Applicability of Machine Learning for Vessel Dimension Survey with a Minimum Number of Common Points
This paper presents the challenges encountered in the dimensional control of ships, platforms, and offshore units. This novel approach utilizes machine learning (MLP—Multilayer Perceptron Neural Network) for three-dimensional (3D) spatial coordinate transformations when only three common points are...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/7/3453 |
| _version_ | 1797440400140533760 |
|---|---|
| author | Ilona Garczyńska Arkadiusz Tomczak Grzegorz Stępień Lech Kasyk Wojciech Ślączka Tomasz Kogut |
| author_facet | Ilona Garczyńska Arkadiusz Tomczak Grzegorz Stępień Lech Kasyk Wojciech Ślączka Tomasz Kogut |
| author_sort | Ilona Garczyńska |
| collection | DOAJ |
| description | This paper presents the challenges encountered in the dimensional control of ships, platforms, and offshore units. This novel approach utilizes machine learning (MLP—Multilayer Perceptron Neural Network) for three-dimensional (3D) spatial coordinate transformations when only three common points are known. The proposed method was verified based on laboratory and field data. The main issue was to provide a sufficient number of valid training points. The oversampling method was used to meet this criterion. The achieved results indicate equal or better accuracy when the points were located inside the adjustment points array. In the case where the points lay outside this array, no improvement in the accuracy of the transformation was observed. The neural approach restores the transformation symmetry, and in some cases, such as the study of deformation of engineering objects, breaks the symmetry rather than restoring it. |
| first_indexed | 2024-03-09T12:07:37Z |
| format | Article |
| id | doaj.art-5f74547771c7469f8d9dc4572b5c9c24 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T12:07:37Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-5f74547771c7469f8d9dc4572b5c9c242023-11-30T22:55:56ZengMDPI AGApplied Sciences2076-34172022-03-01127345310.3390/app12073453Applicability of Machine Learning for Vessel Dimension Survey with a Minimum Number of Common PointsIlona Garczyńska0Arkadiusz Tomczak1Grzegorz Stępień2Lech Kasyk3Wojciech Ślączka4Tomasz Kogut5Faculty of Navigation, Maritime University of Szczecin, 70-500 Szczecin, PolandFaculty of Navigation, Maritime University of Szczecin, 70-500 Szczecin, PolandFaculty of Navigation, Maritime University of Szczecin, 70-500 Szczecin, PolandFaculty of Navigation, Maritime University of Szczecin, 70-500 Szczecin, PolandFaculty of Navigation, Maritime University of Szczecin, 70-500 Szczecin, PolandFaculty of Navigation, Maritime University of Szczecin, 70-500 Szczecin, PolandThis paper presents the challenges encountered in the dimensional control of ships, platforms, and offshore units. This novel approach utilizes machine learning (MLP—Multilayer Perceptron Neural Network) for three-dimensional (3D) spatial coordinate transformations when only three common points are known. The proposed method was verified based on laboratory and field data. The main issue was to provide a sufficient number of valid training points. The oversampling method was used to meet this criterion. The achieved results indicate equal or better accuracy when the points were located inside the adjustment points array. In the case where the points lay outside this array, no improvement in the accuracy of the transformation was observed. The neural approach restores the transformation symmetry, and in some cases, such as the study of deformation of engineering objects, breaks the symmetry rather than restoring it.https://www.mdpi.com/2076-3417/12/7/3453three-dimensional coordinates transformationsoff-shore surveyingdimensional controlmarine geodesyartificial neural networksapplied engineering |
| spellingShingle | Ilona Garczyńska Arkadiusz Tomczak Grzegorz Stępień Lech Kasyk Wojciech Ślączka Tomasz Kogut Applicability of Machine Learning for Vessel Dimension Survey with a Minimum Number of Common Points Applied Sciences three-dimensional coordinates transformations off-shore surveying dimensional control marine geodesy artificial neural networks applied engineering |
| title | Applicability of Machine Learning for Vessel Dimension Survey with a Minimum Number of Common Points |
| title_full | Applicability of Machine Learning for Vessel Dimension Survey with a Minimum Number of Common Points |
| title_fullStr | Applicability of Machine Learning for Vessel Dimension Survey with a Minimum Number of Common Points |
| title_full_unstemmed | Applicability of Machine Learning for Vessel Dimension Survey with a Minimum Number of Common Points |
| title_short | Applicability of Machine Learning for Vessel Dimension Survey with a Minimum Number of Common Points |
| title_sort | applicability of machine learning for vessel dimension survey with a minimum number of common points |
| topic | three-dimensional coordinates transformations off-shore surveying dimensional control marine geodesy artificial neural networks applied engineering |
| url | https://www.mdpi.com/2076-3417/12/7/3453 |
| work_keys_str_mv | AT ilonagarczynska applicabilityofmachinelearningforvesseldimensionsurveywithaminimumnumberofcommonpoints AT arkadiusztomczak applicabilityofmachinelearningforvesseldimensionsurveywithaminimumnumberofcommonpoints AT grzegorzstepien applicabilityofmachinelearningforvesseldimensionsurveywithaminimumnumberofcommonpoints AT lechkasyk applicabilityofmachinelearningforvesseldimensionsurveywithaminimumnumberofcommonpoints AT wojciechslaczka applicabilityofmachinelearningforvesseldimensionsurveywithaminimumnumberofcommonpoints AT tomaszkogut applicabilityofmachinelearningforvesseldimensionsurveywithaminimumnumberofcommonpoints |