2026-09-21T03:32:53Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1446722022-08-30T03:43:06Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Sapsis, Themistoklis
Kriezis, Anthony
Massachusetts Institute of Technology. Department of Mechanical Engineering
2022-08-29T16:03:45Z
2022-08-29T16:03:45Z
2022-05
2022-06-23T14:10:10.933Z
https://hdl.handle.net/1721.1/144672
0000-0003-3637-4285
One of the biggest challenges facing the shipping industry in the coming decades is the reduction of carbon emissions. A promising approach to this end is the use of the growing amount of data collected by vessels to optimize a voyage so as to minimize power consumption. The focus of this paper is on building and testing machine learning models that can accurately predict the shaft power of a vessel under different conditions. The models examined include pure theoretical models, pure neural network models, and combinations of the two. Using data on two car carrying vessels for 8 years it was found that neural networks incorporating some physical intuition can achieve a mean absolute percentage error of less than 5%, and an R-squared above 95%. This performance can be further improved by the addition of wave information, but it deteriorates when the data collection becomes less frequent.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
Ship Power Prediction Using Machine Learning
Thesis
application/pdf
Master
Master of Science in Naval Architecture and Marine Engineering
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="5cd08168-1b74-467d-ada0-aba17138d309">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Ship Power Prediction Using Machine Learning</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Kriezis, Anthony</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>One of the biggest challenges facing the shipping industry in the coming decades is the reduction of carbon emissions. A promising approach to this end is the use of the growing amount of data collected by vessels to optimize a voyage so as to minimize power consumption. The focus of this paper is on building and testing machine learning models that can accurately predict the shaft power of a vessel under different conditions. The models examined include pure theoretical models, pure neural network models, and combinations of the two. Using data on two car carrying vessels for 8 years it was found that neural networks incorporating some physical intuition can achieve a mean absolute percentage error of less than 5%, and an R-squared above 95%. This performance can be further improved by the addition of wave information, but it deteriorates when the data collection becomes less frequent.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>