Artificial Neural Networks for Control and Propagation of Low-Thrust Trajectories

被引：0
|
作者：
Sorokin, A. V. [1 ]
Shirobokov, M. G. [2 ]
Trofimov, S. P. [2 ]
机构：
[1] Moscow Inst Phys & Technol, Moscow, Russia
[2] Keldysh Inst Appl Math, Moscow, Russia
来源：
XLIII ACADEMIC SPACE CONFERENCE, DEDICATED TO THE MEMORY OF ACADEMICIAN S P KOROLEV AND OTHER OUTSTANDING RUSSIAN SCIENTISTS - PIONEERS OF SPACE EXPLORATION | 2019年 / 2171卷
基金：
俄罗斯基础研究基金会;
关键词：
OPTIMIZATION; SPACECRAFT;
D O I：
10.1063/1.5133368
中图分类号：
P1 [天文学];
学科分类号：
0704 ;
摘要：
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.
引用
收藏
页数：7
相关论文
共 50 条
12345