Detection of plunging breaking waves based on machine learning
Plunging breaking waves that occur in the vicinity of offshore structures can lead to high impulsive slamming loads, which are significant for the structural loading. The occurrence of plunging breaking waves is usually identified based on criteria that are derived from theoretical analyses and expe...
Published in: | Volume 7A: Ocean Engineering |
---|---|
Main Authors: | , , |
Format: | Book Part |
Language: | English |
Published: |
ASME
2018
|
Subjects: | |
Online Access: | http://hdl.handle.net/11250/2580764 https://doi.org/10.1115/OMAE2018-77671 |
id |
ftntnutrondheimi:oai:ntnuopen.ntnu.no:11250/2580764 |
---|---|
record_format |
openpolar |
spelling |
ftntnutrondheimi:oai:ntnuopen.ntnu.no:11250/2580764 2023-05-15T14:23:42+02:00 Detection of plunging breaking waves based on machine learning Tu, Ying Cheng, Zhengshun Muskulus, Michael 2018 http://hdl.handle.net/11250/2580764 https://doi.org/10.1115/OMAE2018-77671 eng eng ASME ASME 2018 37th International Conference on Ocean, Offshore and Arctic Engineering - Volume 7A: Ocean Engineering urn:isbn:978-0-7918-5126-5 http://hdl.handle.net/11250/2580764 https://doi.org/10.1115/OMAE2018-77671 cristin:1647179 Chapter 2018 ftntnutrondheimi https://doi.org/10.1115/OMAE2018-77671 2019-09-17T06:54:45Z Plunging breaking waves that occur in the vicinity of offshore structures can lead to high impulsive slamming loads, which are significant for the structural loading. The occurrence of plunging breaking waves is usually identified based on criteria that are derived from theoretical analyses and experimental studies. Given a large amount of data, detecting plunging breaking waves can be treated as a typical classification problem, which can be solved by a machine learning approach. In this study, logistic regression algorithm is used together with the experimental data from the WaveSlam project to train a classifier for the detection. Three normalized dimensionless features are introduced based on the measured data for the training. A classifier with respect to four wave parameters (i.e. water depth, wave height, crest height and wave period) is then explicitly developed for detecting plunging breaking waves. It is found that the trained classifier has an accuracy of 98.7% and F1 score of 99.2% for the tested data. Among the three dimensionless parameters, the ratio of wave height to water depth, H/d, is the most decisive factor for the detection of plunging breaking waves. publishedVersion Copyright © 2018 by ASME Book Part Arctic NTNU Open Archive (Norwegian University of Science and Technology) Volume 7A: Ocean Engineering |
institution |
Open Polar |
collection |
NTNU Open Archive (Norwegian University of Science and Technology) |
op_collection_id |
ftntnutrondheimi |
language |
English |
description |
Plunging breaking waves that occur in the vicinity of offshore structures can lead to high impulsive slamming loads, which are significant for the structural loading. The occurrence of plunging breaking waves is usually identified based on criteria that are derived from theoretical analyses and experimental studies. Given a large amount of data, detecting plunging breaking waves can be treated as a typical classification problem, which can be solved by a machine learning approach. In this study, logistic regression algorithm is used together with the experimental data from the WaveSlam project to train a classifier for the detection. Three normalized dimensionless features are introduced based on the measured data for the training. A classifier with respect to four wave parameters (i.e. water depth, wave height, crest height and wave period) is then explicitly developed for detecting plunging breaking waves. It is found that the trained classifier has an accuracy of 98.7% and F1 score of 99.2% for the tested data. Among the three dimensionless parameters, the ratio of wave height to water depth, H/d, is the most decisive factor for the detection of plunging breaking waves. publishedVersion Copyright © 2018 by ASME |
format |
Book Part |
author |
Tu, Ying Cheng, Zhengshun Muskulus, Michael |
spellingShingle |
Tu, Ying Cheng, Zhengshun Muskulus, Michael Detection of plunging breaking waves based on machine learning |
author_facet |
Tu, Ying Cheng, Zhengshun Muskulus, Michael |
author_sort |
Tu, Ying |
title |
Detection of plunging breaking waves based on machine learning |
title_short |
Detection of plunging breaking waves based on machine learning |
title_full |
Detection of plunging breaking waves based on machine learning |
title_fullStr |
Detection of plunging breaking waves based on machine learning |
title_full_unstemmed |
Detection of plunging breaking waves based on machine learning |
title_sort |
detection of plunging breaking waves based on machine learning |
publisher |
ASME |
publishDate |
2018 |
url |
http://hdl.handle.net/11250/2580764 https://doi.org/10.1115/OMAE2018-77671 |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
ASME 2018 37th International Conference on Ocean, Offshore and Arctic Engineering - Volume 7A: Ocean Engineering urn:isbn:978-0-7918-5126-5 http://hdl.handle.net/11250/2580764 https://doi.org/10.1115/OMAE2018-77671 cristin:1647179 |
op_doi |
https://doi.org/10.1115/OMAE2018-77671 |
container_title |
Volume 7A: Ocean Engineering |
_version_ |
1766296180419985408 |