Artificial Intelligence Machine Learning in Marine Hydrodynamics
Artificial Intelligence (AI) Support Vector Machine (SVM) learning algorithms have enjoyed rapid growth in recent years with applications in a wide range of disciplines often with impressive results. The present paper introduces this machine learning technology to the field of marine hydrodynamics f...
Published in: | Volume 9: Offshore Geotechnics; Honoring Symposium for Professor Bernard Molin on Marine and Offshore Hydrodynamics |
---|---|
Main Authors: | , |
Other Authors: | |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
American Society of Mechanical Engineers
2018
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/121110 |
id |
ftmit:oai:dspace.mit.edu:1721.1/121110 |
---|---|
record_format |
openpolar |
spelling |
ftmit:oai:dspace.mit.edu:1721.1/121110 2023-06-11T04:07:31+02:00 Artificial Intelligence Machine Learning in Marine Hydrodynamics Sclavounos, Paul D Ma, Yu Massachusetts Institute of Technology. Department of Mechanical Engineering Sclavounos, Paul D Ma, Yu 2018-12-20T16:33:09Z application/pdf http://hdl.handle.net/1721.1/121110 unknown American Society of Mechanical Engineers http://dx.doi.org/10.1115/OMAE2018-77599 Proceedings of the ASME 2018 37th International Conference on Ocean, Offshore and Arctic Engineering 978-0-7918-5130-2 http://hdl.handle.net/1721.1/121110 orcid:0000-0002-9141-6073 orcid:0000-0001-5256-3372 Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. ASME Article http://purl.org/eprint/type/ConferencePaper 2018 ftmit https://doi.org/10.1115/OMAE2018-77599 2023-05-29T08:31:21Z Artificial Intelligence (AI) Support Vector Machine (SVM) learning algorithms have enjoyed rapid growth in recent years with applications in a wide range of disciplines often with impressive results. The present paper introduces this machine learning technology to the field of marine hydrodynamics for the study of complex potential and viscous flow problems. Examples considered include the forecasting of the seastate elevations and vessel responses using their past time records as "explanatory variables" or "features" and the development of a nonlinear model for the roll restoring, added moment of inertia and viscous damping using the vessel response kinematics from free decay tests as "features". A key innovation of AI-SVM kernel algorithms is that the nonlinear dependence of the dependent variable on the "features" is embedded into the SVM kernel and its selection plays a key role in the performance of the algorithms. The kernel selection is discussed and its relation to the physics of the marine hydrodynamic flows considered in the present paper is addressed. United States. Office of Naval Research (Grant N00014-17-1-2985) Article in Journal/Newspaper Arctic DSpace@MIT (Massachusetts Institute of Technology) Volume 9: Offshore Geotechnics; Honoring Symposium for Professor Bernard Molin on Marine and Offshore Hydrodynamics |
institution |
Open Polar |
collection |
DSpace@MIT (Massachusetts Institute of Technology) |
op_collection_id |
ftmit |
language |
unknown |
description |
Artificial Intelligence (AI) Support Vector Machine (SVM) learning algorithms have enjoyed rapid growth in recent years with applications in a wide range of disciplines often with impressive results. The present paper introduces this machine learning technology to the field of marine hydrodynamics for the study of complex potential and viscous flow problems. Examples considered include the forecasting of the seastate elevations and vessel responses using their past time records as "explanatory variables" or "features" and the development of a nonlinear model for the roll restoring, added moment of inertia and viscous damping using the vessel response kinematics from free decay tests as "features". A key innovation of AI-SVM kernel algorithms is that the nonlinear dependence of the dependent variable on the "features" is embedded into the SVM kernel and its selection plays a key role in the performance of the algorithms. The kernel selection is discussed and its relation to the physics of the marine hydrodynamic flows considered in the present paper is addressed. United States. Office of Naval Research (Grant N00014-17-1-2985) |
author2 |
Massachusetts Institute of Technology. Department of Mechanical Engineering Sclavounos, Paul D Ma, Yu |
format |
Article in Journal/Newspaper |
author |
Sclavounos, Paul D Ma, Yu |
spellingShingle |
Sclavounos, Paul D Ma, Yu Artificial Intelligence Machine Learning in Marine Hydrodynamics |
author_facet |
Sclavounos, Paul D Ma, Yu |
author_sort |
Sclavounos, Paul D |
title |
Artificial Intelligence Machine Learning in Marine Hydrodynamics |
title_short |
Artificial Intelligence Machine Learning in Marine Hydrodynamics |
title_full |
Artificial Intelligence Machine Learning in Marine Hydrodynamics |
title_fullStr |
Artificial Intelligence Machine Learning in Marine Hydrodynamics |
title_full_unstemmed |
Artificial Intelligence Machine Learning in Marine Hydrodynamics |
title_sort |
artificial intelligence machine learning in marine hydrodynamics |
publisher |
American Society of Mechanical Engineers |
publishDate |
2018 |
url |
http://hdl.handle.net/1721.1/121110 |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
ASME |
op_relation |
http://dx.doi.org/10.1115/OMAE2018-77599 Proceedings of the ASME 2018 37th International Conference on Ocean, Offshore and Arctic Engineering 978-0-7918-5130-2 http://hdl.handle.net/1721.1/121110 orcid:0000-0002-9141-6073 orcid:0000-0001-5256-3372 |
op_rights |
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. |
op_doi |
https://doi.org/10.1115/OMAE2018-77599 |
container_title |
Volume 9: Offshore Geotechnics; Honoring Symposium for Professor Bernard Molin on Marine and Offshore Hydrodynamics |
_version_ |
1768380693646147584 |