https://doi.org/10.1140/epjs/s11734-025-01870-y
Regular Article
Machine learning techniques for the design of spinning tether system
UNESP-São Paulo State University, Guaratinguetá, São Paulo, Brazil
a
This email address is being protected from spambots. You need JavaScript enabled to view it.
Received:
3
April
2025
Accepted:
17
August
2025
Published online:
23
August
2025
Abstract
Two spacecraft can be joined by a tether to create a new, combined spacecraft. This kind of spacecraft is called the Spinning Tether System (STS). This technology finds use in various applications, including orbital maneuvers, aerobraking, and artificial gravity. In this work, we propose STS for payload transfer and orbit acquisition. The model uses gravitational capture, defined as the transition from a hyperbolic orbit to a temporary elliptical orbit, and a controlled rupture of the tether. In this process, one spacecraft loses orbital energy, while the other one has a gain in orbital energy. The one that loses energy has its temporary elliptical orbit turned into a permanent one, whereas the other is spelled from the orbit. In the present study, machine learning strategies are used to metamodel the relationship between design variables and performance index. Simulation data are ingested in the training phase of machine learning algorithms to build a metamodel that maps the relation between input and output quantities. The performance of two machine learning strategies is compared through the average error obtained in predicting new designs. The numerical results show the viability of the proposed methodology.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Ernesto Vieira Neto and Rogério Rodrigues dos Santos have contributed equally to this work.
© The Author(s), under exclusive licence to EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
