Zobrazit v EDS

Machine learning-based semi-online performance optimisation for long-range underwater glider missions.

Uloženo v:
Podrobná bibliografie
Název: Machine learning-based semi-online performance optimisation for long-range underwater glider missions.
Autoři: Feng, Kunpeng, Tan, Lijie, Cai, Jinhu, Wu, Hongyu, Hao, Yuxing, Yang, Yunqiang, Yan, Shaoze
Zdroj: Ships & Offshore Structures; Mar2026, Vol. 21 Issue 3, p268-278, 11p
Témata: UNDERWATER gliders, MULTI-objective optimization, ENERGY consumption, MACHINE learning, MATHEMATICAL optimization, DYNAMIC simulation
Abstrakt: This paper proposes a semi-online optimisation method for enhancing the performance of underwater gliders during long-range missions. The design variables include control parameters and target depth. The optimisation objective is to maximise the energy efficiency, motion accuracy and voyage velocity for a single profile. Initially, environmental data and glider position are collected by the monitoring equipment and communication satellite in real-time and then fed into the dynamic model. Subsequently, a training dataset is generated through dynamic simulation to establish a surrogate model by machine learning technology. Then, iterative calculations are executed based on the multi-objective optimisation algorithm and surrogate model to determine the optimal solution of design variables. Finally, an optimal solution is transmitted to the glider via a communication satellite, and a single profile gliding motion is executed. This process repeats until the glider reaches the target exploration point. The numerical case validates the effectiveness of this method. [ABSTRACT FROM AUTHOR]
Copyright of Ships & Offshore Structures is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáze: Complementary Index
Popis
Abstrakt:This paper proposes a semi-online optimisation method for enhancing the performance of underwater gliders during long-range missions. The design variables include control parameters and target depth. The optimisation objective is to maximise the energy efficiency, motion accuracy and voyage velocity for a single profile. Initially, environmental data and glider position are collected by the monitoring equipment and communication satellite in real-time and then fed into the dynamic model. Subsequently, a training dataset is generated through dynamic simulation to establish a surrogate model by machine learning technology. Then, iterative calculations are executed based on the multi-objective optimisation algorithm and surrogate model to determine the optimal solution of design variables. Finally, an optimal solution is transmitted to the glider via a communication satellite, and a single profile gliding motion is executed. This process repeats until the glider reaches the target exploration point. The numerical case validates the effectiveness of this method. [ABSTRACT FROM AUTHOR]
ISSN:17445302
DOI:10.1080/17445302.2024.2419514