Physics-informed machine learning models for ship speed prediction
This paper proposes a novel physics-informed machine learning method to build grey-box model (GBM) predicting ship speed for ocean crossing ships. In this method, the expected ship speed in calm water is first modeled by the physics-informed neural networks (PINNs) based on speed-power model tests....
Published in: | Expert Systems with Applications |
---|---|
Main Authors: | , , |
Language: | unknown |
Published: |
1481
|
Subjects: | |
Online Access: | https://doi.org/10.1016/j.eswa.2023.121877 https://research.chalmers.se/en/publication/537824 |
id |
ftchalmersuniv:oai:research.chalmers.se:537824 |
---|---|
record_format |
openpolar |
spelling |
ftchalmersuniv:oai:research.chalmers.se:537824 2023-11-12T04:22:20+01:00 Physics-informed machine learning models for ship speed prediction Lang, Xiao Wu, Da Mao, Wengang 2024 text https://doi.org/10.1016/j.eswa.2023.121877 https://research.chalmers.se/en/publication/537824 unknown http://dx.doi.org/10.1016/j.eswa.2023.121877 https://research.chalmers.se/en/publication/537824 Transport Systems and Logistics Astronomy Astrophysics and Cosmology Marine Engineering Computer Science Ship speed over ground Physics-informed neural networks Machine learning XGBoost Full-scale measurements ETA Grey-box model 1481 ftchalmersuniv https://doi.org/10.1016/j.eswa.2023.121877 2023-10-18T22:36:37Z This paper proposes a novel physics-informed machine learning method to build grey-box model (GBM) predicting ship speed for ocean crossing ships. In this method, the expected ship speed in calm water is first modeled by the physics-informed neural networks (PINNs) based on speed-power model tests. Then the eXtreme Gradient Boosting (XGBoost) machine learning algorithm is integrated to estimate ship speed reduction under actual weather conditions. The proposed GBM has been compared against the traditional black-box model (BBM) using performance monitoring data from two ships. The results show that when the amount of data is sufficient for modeling, the GBM can increase the accuracy of speed prediction by about 30%. When data volume is limited, the GBM can also significantly improve the prediction results. Finally, the GBM is validated by checking its implementation for the ETA predictions of cross-Pacific or North Atlantic voyages. The highest cumulative error of sailing time estimated by the GBM is 5 h among all the study cases. Other/Unknown Material North Atlantic Chalmers University of Technology: Chalmers research Eta ENVELOPE(-62.917,-62.917,-64.300,-64.300) Pacific Expert Systems with Applications 238 121877 |
institution |
Open Polar |
collection |
Chalmers University of Technology: Chalmers research |
op_collection_id |
ftchalmersuniv |
language |
unknown |
topic |
Transport Systems and Logistics Astronomy Astrophysics and Cosmology Marine Engineering Computer Science Ship speed over ground Physics-informed neural networks Machine learning XGBoost Full-scale measurements ETA Grey-box model |
spellingShingle |
Transport Systems and Logistics Astronomy Astrophysics and Cosmology Marine Engineering Computer Science Ship speed over ground Physics-informed neural networks Machine learning XGBoost Full-scale measurements ETA Grey-box model Lang, Xiao Wu, Da Mao, Wengang Physics-informed machine learning models for ship speed prediction |
topic_facet |
Transport Systems and Logistics Astronomy Astrophysics and Cosmology Marine Engineering Computer Science Ship speed over ground Physics-informed neural networks Machine learning XGBoost Full-scale measurements ETA Grey-box model |
description |
This paper proposes a novel physics-informed machine learning method to build grey-box model (GBM) predicting ship speed for ocean crossing ships. In this method, the expected ship speed in calm water is first modeled by the physics-informed neural networks (PINNs) based on speed-power model tests. Then the eXtreme Gradient Boosting (XGBoost) machine learning algorithm is integrated to estimate ship speed reduction under actual weather conditions. The proposed GBM has been compared against the traditional black-box model (BBM) using performance monitoring data from two ships. The results show that when the amount of data is sufficient for modeling, the GBM can increase the accuracy of speed prediction by about 30%. When data volume is limited, the GBM can also significantly improve the prediction results. Finally, the GBM is validated by checking its implementation for the ETA predictions of cross-Pacific or North Atlantic voyages. The highest cumulative error of sailing time estimated by the GBM is 5 h among all the study cases. |
author |
Lang, Xiao Wu, Da Mao, Wengang |
author_facet |
Lang, Xiao Wu, Da Mao, Wengang |
author_sort |
Lang, Xiao |
title |
Physics-informed machine learning models for ship speed prediction |
title_short |
Physics-informed machine learning models for ship speed prediction |
title_full |
Physics-informed machine learning models for ship speed prediction |
title_fullStr |
Physics-informed machine learning models for ship speed prediction |
title_full_unstemmed |
Physics-informed machine learning models for ship speed prediction |
title_sort |
physics-informed machine learning models for ship speed prediction |
publishDate |
1481 |
url |
https://doi.org/10.1016/j.eswa.2023.121877 https://research.chalmers.se/en/publication/537824 |
long_lat |
ENVELOPE(-62.917,-62.917,-64.300,-64.300) |
geographic |
Eta Pacific |
geographic_facet |
Eta Pacific |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_relation |
http://dx.doi.org/10.1016/j.eswa.2023.121877 https://research.chalmers.se/en/publication/537824 |
op_doi |
https://doi.org/10.1016/j.eswa.2023.121877 |
container_title |
Expert Systems with Applications |
container_volume |
238 |
container_start_page |
121877 |
_version_ |
1782337405255155712 |