提出了一种基于滤波思想的卫星轨迹预测方法.该方法借鉴长短期记忆网络的结构,以最优估计为统计方法,从信号分析的角度入手,且具有明确的物理意义.通过短弧轨道外推的对比仿真实验,验证了波模型与当前常用轨道外推方法的性能差异.实验中使用两种不同程度系统误差的波模型,并通过控制变量讨论了轨道高度、观测精度、以及观测弧长对预报精度的影响.对于3 min的短弧观测数据,当预报时长少于10 min时,对低轨(lowearth orbit,LEO)目标,J2波模型的预报精度与动力学外推方法相当,且优于切比雪夫外推方法;对地球静止轨道(geostationary earth orbit,GEO)目标,J2波模型的预报精度优于动力学外推方法.
This paper proposed a satellite trajectory prediction method based on the idea of filtering. Drawing on the structure of long short-term memory（LSTM）networks, this method employed optimal estimation as the statistical method and began from the perspective of signal analysis, with a clear physical significance. Through comparative simulation experiments on short-arc orbit extrapolation, the performance differences between the wave model and the currently commonly used orbit extrapolation methods were verified. In the experiments, two wave models with different levels of systematic errors were used. The controlled variable experiments were conducted to discuss the effects of orbit altitude, observation accuracy, and observation arc length on forecast accuracy. For a short-arc observation data of three minutes, if the forecast duration is less than 10 minutes, the J2 wave model has comparable forecast accuracy to the dynamical extrapolation method and is superior to the Chebyshev extrapolation method for low earth orbit (LEO) targets, while the forecast accuracy of the J2 wave model is superior to that of the dynamical extrapolation method for geostationary earth orbit (GEO) targets.
[1] Peng H, Bai X L. Improving orbit prediction accuracy through supervised machine learning [J]. Advances in Space Research, 2018, 61(10): 2628-2646.
[2] 谭理庆, 彭琦, 曹阳, 等. 不同轨道类型LEO卫星轨道拟合及预报精度研究[J]. 全球定位系统, 2022, 47(2): 44-51.
[3] 郭睿, 胡小工, 黄勇, 等. 基于星历拟合的短弧运动学定轨[J]. 宇航学报, 2010, 31(2): 416-422.
[4] 雷祥旭, 夏胜夫, 杨洋, 等. LEO空间碎片甚短弧角度数据初轨确定方法对比[J]. 空间科学学报, 2022, 42(5): 984-990.
[5] Zhai M, Huyan Z, Hu Y, et al. Improvement of orbit prediction accuracy using extreme gradient boosting and principal component analysis [J]. Open Astronomy, 2022, 31(1): 229-243.
[6] Heisenberg W. Über den anschaulichen Inhalt der quantentheoretischen Kinematik und Mechanik [J]. Zeitschrift für Physik, 1927, 43(3/4): 172-198.
[7] Schrödinger E. An undulatory theory of the mechanics of atoms and molecules [J]. Physical Review, 1926, 28(6): 1049-1070.
[8] Agrawal G P. Nonlinear Fiber Optics [M]. 6 th ed. Amsterdam: Elsevier, 2019: 41-43.
[9] Vyas D R, Ottino J M, Lueptow R M, et al. Improved velocity-verlet algorithm for the discrete element method [J]. Computer Physics Communications, 2025, 310: 109524.
[10] Hochreiter S, Schmidhuber J. Long short-term memory [J]. Neural Computation, 1997, 9(8): 1735-1780.
[11] 杨延玲. 两种量子力学常用绘景的比较[J]. 科技信息, 2009(10): 17-20.
[12] DeWitt C M. Feynman’s path integral [J]. Commun Math Phys, 1972, 28: 47-67.
[13] 刘林, 王歆. 考虑地球扁率摄动影响的初轨计算方法[J]. 天文学报, 2003, 44(2): 175-179.
[14] Melko R G, Carleo G, Carrasquilla J, et al. Restricted Boltzmann machines in quantum physics [J]. Nature Physics, 2019, 15(9): 887-892.
[15] Sharma P, Chung W T, Akoush B, et al. A review of physics-informed machine learning in fluid mechanics [J]. Energies, 2023, 16(5): 2343.
[16] Lancaster T, Blundell S J. Quantum Field Theory for the Gifted Amateur [M]. Oxford: Oxford University Press, 2014: 154-163.
[17] 彭桓武. 阻尼谐振子的量子力学处理[J]. 物理学报, 1980, 29(8): 1084-1089.
