Improving the Evolutionary Optimization of Interplanetary Low-Thrust Trajectories Using a Neural Network Surrogate Model

Conference Paper (2021)
Author(s)

L.J. Stubbig (Student TU Delft)

K.J. Cowan (TU Delft - Astrodynamics & Space Missions)

Research Group
Astrodynamics & Space Missions
Copyright
© 2021 L.J. Stubbig, K.J. Cowan
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 L.J. Stubbig, K.J. Cowan
Research Group
Astrodynamics & Space Missions
Volume number
175
ISBN (print)
978-0-87703-675-3
ISBN (electronic)
978-0-87703-676-0
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Building on recent advances in the fields of low-thrust trajectory optimization based on shaping methods, Artificial Neural Networks, and surrogate models in Evolutionary Algorithms, an investigation into a novel optimization routine is conducted. A flexible Python tool to evaluate linked trajectories in a two-body model based on hodographic shaping is implemented and used to develop a novel evolutionary optimization approach where a Genetic Algorithm is assisted in finding new candidate solutions by an online surrogate. The algorithm and different surrogate designs are experimentally investigated on two example problems based on the Dawn trajectory and the GTOC2 problem. Employing the surrogate yields new candidate solutions that improve the population’s fitness especially when the surrogate is used to approximate the shaping computation. Additionally, the use of a surrogate pretrained on a general data set of low-thrust transfers is tested and found to considerably improve the initial quality of the model, meaning that more good candidate solutions are found early on, accelerating the algorithm’s convergence.

Files

AAS_20_658.pdf
(pdf | 2.81 Mb)
- Embargo expired in 20-12-2021
License info not available