WEI Erhu, REN Xiaobin, LIU Jingnan, LI Lianyan, WU Shuguang, NIE Guigen. Prediction of Lunar Libration Parameters Using LSTM[J]. Geomatics and Information Science of Wuhan University, 2022, 47(11): 1815-1822. DOI: 10.13203/j.whugis20200318
Citation: WEI Erhu, REN Xiaobin, LIU Jingnan, LI Lianyan, WU Shuguang, NIE Guigen. Prediction of Lunar Libration Parameters Using LSTM[J]. Geomatics and Information Science of Wuhan University, 2022, 47(11): 1815-1822. DOI: 10.13203/j.whugis20200318

Prediction of Lunar Libration Parameters Using LSTM

Funds: 

The National Key Research and Development Program of China 2018YFC1503600

the National Natural Science Foundation of China 41874036

More Information
  • Author Bio:

    WEI Erhu, PhD, professor, specializes in space geodesy and deep space navigation. E-mail: ehwei@sgg.whu.edu.cn

  • Corresponding author:

    REN Xiaobin, master. E-mail: xiaobinren@whu.edu.cn

  • Received Date: July 08, 2021
  • Available Online: November 15, 2022
  • Published Date: November 04, 2022
  •   Objectives  The prediction of lunar physical liberation is very important for precise positioning of lander and rover. The coordinates and physical libration of Chang'E-3 lander are calculated based on the very long baseline interferometry(VLBI) single point positioning model. Meanwhile, the parameters of the lunar libration are obtained in the 7-day arc.
      Methods  Based on the recursive neural network(RNN), a long-short term memory(LSTM) neural network is used to establish a prediction model of the lunar libration parameters. Using the coordinates of the lunar lander and the VLBI observation as input, selecting three Euler angles as output, 2 424 samples are used for training, 519 samples are used for testing, and 519 samples are used for verification.
      Results  The results show that the data of the verification set has a gradient of about 1 000 training and 9 iterations, and the maximum absolute error after training is only 6.2×10-5(″)/s. The experimental results show that the three Euler angles Ωiμ of LSTM are accurate to 97.8%, 99.7%, 97.2%, and the three Euler angles of RNN networks are accurate to 95.2%, 98.5%, 95.8%.
      Conclusions  It is proved that the LSTM network has higher prediction accuracy than the RNN network. Compared with the predicted results of JPL DE421 ephemeris, it is proved that the LSTM network has the higher prediction accuracy.
  • [1]
    Wen W B, Wang F, Li C L, et al. Data Preprocessing and Preliminary Results of the Moon-Based Ultraviolet Telescope on the CE-3 Lander[J]. Research in Astronomy and Astrophysics, 2014, 14(12): 1674-1681 doi: 10.1088/1674-4527/14/12/015
    [2]
    Zhang H Y, Wang Y, Chen L P, et al. In-Situ Lunar Dust Deposition Amount Induced by Lander Landing in Chang'E-3 Mission[J]. Science China Technological Sciences, 2020, 63(3): 520-527 doi: 10.1007/s11431-019-1434-y
    [3]
    徐焕宇, 刘佶鑫, 孙巍巍, 等. 基于序列图像的月球着陆定位计算方法研究[J]. 计算机科学, 2011, 38(12): 269-273 doi: 10.3969/j.issn.1002-137X.2011.12.062

    Xu Huanyu, Liu Jixin, Sun Weiwei, et al. Image Sequence Based Lunar Landing Locating Algorithm[J]. Computer Science, 2011, 38(12): 269-273 doi: 10.3969/j.issn.1002-137X.2011.12.062
    [4]
    魏二虎, 李雪川, 金双根, 等. 用VLBI跟踪数据确定CE-2环月段轨道的研究[J]. 测绘地理信息, 2015, 40(4): 6-9 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG201504003.htm

    Wei Erhu, Li Xuechuan, Jin Shuanggen, et al. Mission Orbit Determination and Analysis of CE-2 with VLBI[J]. Journal of Geomatics, 2015, 40(4): 6-9 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG201504003.htm
    [5]
    曹建峰, 张宇, 胡松杰, 等. 嫦娥三号着陆器精确定位与精度分析[J]. 武汉大学学报·信息科学版, 2016, 41(2): 274-278 doi: 10.13203/j.whugis20140123

    Cao Jianfeng, Zhang Yu, Hu Songjie, et al. An Analysis of Precise Positioning and Accuracy of the CE-3 Lunarlander Soft Landing[J]. Geomatics and Information Science of Wuhan University, 2016, 41(2): 274-278 doi: 10.13203/j.whugis20140123
    [6]
    李培佳, 黄勇, 昌胜骐, 等. 基于地基观测的嫦娥三号着陆器与巡视器高精度定位[J]. 科学通报, 2014, 59(32): 3162-3173 https://www.cnki.com.cn/Article/CJFDTOTAL-KXTB201432007.htm

    Li Peijia, Huang Yong, Chang Shengqi, et al. Positioning for the Chang'E-3 Lander and Rover Using Earth-Based Observations[J]. Chinese Science Bulletin, 2014, 59(32): 3162-3173 https://www.cnki.com.cn/Article/CJFDTOTAL-KXTB201432007.htm
    [7]
    Newhall X X, Williams J G. Estimation of the Lunar Physical Librations[J]. Celestial Mechanics and Dynamical Astronomy, 1997, 66(1): 21-30 doi: 10.1007/BF00048820
    [8]
    Williams J G. A Scheme for Lunar Inner Core Detection[J]. Geophysical Research Letters, 2007, 34(3): L03202
    [9]
    Petrova N, Gusev A, Ping J S, et al. Lunar Project ILOM: Application of the Analytical Theory of Lunar Physical Libration for the Simulation of Star Observations[J]. Science China Physics, Mechanics and Astronomy, 2012, 55(5): 888-891 doi: 10.1007/s11433-012-4698-5
    [10]
    Petrova N, Gusev A, Kawano N, et al. Free Librations of the Two-Layer Moon and the Possibilities of Their Detection[J]. Advances in Space Research, 2008, 42(8): 1398-1404 doi: 10.1016/j.asr.2008.02.017
    [11]
    Yang Y Z, He Q B, Ping J S, et al. Estimation of the Lunar Free Libration Modes Based on the Recent Ephemerides[J]. Astrophysics and Space Science, 2019, 364(12): 218 doi: 10.1007/s10509-019-3684-z
    [12]
    Panafidina N, Hugentobler U, Krásná H, et al. Mechanism of Error Propagation from the Subdaily Universal Time Model into the Celestial Pole Offsets Estimated by VLBI[J]. Advances in Space Research, 2019, 63(1): 51-62 doi: 10.1016/j.asr.2018.08.007
    [13]
    Bergstrand S, Herbertsson M, Rieck C, et al. A Gravitational Telescope Deformation Model for Geodetic VLBI[J]. Journal of Geodesy, 2019, 93(5): 669-680 doi: 10.1007/s00190-018-1188-1
    [14]
    Sharma D. Deep Learning Without Tears: A Simple Introduction[J]. Resonance, 2020, 25(1): 15-32 doi: 10.1007/s12045-019-0919-9
    [15]
    Mahendran K, Prabha S U. Optimal Control Strategies for a Hybrid Renewable Energy System: An ALANN/RNN Technique[J]. Soft Computing, 2019, 23(24): 13459-13475 doi: 10.1007/s00500-019-03885-9
    [16]
    Ahmadi A, Jun T N. A Novel Predictive-Coding-Inspired Variational RNN Model for Online Prediction and Recognition[J]. Neural Computation, 2019, 31(11): 2025-2074 doi: 10.1162/neco_a_01228
    [17]
    Kulkarni S S, Achenbach J D. Structural Health Monitoring and Damage Prognosis in Fatigue[J]. Structural Health Monitoring, 2008, 7(1): 37-49 doi: 10.1177/1475921707081973
    [18]
    Yu Y, Si X S, Hu C H, et al. A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures[J]. Neural Computation, 2019, 31(7): 1235-1270 doi: 10.1162/neco_a_01199
    [19]
    Wu Y T, Yuan M, Dong S P, et al. Remaining Useful Life Estimation of Engineered Systems Using Vanilla LSTM Neural Networks[J]. Neurocomputing, 2018, 275: 167-179 doi: 10.1016/j.neucom.2017.05.063
    [20]
    Shao H D, Jiang H K, Li X Q, et al. Rolling Bearing Fault Detection Using Continuous Deep Belief Network with Locally Linear Embedding[J]. Computers in Industry, 2018, 96: 27-39 doi: 10.1016/j.compind.2018.01.005
  • Related Articles

    [1]ZHONG Shengjian, SHU Fengchun, LI Jinling, WU De, HE Xuan, TONG Fengxian. Simulated Analysis of EOP Measurement Accuracies with Participation of Chinese VGOS Stations in International Observations[J]. Geomatics and Information Science of Wuhan University, 2023, 48(9): 1455-1464. DOI: 10.13203/j.whugis20210204
    [2]YANG Peng, HUANG Yong, LI Peijia, LIU Qinghui, QIN Songhe, SHAN Quan, LIU Siyu. Positioning and Accuracy Analysis of Tianwen-1 Mars Rover Based on Same-Beam VLBI Measurement[J]. Geomatics and Information Science of Wuhan University, 2023, 48(1): 84-91. DOI: 10.13203/j.whugis20200532
    [3]HUANG Yidan, SHU Fengchun, HE Xuan, ZHENG Weimin. Data Processing and Analysis for the First UT1 Session Using VGOS Broadband System[J]. Geomatics and Information Science of Wuhan University, 2023, 48(1): 75-83. DOI: 10.13203/j.whugis20210084
    [4]WU Yuxiang, YAN Wei, KONG Deqing, ZHANG Hongbo, ZHU Xinying, XUE Xiping, DAI Shun, WANG Zan. Radio Telescope Center Point Calibration Method Using Reference Objects[J]. Geomatics and Information Science of Wuhan University, 2022, 47(5): 715-721. DOI: 10.13203/j.whugis20190447
    [5]WEI Erhu, REN Xiaobin, LIU Jingnan, LI Lianyan, NIE Guigen, LI Yanlin. Calculation of Lunar Libration Parameters Using VLBI Observations and Improvement of Lander Positioning and Velocity Measurement[J]. Geomatics and Information Science of Wuhan University, 2022, 47(4): 483-491. DOI: 10.13203/j.whugis20200311
    [6]FENG Haotong, SHU Fengchun, HE Xuan. Accuracy Analysis of Clock Offset Compensation of Shanghai Sheshan VLBI Station[J]. Geomatics and Information Science of Wuhan University, 2021, 46(8): 1148-1153. DOI: 10.13203/j.whugis20190053
    [7]LIU Shanhong, YAN Jianguo, YE Mao, LI Fei. Contributions of Chinese VLBI Network to the Low Degree Coefficients of the Jupiter Gravity Field[J]. Geomatics and Information Science of Wuhan University, 2020, 45(6): 862-869. DOI: 10.13203/j.whugis20190385
    [8]WEI Erhu, LIU Wenjie, WEI Jianan, JIN Shuanggen, LIU Jingnan. Estimation of Earth Rotation Parameters and ΔLOD with Combining VLBI and GPS Observations[J]. Geomatics and Information Science of Wuhan University, 2016, 41(1): 66-71,92. DOI: 10.13203/j.whugis20130435
    [9]WEI Erhu, ZHANG Qi. On Length of Day with 1985-2010 VLBI Observations[J]. Geomatics and Information Science of Wuhan University, 2012, 37(9): 1020-1023.
    [10]WEI Erhu, TIAN Xiaojing, LIU Jingnan, ZHANG Rui. Analysis of Length of Day with 2008-2009 VLBI Observations[J]. Geomatics and Information Science of Wuhan University, 2010, 35(9): 1009-1012.
  • Cited by

    Periodical cited type(1)

    1. 陈鸿鑫,马天霆,周阳,简彦辰,高犇,戴明露. 基于CNN-GAN数据增强网络的电厂锅炉管道温度压力及健康状态预测. 电子器件. 2023(06): 1593-1600 .

    Other cited types(5)

Catalog

    Article views (627) PDF downloads (103) Cited by(6)
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return