A Machine Learning Ship's Speed Prediction Model and Sailing Time Control Strategy
Paper i proceeding, 2022

This paper proposes a machine learning based ship speed over ground prediction model, driven by the eXtreme Gradient Boosting (XGBoost) algorithm. The dataset is acquired from a world-sailing chemical tanker with five years of full-scale measurements. The model is trained using encountered metocean environments and ship operation profiles in two scenarios, i.e., through RPM or propulsion power. This model is further combined with the particle swarm optimization (PSO) algorithm to integrate a sailing time control method. It optimizes constant RPM or power operation strategy to meet the requirements of fixed ETA.

particle swarm optimization

speed over ground

ETA

XGBoost

Machine learning

full-scale measurements

Författare

Xiao Lang

Chalmers, Mekanik och maritima vetenskaper, Marin teknik

Da Wu

Chalmers, Mekanik och maritima vetenskaper, Marin teknik

Wengang Mao

Chalmers, Mekanik och maritima vetenskaper, Marin teknik

Proceedings of the International Offshore and Polar Engineering Conference

10986189 (ISSN) 15551792 (eISSN)

3598-3605
978-1-880653-81-4 (ISBN)

The 32nd International Ocean and Polar Engineering Conference
Shanghai, China,

E-Nav - Efficient Electronic Navigation at Sea

VINNOVA (2019-01059), 2019-03-01 -- 2021-08-31.

VINNOVA (2019-01059), 2019-04-11 -- 2021-10-11.

Europeiska kommissionen (EU), 2019-04-11 -- 2021-10-11.

Utforska innovativa lösningar för arktisk sjöfart

STINT (Dnr:CH2016-6673), 2017-05-01 -- 2020-06-30.

EcoSail - Miljövänlig och kunddriven Sailplan optimeringstjänst

Europeiska kommissionen (EU) (EC/H2020/820593), 2018-11-01 -- 2021-04-30.

Hur realiserar man den mest energieffektiva fartygsresan i praktiken?

Trafikverket, 2020-10-01 -- 2022-09-30.

Drivkrafter

Hållbar utveckling

Styrkeområden

Transport

Ämneskategorier

Marin teknik

Sannolikhetsteori och statistik

Signalbehandling

Annan elektroteknik och elektronik

Mer information

Senast uppdaterat

2023-10-25