th International Conference on Computer and IT Applications in the Maritime Industries. Budapest, 10-12 May 2009, 2009. p. 537-550.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Prediction of Full-Scale Propulsion Power using Artificial Neural Networks

AU - Pedersen, Benjamin Pjedsted

AU - Larsen, Jan

PY - 2009

Y1 - 2009

N2 - Full scale measurements of the propulsion power, ship speed, wind speed and direction, sea and air temperature from four different loading conditions, together with hind cast data of wind and sea properties; and noon report data has been used to train an Artificial Neural Network for prediction of propulsion power. The model was optimized using a double cross validation procedure. The network was able to predict the propulsion power with accuracy between 0.8-1.7% using onboard measurement system data and 7% from manually acquired noon reports.

AB - Full scale measurements of the propulsion power, ship speed, wind speed and direction, sea and air temperature from four different loading conditions, together with hind cast data of wind and sea properties; and noon report data has been used to train an Artificial Neural Network for prediction of propulsion power. The model was optimized using a double cross validation procedure. The network was able to predict the propulsion power with accuracy between 0.8-1.7% using onboard measurement system data and 7% from manually acquired noon reports.

KW - propulsion

KW - vessel

KW - fuel consumption

KW - ship

KW - performance

KW - Artificial neural networks

M3 - Article in proceedings

SP - 537

EP - 550

BT - COMPIT '09

CY - Budapest, 10-12 May 2009

T2 - Prediction of Full-Scale Propulsion Power using Artificial Neural Networks

Y2 - 1 January 2009

ER -

Prediction of Full-Scale Propulsion Power using Artificial Neural Networks

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this