Intelligent orbit prediction for large morphing spacecraft

LIAO Jiahao; MENG Yunhe

doi:10.11714/acta.snus.ZR20260013

您当前的位置：

首页 >

文章列表页 >

Intelligent orbit prediction for large morphing spacecraft

Research articles | 更新时间：2026-05-22

- Intelligent orbit prediction for large morphing spacecraft
- Acta Scientiarum Naturalium Universitatis Sunyatseni Vol. 65, Issue 3, Pages: 128-134(2026)
- 作者机构：
  
  中山大学人工智能学院，广东珠海 519082
- 作者简介：
- 基金信息：
- DOI：10.11714/acta.snus.ZR20260013
  CLC： V412.4
- Received：02 January 2026，
  
  Accepted：26 January 2026，
  
  Online First：07 April 2026，
  
  Published：25 May 2026
- 稿件说明：
移动端阅览
廖嘉豪,孟云鹤.面向大型变型航天器的智能轨道预报方法[J].中山大学学报(自然科学版)(中英文),2026,65(03):128-134.

LIAO Jiahao,MENG Yunhe.Intelligent orbit prediction for large morphing spacecraft[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2026,65(03):128-134.
廖嘉豪,孟云鹤.面向大型变型航天器的智能轨道预报方法[J].中山大学学报(自然科学版)(中英文),2026,65(03):128-134. DOI： 10.11714/acta.snus.ZR20260013.

LIAO Jiahao,MENG Yunhe.Intelligent orbit prediction for large morphing spacecraft[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2026,65(03):128-134. DOI： 10.11714/acta.snus.ZR20260013.

摘要

低轨大型航天器的中长期轨道预报精度主要受空间环境不确定性及在轨构型变化的影响。传统预报方法受限于大气密度模型误差及阻力系数的适用性，且对迎风面积随构型变化缺乏精细建模。本文提出了一种面向大型变型航天器的中长期智能轨道预报方法。该方法引入伪阻力系数概念，将大气密度和阻力系数的不确定性统一建模为可学习的时变参数，构建了融合高精度动力学模型与数据驱动的预报框架；进一步给出了伪阻力系数修正模型，显式刻画迎风面积变化与伪阻力系数之间的定量关系。以某在轨大型变型航天器为研究对象的仿真实验表明：在多次变型场景下，所提方法的轨道预报误差显著低于传统方法，可有效提升中长期预报的精度与适应性。

Abstract

The accuracy of medium and long-term orbit predictions for LEO spacecraft is susceptible to uncertainties in the space environment and on-orbit configuration changes.The traditional prediction methods are limited by errors in atmospheric density models，the inadequate applicability of drag coefficients，and the lack of detailed modeling of the variation in effective windward area due to configuration changes.This paper proposes a medium and long-term orbit prediction method for large morphing spacecraft.This method introduces pseudo-drag coefficient to uniformly model the multiple uncertainties related to atmospheric drag as a learnable time-varying parameter.It constructs a prediction framework that integrates high-precision dynamic orbit model with data-driven techniques.Furthermore，a correction model for the pseudo-drag coefficient is established to explicitly characterize the quantitative relationship between changes in the windward area and the pseudo-drag coefficient. Simulation experiments conducted on a large morphing spacecraft demonstrate that， under multiple morphing scenarios，the proposed method achieves significantly lower orbit prediction errors than traditional method，effectively enhancing the accuracy and adaptability of medium and long-term prediction.

关键词

Keywords

references

段成林，盛庆轩，慎千慧，等， 2025 . 空间站高精度轨道预报空间环境参数使用策略分析［J］. 载人航天， 31 （ 3 ）： 344 - 350 .

雷骐玮，张洪波， 2023 . 基于PPO2强化学习算法的空间站轨道预报方法［J］. 中国空间科学技术， 43 （ 4 ）： 93 - 103 .

汪宏波，赵长印，柳仲贵，等， 2016 . 基于误差发散规律的低轨卫星大气阻力系数计算方法［J］. 天文学报， 57 （ 4 ）： 447 - 460 .

徐玲玲，赵航，宋静，等， 2024 . 基于SGP4模型的空间站轨道精度分析［J］. 全球定位系统， 49 （ 2 ）： 98 - 105 .

CALABIA A ， JIN S ， 2021 . Upper-Atmosphere Mass Density Variations From CASSIOPE Precise Orbits ［J］. Space Weather ， 19 （ 4 ）： e2020SW002645 .

CHEN X ， TANG C ， DAI W ， et al ， 2025 . Modelling and prediction of atmospheric drag coefficients in LEO satellite orbit determination and prediction with Bi-LSTM approach ［J］. Adv Space Res ， 75 （ 3 ）： 2874 - 2888 .

CIMMINO N ， OPROMOLLA R ， FASANO G ， 2023 . Machine learning-based approach for ballistic coefficient estimation of resident space objects in LEO ［J］. Adv Space Res ， 71 （ 12 ）： 5007 - 5025 .

DEY S ， RAY S ， GHOSH S ， et al ， 2025 . An extreme events study of the storm-time variations in satellite drag coefficients ［J］. Space Weather ， 23 （ 12 ）： e2025SW004634 .

EMMERT J T ， 2015 . Thermospheric mass density： A review ［J］. Adv Space Res ， 56 （ 5 ）： 773 - 824 .

HAO Y ， LU J ， PENG G ， et al ， 2024 . F10.7 daily forecast using LSTM combined with VMD method ［J］. Space Weather ， 22 （ 1 ）： e2023SW003552 .

HUANG W B ， TANG R ， QU G Z ， et al ， 2024 . An XGBoost-based method for improved orbit prediction with an orbit-separate modeling strategy ［J］. IEEE Trans Aerosp Electron Syst ， 60 （ 4 ）： 4887 - 4895

LI B ， ZHANG Y ， HUANG J ， et al ， 2021 . Improved orbit predictions using two-line elements through error pattern mining and transferring ［J］. Acta Astronaut ， 188 ： 405 - 415 .

LIN C ， CHEN J ， ZHU H ， 2025 . A method for compensating prediction errors to improve the orbit prediction accuracy of Starlink satellites ［J］. GPS Solutions ， 29 （ 1 ）： 17 .

MONTENBRUCK O ， GILL E ， RACKESTAD B ， et al ， 2011 . Orbit determination and prediction of the International Space Station ［J］. J Spacecr Rockets ， 48 （ 6 ）： 1055 - 1067 .

National Aeronautics and Space Administration（NASA）， 2025 . Unique Conjunction Events ［EB/OL］.［ 2025-01-01 ］. https：//www.nasa.gov/cara/unique-conjunction-events https://www.nasa.gov/cara/unique-conjunction-events .

North American Aerospace Defense Command（NORAD）， 2024 . Space Scoreboard ［EB/OL］. ［ 2024-12-24 ］. https：//www.space-track.org https://www.space-track.org .

PENG H ， BAI X ， 2023 . A medium-scale study of using machine learning fusion to improve TLE prediction precision without external information ［J］. Acta Astronaut ， 204 ： 477 - 491 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-method approach for groundwater pollution source apportionment： A case study in the Pearl River Delta

Mechanism of hydroxyl radical elimination by gallic acid in physiological aqueous environments based on density functional theory

Effects of different light conditions on the growth and pharmacodynamic components of Isodon lophanthoides var. graciliflorus

Morphological changes and gibberellin-related gene expression patterns during fruit growth and development of Amomum villosum

Multiple headspace solid-phase microextraction for quantifying volatiles in Citrus reticulata 'Chachi' peel of different storage time

Related Author

No data

Related Institution

No data

Postal code：510275
Tel：020-84112585，84113223 Email：xuebaozr@mail.sysu.edu.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰