Artificial neural networks for control and propagation of low-thrust trajectories

The work is devoted to the design of artificial neural networks which can be used for the orbital control of a spacecraft equipped with a low-thrust engine. The problem of energy-optimal transfer between two points is considered. Two neural networks are constructed: the predictive one and the contro...

Full description

Saved in:
Bibliographic Details
Main Authors: Sorokin, A. V., Shirobokov, M. G., Trofimov, S. P.
Format: Conference Proceeding
Language:English
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The work is devoted to the design of artificial neural networks which can be used for the orbital control of a spacecraft equipped with a low-thrust engine. The problem of energy-optimal transfer between two points is considered. Two neural networks are constructed: the predictive one and the controlling one. Their architecture, learning algorithms, and the performance in the presence of unaccounted disturbances are given.
ISSN:0094-243X
1551-7616
DOI:10.1063/1.5133368