A Machine-Learning Approach to Predict Main Energy Consumption under Realistic Operational Conditions

Publication: ResearchJournal article – Annual report year: 2012

Standard

A Machine-Learning Approach to Predict Main Energy Consumption under Realistic Operational Conditions. / Petersen, Joan P; Winther, Ole; Jacobsen, Daniel J.

In: Ship Technology Research, Vol. 59, No. 1, 2012, p. 64-72.

Publication: ResearchJournal article – Annual report year: 2012

Harvard

APA

CBE

MLA

Vancouver

Author

Petersen, Joan P; Winther, Ole; Jacobsen, Daniel J / A Machine-Learning Approach to Predict Main Energy Consumption under Realistic Operational Conditions.

In: Ship Technology Research, Vol. 59, No. 1, 2012, p. 64-72.

Publication: ResearchJournal article – Annual report year: 2012

Bibtex

@article{619313923ee843af9c3569ebc984ecfb,
title = "A Machine-Learning Approach to Predict Main Energy Consumption under Realistic Operational Conditions",
keywords = "Neural net, Power prognosis, Trim",
author = "Petersen, {Joan P} and Ole Winther and Jacobsen, {Daniel J}",
year = "2012",
volume = "59",
number = "1",
pages = "64--72",
journal = "Ship Technology Research",
issn = "0937-7255",

}

RIS

TY - JOUR

T1 - A Machine-Learning Approach to Predict Main Energy Consumption under Realistic Operational Conditions

A1 - Petersen,Joan P

A1 - Winther,Ole

A1 - Jacobsen,Daniel J

AU - Petersen,Joan P

AU - Winther,Ole

AU - Jacobsen,Daniel J

PY - 2012

Y1 - 2012

N2 - The paper presents a novel and publicly available set of high-quality sensory data collected from a ferry over a period of two months and overviews exixting machine-learning methods for the prediction of main propulsion efficiency. Neural networks are applied on both real-time and predictive settings. Performance results for the real-time models are shown. The presented models were successfully developed in a trim optimisation application onboard a product tanker.

AB - The paper presents a novel and publicly available set of high-quality sensory data collected from a ferry over a period of two months and overviews exixting machine-learning methods for the prediction of main propulsion efficiency. Neural networks are applied on both real-time and predictive settings. Performance results for the real-time models are shown. The presented models were successfully developed in a trim optimisation application onboard a product tanker.

KW - Neural net

KW - Power prognosis

KW - Trim

JO - Ship Technology Research

JF - Ship Technology Research

SN - 0937-7255

IS - 1

VL - 59

SP - 64

EP - 72

ER -