Ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm
In order to identify more accurately and efficiently the unknown parameters of a ship motions model, a novel Nonlinear Least Squares Support Vector Machine (NLSSVM) algorithm, whose penalty factor and Radial Basis Function (RBF) kernel parameters are optimised by the Beetle Antennae Search algorithm...
Published in: | Volume 7B: Ocean Engineering |
---|---|
Main Authors: | , , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
AMER SOC MECHANICAL ENGINEERS
2019
|
Subjects: | |
Online Access: | https://biblio.ugent.be/publication/8639442 http://hdl.handle.net/1854/LU-8639442 https://doi.org/10.1115/OMAE2019-95565 https://biblio.ugent.be/publication/8639442/file/8639443 |
id |
ftunivgent:oai:archive.ugent.be:8639442 |
---|---|
record_format |
openpolar |
spelling |
ftunivgent:oai:archive.ugent.be:8639442 2023-06-11T04:07:31+02:00 Ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm Chen, Changyuan Tello Ruiz, Manasés Lataire, Evert Delefortrie, Guillaume Mansuy, Marc Mei, Tianlong Vantorre, Marc 2019 application/pdf https://biblio.ugent.be/publication/8639442 http://hdl.handle.net/1854/LU-8639442 https://doi.org/10.1115/OMAE2019-95565 https://biblio.ugent.be/publication/8639442/file/8639443 eng eng AMER SOC MECHANICAL ENGINEERS https://biblio.ugent.be/publication/8639442 http://hdl.handle.net/1854/LU-8639442 http://dx.doi.org/10.1115/OMAE2019-95565 https://biblio.ugent.be/publication/8639442/file/8639443 No license (in copyright) info:eu-repo/semantics/restrictedAccess PROCEEDINGS OF THE ASME 38TH INTERNATIONAL CONFERENCE ON OCEAN, OFFSHORE AND ARCTIC ENGINEERING ISSN: 2153-4772 ISBN: 9780791858851 Technology and Engineering ship motions model NLSSVM BAS parameter identification conference info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/publishedVersion 2019 ftunivgent https://doi.org/10.1115/OMAE2019-95565 2023-05-10T22:38:29Z In order to identify more accurately and efficiently the unknown parameters of a ship motions model, a novel Nonlinear Least Squares Support Vector Machine (NLSSVM) algorithm, whose penalty factor and Radial Basis Function (RBF) kernel parameters are optimised by the Beetle Antennae Search algorithm (BAS), is proposed and investigated Aiming at validating the accuracy and applicability of the proposed method, the method is employed to identify the linear and nonlinear parameters of the first-order nonlinear Nomoto model with training samples from numerical simulation and experimental data. Subsequently, the identified parameters are applied in predicting the ship motion. The predicted results illustrate that the new NLSSVM-BAS algorithm can be applied in identifying ship motion's model, and the effectiveness is verified. Compared among traditional identification approaches with the proposed method, the results display that the accuracy is improved. Moreover, the robust and stability of the NLSSVM-BAS are verified by adding noise in the training sample data. Conference Object Arctic Ghent University Academic Bibliography Volume 7B: Ocean Engineering |
institution |
Open Polar |
collection |
Ghent University Academic Bibliography |
op_collection_id |
ftunivgent |
language |
English |
topic |
Technology and Engineering ship motions model NLSSVM BAS parameter identification |
spellingShingle |
Technology and Engineering ship motions model NLSSVM BAS parameter identification Chen, Changyuan Tello Ruiz, Manasés Lataire, Evert Delefortrie, Guillaume Mansuy, Marc Mei, Tianlong Vantorre, Marc Ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm |
topic_facet |
Technology and Engineering ship motions model NLSSVM BAS parameter identification |
description |
In order to identify more accurately and efficiently the unknown parameters of a ship motions model, a novel Nonlinear Least Squares Support Vector Machine (NLSSVM) algorithm, whose penalty factor and Radial Basis Function (RBF) kernel parameters are optimised by the Beetle Antennae Search algorithm (BAS), is proposed and investigated Aiming at validating the accuracy and applicability of the proposed method, the method is employed to identify the linear and nonlinear parameters of the first-order nonlinear Nomoto model with training samples from numerical simulation and experimental data. Subsequently, the identified parameters are applied in predicting the ship motion. The predicted results illustrate that the new NLSSVM-BAS algorithm can be applied in identifying ship motion's model, and the effectiveness is verified. Compared among traditional identification approaches with the proposed method, the results display that the accuracy is improved. Moreover, the robust and stability of the NLSSVM-BAS are verified by adding noise in the training sample data. |
format |
Conference Object |
author |
Chen, Changyuan Tello Ruiz, Manasés Lataire, Evert Delefortrie, Guillaume Mansuy, Marc Mei, Tianlong Vantorre, Marc |
author_facet |
Chen, Changyuan Tello Ruiz, Manasés Lataire, Evert Delefortrie, Guillaume Mansuy, Marc Mei, Tianlong Vantorre, Marc |
author_sort |
Chen, Changyuan |
title |
Ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm |
title_short |
Ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm |
title_full |
Ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm |
title_fullStr |
Ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm |
title_full_unstemmed |
Ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm |
title_sort |
ship manoeuvring model parameter identification using intelligent machine learning method and the beetle antennae search algorithm |
publisher |
AMER SOC MECHANICAL ENGINEERS |
publishDate |
2019 |
url |
https://biblio.ugent.be/publication/8639442 http://hdl.handle.net/1854/LU-8639442 https://doi.org/10.1115/OMAE2019-95565 https://biblio.ugent.be/publication/8639442/file/8639443 |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
PROCEEDINGS OF THE ASME 38TH INTERNATIONAL CONFERENCE ON OCEAN, OFFSHORE AND ARCTIC ENGINEERING ISSN: 2153-4772 ISBN: 9780791858851 |
op_relation |
https://biblio.ugent.be/publication/8639442 http://hdl.handle.net/1854/LU-8639442 http://dx.doi.org/10.1115/OMAE2019-95565 https://biblio.ugent.be/publication/8639442/file/8639443 |
op_rights |
No license (in copyright) info:eu-repo/semantics/restrictedAccess |
op_doi |
https://doi.org/10.1115/OMAE2019-95565 |
container_title |
Volume 7B: Ocean Engineering |
_version_ |
1768380673202061312 |