Satellite Attitude Identification and Prediction Based on Neural Network Compensation

This paper proposed a new attitude determination method for low-orbit spacecraft. The attitude prediction accuracy is greatly improved by adding the unmodeled environmental torque to the dynamic equation. Specifically, the environmental torque extraction algorithm based on extended Kalman filter and...

Full description

Bibliographic Details
Main Authors: Zibin Sun, Jules Simo, Shengping Gong
Format: Article
Language:English
Published: American Association for the Advancement of Science (AAAS) 2023-01-01
Series:Space: Science & Technology
Online Access:https://spj.science.org/doi/10.34133/space.0009
_version_ 1797810749470408704
author Zibin Sun
Jules Simo
Shengping Gong
author_facet Zibin Sun
Jules Simo
Shengping Gong
author_sort Zibin Sun
collection DOAJ
description This paper proposed a new attitude determination method for low-orbit spacecraft. The attitude prediction accuracy is greatly improved by adding the unmodeled environmental torque to the dynamic equation. Specifically, the environmental torque extraction algorithm based on extended Kalman filter and series extended state observer is introduced, and the unmodeled part of dynamic is identified through the inverse dynamic model. Then, the collected data are analyzed and trained by a backpropagation neural network, resulting in an attitude-torque mapping network with compensation ability. The simulation results show that the proposed feedback attitude prediction algorithm can outperform standard methods and provide a high accurate picture of prediction and reliability with discontinuous measurement.
first_indexed 2024-03-13T07:12:28Z
format Article
id doaj.art-f78b2da0e4584afaa052072eb8f2c327
institution Directory Open Access Journal
issn 2692-7659
language English
last_indexed 2024-03-13T07:12:28Z
publishDate 2023-01-01
publisher American Association for the Advancement of Science (AAAS)
record_format Article
series Space: Science & Technology
spelling doaj.art-f78b2da0e4584afaa052072eb8f2c3272023-06-05T19:35:33ZengAmerican Association for the Advancement of Science (AAAS)Space: Science & Technology2692-76592023-01-01310.34133/space.0009Satellite Attitude Identification and Prediction Based on Neural Network CompensationZibin Sun0Jules Simo1Shengping Gong2School of Aerospace Engineering, Tsinghua University, Beijing 100084, China.School of Engineering, University of Central Lancashire, Preston PR1 1XJ, UK.School of Astronuatics, Beihang University, Beijing 102206, China.This paper proposed a new attitude determination method for low-orbit spacecraft. The attitude prediction accuracy is greatly improved by adding the unmodeled environmental torque to the dynamic equation. Specifically, the environmental torque extraction algorithm based on extended Kalman filter and series extended state observer is introduced, and the unmodeled part of dynamic is identified through the inverse dynamic model. Then, the collected data are analyzed and trained by a backpropagation neural network, resulting in an attitude-torque mapping network with compensation ability. The simulation results show that the proposed feedback attitude prediction algorithm can outperform standard methods and provide a high accurate picture of prediction and reliability with discontinuous measurement.https://spj.science.org/doi/10.34133/space.0009
spellingShingle Zibin Sun
Jules Simo
Shengping Gong
Satellite Attitude Identification and Prediction Based on Neural Network Compensation
Space: Science & Technology
title Satellite Attitude Identification and Prediction Based on Neural Network Compensation
title_full Satellite Attitude Identification and Prediction Based on Neural Network Compensation
title_fullStr Satellite Attitude Identification and Prediction Based on Neural Network Compensation
title_full_unstemmed Satellite Attitude Identification and Prediction Based on Neural Network Compensation
title_short Satellite Attitude Identification and Prediction Based on Neural Network Compensation
title_sort satellite attitude identification and prediction based on neural network compensation
url https://spj.science.org/doi/10.34133/space.0009
work_keys_str_mv AT zibinsun satelliteattitudeidentificationandpredictionbasedonneuralnetworkcompensation
AT julessimo satelliteattitudeidentificationandpredictionbasedonneuralnetworkcompensation
AT shengpinggong satelliteattitudeidentificationandpredictionbasedonneuralnetworkcompensation