Phase-resolved wave prediction with varying buoy positions in the field using machine learning-based methods
Surface wave predictions for several wave periods in advance are crucial for optimizing a wide range of offshore applications. This work focuses on the potential application in active control of wave energy converters (WECs), which can dramatically enhance the efficiency of power generation. Field t...
Published in: | Ocean Engineering |
---|---|
Main Authors: | , , , , , |
Format: | Text |
Language: | unknown |
Published: |
Research Online
2024
|
Subjects: | |
Online Access: | https://ro.uow.edu.au/test2021/11621 https://doi.org/10.1016/j.oceaneng.2024.118107 |
id |
ftunivwollongong:oai:ro.uow.edu.au:test2021-17168 |
---|---|
record_format |
openpolar |
spelling |
ftunivwollongong:oai:ro.uow.edu.au:test2021-17168 2024-09-09T20:10:04+00:00 Phase-resolved wave prediction with varying buoy positions in the field using machine learning-based methods Chen, Jialun Hlophe, Thobani Gunawan, David Taylor, Paul H. Milne, Ian A. Zhao, Wenhua 2024-09-01T07:00:00Z https://ro.uow.edu.au/test2021/11621 https://doi.org/10.1016/j.oceaneng.2024.118107 unknown Research Online https://ro.uow.edu.au/test2021/11621 doi:10.1016/j.oceaneng.2024.118107 https://doi.org/10.1016/j.oceaneng.2024.118107 Scopus Harvesting Series Artificial intelligence Directional spreading Machine learning Wave buoys Wave prediction text 2024 ftunivwollongong https://doi.org/10.1016/j.oceaneng.2024.118107 2024-06-18T23:54:46Z Surface wave predictions for several wave periods in advance are crucial for optimizing a wide range of offshore applications. This work focuses on the potential application in active control of wave energy converters (WECs), which can dramatically enhance the efficiency of power generation. Field tests were conducted in the Southern Ocean of Albany, Western Australia. We compared two prediction models: a physics-based algebraic model and a machine learning-based Artificial Neural Network (ANN) model. Although the standard ANN model is found to achieve better prediction accuracy than the algebraic model for highly directional spreading waves, the prediction performance of the model is greatly reduced due to varying buoy positions, leading to phase offset in predictions. To overcome this limitation, phase correction and partition methods have been incorporated with physical insights into a purely data-driven ANN model. The modified ANN model significantly reduced the prediction error in peaks and troughs compared to the standard ANN model. This study demonstrates that both physics-based and machine learning-based models can work in parallel to provide more accurate predictions, thereby enhancing the practical value of wave prediction for WECs. Text Southern Ocean University of Wollongong, Australia: Research Online Southern Ocean Ocean Engineering 307 118107 |
institution |
Open Polar |
collection |
University of Wollongong, Australia: Research Online |
op_collection_id |
ftunivwollongong |
language |
unknown |
topic |
Artificial intelligence Directional spreading Machine learning Wave buoys Wave prediction |
spellingShingle |
Artificial intelligence Directional spreading Machine learning Wave buoys Wave prediction Chen, Jialun Hlophe, Thobani Gunawan, David Taylor, Paul H. Milne, Ian A. Zhao, Wenhua Phase-resolved wave prediction with varying buoy positions in the field using machine learning-based methods |
topic_facet |
Artificial intelligence Directional spreading Machine learning Wave buoys Wave prediction |
description |
Surface wave predictions for several wave periods in advance are crucial for optimizing a wide range of offshore applications. This work focuses on the potential application in active control of wave energy converters (WECs), which can dramatically enhance the efficiency of power generation. Field tests were conducted in the Southern Ocean of Albany, Western Australia. We compared two prediction models: a physics-based algebraic model and a machine learning-based Artificial Neural Network (ANN) model. Although the standard ANN model is found to achieve better prediction accuracy than the algebraic model for highly directional spreading waves, the prediction performance of the model is greatly reduced due to varying buoy positions, leading to phase offset in predictions. To overcome this limitation, phase correction and partition methods have been incorporated with physical insights into a purely data-driven ANN model. The modified ANN model significantly reduced the prediction error in peaks and troughs compared to the standard ANN model. This study demonstrates that both physics-based and machine learning-based models can work in parallel to provide more accurate predictions, thereby enhancing the practical value of wave prediction for WECs. |
format |
Text |
author |
Chen, Jialun Hlophe, Thobani Gunawan, David Taylor, Paul H. Milne, Ian A. Zhao, Wenhua |
author_facet |
Chen, Jialun Hlophe, Thobani Gunawan, David Taylor, Paul H. Milne, Ian A. Zhao, Wenhua |
author_sort |
Chen, Jialun |
title |
Phase-resolved wave prediction with varying buoy positions in the field using machine learning-based methods |
title_short |
Phase-resolved wave prediction with varying buoy positions in the field using machine learning-based methods |
title_full |
Phase-resolved wave prediction with varying buoy positions in the field using machine learning-based methods |
title_fullStr |
Phase-resolved wave prediction with varying buoy positions in the field using machine learning-based methods |
title_full_unstemmed |
Phase-resolved wave prediction with varying buoy positions in the field using machine learning-based methods |
title_sort |
phase-resolved wave prediction with varying buoy positions in the field using machine learning-based methods |
publisher |
Research Online |
publishDate |
2024 |
url |
https://ro.uow.edu.au/test2021/11621 https://doi.org/10.1016/j.oceaneng.2024.118107 |
geographic |
Southern Ocean |
geographic_facet |
Southern Ocean |
genre |
Southern Ocean |
genre_facet |
Southern Ocean |
op_source |
Scopus Harvesting Series |
op_relation |
https://ro.uow.edu.au/test2021/11621 doi:10.1016/j.oceaneng.2024.118107 https://doi.org/10.1016/j.oceaneng.2024.118107 |
op_doi |
https://doi.org/10.1016/j.oceaneng.2024.118107 |
container_title |
Ocean Engineering |
container_volume |
307 |
container_start_page |
118107 |
_version_ |
1809944410349109248 |