Robust Gaussian Mixture Model for Maneuver Detection Using TLE Data

ZHANG Haoyue; ZHAO Chunmei; HE Zhengbin

doi:10.13203/j.whugis20230360

Turn off MathJax

Article Contents

Abstract

References

ZHANG Haoyue, ZHAO Chunmei, HE Zhengbin. Robust Gaussian Mixture Model for Maneuver Detection Using TLE Data[J]. Geomatics and Information Science of Wuhan University. DOI: 10.13203/j.whugis20230360

Citation:

PDF (1188 KB)

Robust Gaussian Mixture Model for Maneuver Detection Using TLE Data

1 School of Geomatics, Liaoning Technical University, Fuxin 123000, China;
2 Institute of Geodesy and Navigation Positioning, Chinese Academy of Surveying & Mapping, Beijing 100036, China;
3 Beijing Fangshan Satellite Laser Ranging National Observation and Research Station, Beijing 100036, China

More Information

Received Date: March 19, 2024
Available Online: April 08, 2024

Graphical Abstract

Abstract

Abstract

Objectives: The number of space objects has grown exponentially due to increased space activities, significantly increasing the collision risk in the Earth’s orbit. Proactive detection and accurate monitoring of changes in the orbits of space objects, including in-orbit collisions and orbital maneuvers of space objects, have become essential. The two-line element (TLE) set is a data format containing information on the movement of objects in the Earth’s orbit. It is the primary resource for monitoring space objects. However, frequent variations in the orbits can cause anomalies in the TLE data, potentially affecting the accuracy of maneuver detection. Therefore, we propose a new maneuver detection methodology that uses a robust Gaussian mixture model (RGMM) to perform probabilistic adjustment of the TLE. Methods: The method used the rate of change of TLE semi-major axis prediction error to detect maneuvers. The robustness of the model is improved by pruning the Gaussian mixture model (GMM) and constraining the a posteriori probability of suspicious data through the incorporation of a robust correction function in the parameter solving process. We compared the performance of the proposed approach for detecting the maneuver of a typical space object with the GMM. Results: The results show that: (1) The RGMM demonstrated greater stability and robustness to outliers in comparison to the GMM. It is effective in accurately modelling the probability distribution of the rate of change of TLE semi-major axis prediction error. (2) Maneuver detection experiments indicated that the RGMM outperformed the GMM. It had a 60.6% higher recall and 18% higher F1 score than the GMM. Conclusions: The appropriate processing of the anomalous data can improve the model’s performance for maneuver detection using TLE data with errors. RGMM can be used to analyze the movements of space objects and ensure greater safety in executing future complex space missions. We plan to improve the model’s performance in future research by incorporating more advanced algorithms.
- maneuver detection,
- two-line element,
- robust estimate,
- GMM

FullText(HTML)

References (34)

References

[1]	Public Catalog Object Count[EB/OL].[2023-09-15] . https://www.space-track.org/#/spaceOpsTempo
[2]	SANG J, LI B, LIU H. Orbital Covariance Propagation of Space Debris and Its Dynamic Calibration[J]. Orbital Covariance Propagation of Space Debris and Its Dynamic Calibration, 2018, 43(12):2139-2146.(桑吉章,李彬,刘宏康.空间碎片轨道协方差传播及其动态校正[J].武汉大学学报(信息科学版), 2018:2139-2146.)
[3]	SHAO Zhenfeng, CHEN Jinlong, WU Changzhi, QI Xiaofei. Communication, Navigation, and Remote Sensing Fusion on Real-Time Complex Environment Perception Services[J]. Geomatics and Information Science of Wuhan University, 2023, 48(7):1100-1105. (邵振峰,陈金龙,吴长枝,等.通导遥融合的复杂环境实时感知服务[J].武汉大学学报(信息科学版), 2023, 48(7):1100-1105)
[4]	雷祥旭,桑吉章,李振伟,等.低轨空间目标甚短弧初轨关联 [J].武汉大学学报(信息科学版),2020,45(10):1526-1532. LEI Xiangxu, SANG Jizhang, LI Zhenwei, et al. Association of Very-Short-Arc Angles Data for LEO Space Objects[J]. Geomatics and Information Science of Wuhan University,2020,45(10):1526-1532.
[5]	LIU lei. Researches on Orbital Maneuver Detection of Space Objects[D]. Wuhan University,2019.(刘磊.空间目标轨道机动探测研究[D].武汉大学, 2019.)
[6]	Greaves J A, Scheeres D J. Observation and Maneuver Detection for Cislunar Vehicles:Using Optical Measurements and the Optimal Control Based Estimator[J]. The Journal of the Astronautical Sciences, 2021, 68(4):826-854.
[7]	Zhou X, Qin T, Ji M, et al. A LSTM assisted orbit determination algorithm for spacecraft executing continuous maneuver[J]. Acta Astronautica, 2023, 204:568-582.
[8]	Qin Z, Zhang Q, Huang G, et al. BDS Orbit Maneuver Detection Based on Epoch-Updated Orbits Estimated by SRIF[J]. Remote Sensing, 2023, 15(10):2558.
[9]	Fan L, Tu R, Zhang R, et al. An orbit maneuver detection method based on orbital elements for BeiDou GEO and IGSO satellites[J]. Advances in Space Research, 2022, 69(10):3644-3654.
[10]	ZHAO Guangyu. Orbit Determination by Fitting Probability Distribution on Space Object Admissible Region Using Gaussian Mixed Model[D].Wuhan University,2022.(赵广宇.利用高斯混合模型拟合空间目标允许域概率分布的轨道确定[D].武汉大学,2022.)
[11]	Kelecy T, Hall D, Hamada K, et al. Satellite maneuver detection using Two-line Element (TLE) data[C]//Proceedings of the Advanced Maui Optical and Space Surveillance Technologies Conference. Maui, HA:Maui Economic Development Board (MEDB), 2007.
[12]	Patera R P. Space event detection method[J]. Journal of Spacecraft and Rockets, 2008, 45(3):554-559.
[13]	WANG Qingrui, ZOU Jiangwei, WU Wenzhen, et al.Orbital maneuver detection method of space target based on Neyman-Pearson criterion[J]. Chinese Space Science and Technology,2021,41(2):96-103.(王庆瑞,邹江威,吴文振,等.基于Neyman-Pearson准则的空间目标轨道机动检测方法[J].中国空间科学技术, 2021, 41(2):96-103.)
[14]	Song W D, Wang R L, Wang J. A simple and valid analysis method for orbit anomaly detection[J]. Advances in space research, 2012, 49(2):386-391.
[15]	YANG Xu, LIU Jing, WU Xiangbin, et al. New Method to Analyse the Orbital Abnormal of LEO Satellite Using TLE Data--Compositive Criterion[J]. Chinese Journal of Space Science,2011,31(02):223-228.(杨旭,刘静,吴相彬,等.利用TLE数据分析 LEO卫星轨道异常的新方法--综合判据法[J].空间科学学报,2011,31(02):223-228.)
[16]	Lemmens S, Krag H. Two-line-elements-based maneuver detection methods for satellites in low earth orbit[J]. Journal of Guidance, Control, and Dynamics, 2014, 37(3):860-868.
[17]	LIU Erjiang, YAN Ye, YANG Yueneng. An Approach of Spacecraft Orbital Anomaly Detection Based on TLE Data[C]//Sustainable development of space resources:Proceedings of the First China Space Safety Conference,2015:341-346.(刘二江,闫野,杨跃能.基于TLE数据的航天器轨道异常检测[C]//空天资源的可持续发展--第一届中国空天安全会议论文集,2015:341-346.)
[18]	Xu Xiaoli, Xiong Yongqing. Research on the Evolution Law of Space Target Orbit Prediction Error Based on Historical TLE[J]. Acta Astronomica Sinica,2019,60(04):28-40.(许晓丽,熊永清.基于历史TLE的空间目标轨道预报误差演化规律研究[J].天文学报,2019,60(04):28-40.)
[19]	Shen D, Sheaff C, Lu J, et al. Adaptive Markov inference game optimization (AMIGO) for rapid Discovery of satellite behaviors[C]// Sensors and Systems for Space Applications XII. SPIE, 2019, 11017:57.
[20]	Shen D, Sheaff C, Guo M, et al. Enhanced GANs for satellite behavior discovery[C]//Sensors and Systems for Space Applications XIII. SPIE, 2020, 11422:110-121.
[21]	Tariq S, Lee S, Shin Y, et al. Detecting anomalies in space using multivariate convolutional LSTM with mixtures of probabilistic PCA[C]//Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery&data mining. 2019:2123-2133.
[22]	Mortlock T, Kassas Z M. Assessing machine learning for LEO satellite orbit determination in simultaneous tracking and navigation[C]//2021 IEEE aerospace conference (50100). IEEE, 2021:1-8.
[23]	Wang Y, Bai X, Peng H, et al. Gaussian-Binary classification for resident space object maneuver detection[J]. Acta Astronautica, 2021, 187:438-446.
[24]	Wang D, Li F. A machine learning method for the orbit state classification of large LEO constellation satellites[J]. Advances in Space Research, 2023, 71(3):1644-1656.
[25]	Liu J, Liu L, Du J, et al. TLE outlier detection based on expectation maximization algorithm[J]. Advances in Space Research, 2021, 68(7):2695-2712.
[26]	XU Xinchao, LI Xujia, XU Yantian, et al. A Real-Time Cross-Lens Continuous Tracking Method for Vertical Mounted Cameras[J]. Geomatics and Information Science of Wuhan University, 2021, 46(8):1247-1258.(徐辛超,李旭佳,徐彦田,等.一种适合垂直镜头的实时跨镜连续跟踪方法[J].武汉大学学报(信息科学版), 2021, 46(8):1247-1258)
[27]	Legendre P, Deguine B, Garmier R, et al. Two line element accuracy assessment based on a mixture of Gaussian laws[C]//AIAA/AAS Astrodynamics Specialist Conference and Exhibit. 2006:6518.
[28]	Li Yangtao, Bao Tengfei, Li Tianyu. A robust real-time detection method for deepwater dam defects[J]. Geomatics and Information Science of Wuhan University.2023.(李扬涛,包腾飞,李田雨.深水大坝缺陷鲁棒实时检测方法[J].武汉大学学报(信息科学版). 2023)
[29]	PENG Fei, WANG Zhong, MENG Qingxu, et al. Application of EM Algorithm in Parameter Estimation of p-Norm Mixture Model[J]. Geomatics and Information Science of Wuhan University, 2022, 47(9):1432-1438.(彭飞,王中,孟庆旭,等. EM算法在p范混合模型参数估计中的应用[J].武汉大学学报(信息科学版), 2022, 47(9):1432-1438)
[30]	FANG Xing, HUANG Lixiong, ZENG Wenxian, WU Yun. On an Improved Iterative Reweighted Least Squares Algorithm in Robust Estimation[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(10):1301-1306.(方兴,黄李雄,曾文宪,等.稳健估计的一种改进迭代算法[J].测绘学报, 2018, 47(10):1301-1306)
[31]	ZHAO Ang, YANG Yuanxi, XU Yangyin, et al. A Method of Protection Level Reconstruction Based on Robust Estimation[J]. Geomatics and Information Science of Wuhan University,2021,46(1):96-102.(赵昂,杨元喜,许扬胤等.一种使用抗差估计的保护水平重构方法[J].武汉大学学报(信息科学版),2021,46(01):96-102.)
[32]	LI Tao, HUANG Hao, CHEN Lei. Method to detect satellite historical orbit maneuver based on fitting of prediction error distribution[J].Journal of National University of Defense Technology,2020,42(02):114-120.(李涛,黄昊,陈磊.利用预报误差分布拟合实现卫星历史轨道机动检测的方法[J].国防科技大学学报,2020,42(02):114-120.)
[33]	WANG Yanli, DONG Zhipeng, WANG Mi. Ulva polifera Detection Method for High Resolution Remote Sensing Images Based on Dual-path Convolutional Neural Networks[J]. Geomatics and Information Science of Wuhan University,2023.(王艳丽,董志鹏, 王密.基于双路卷积神经网络的高分辨率遥感影像浒苔检测方法[J].武汉大学学报(信息科学版), 2023)
[34]	LIU Jinghong, SANG Jizhang, LIU Hongkang.TLE Orbital Determination Based on Simplex Method[J]. Chinese Journal of Space Science,2020,40(06):1102-1108.(刘劲宏,桑吉章,刘宏康.基于单纯形法的TLE轨道确定[J].空间科学学报,2020,40(06):1102-1108.)

[1]	HUANG Li, GONG Zhipeng, LIU Fanfan, CHENG Qimin. Bus Passenger Flow Detection Model Based on Image Cross-Scale Feature Fusion and Data Augmentation[J]. Geomatics and Information Science of Wuhan University, 2024, 49(5): 700-708. DOI: 10.13203/j.whugis20220690
[2]	HOU Zhaoyang, LÜ Kaiyun, GONG Xunqiang, ZHI Junhao, WANG Nan. Remote Sensing Image Fusion Based on Low-Level Visual Features and PAPCNN in NSST Domain[J]. Geomatics and Information Science of Wuhan University, 2023, 48(6): 960-969. DOI: 10.13203/j.whugis20220168
[3]	GUO Chunxi, GUO Xinwei, NIE Jianliang, WANG Bin, LIU Xiaoyun, WANG Haitao. Establishment of Vertical Movement Model of Chinese Mainland by Fusion Result of Leveling and GNSS[J]. Geomatics and Information Science of Wuhan University, 2023, 48(4): 579-586. DOI: 10.13203/j.whugis20200167
[4]	TU Chao-hu, YI Yao-hua, WANG Kai-li, PENG Ji-bing, YIN Ai-guo. Adaptive Multi-level Feature Fusion for Scene Ancient Chinese Text Recognition[J]. Geomatics and Information Science of Wuhan University. DOI: 10.13203/j.whugis20230176
[5]	LIN Dong, QIN Zhiyuan, TONG Xiaochong, QIU Chunping, LI He. Objected-Based Structural Feature Extraction Method Using Spectral and Morphological Information[J]. Geomatics and Information Science of Wuhan University, 2018, 43(5): 704-710. DOI: 10.13203/j.whugis20150627
[6]	LIN Xueyuan. Two-Level Distributed Fusion Algorithm for Multisensor Integrated Navigation System[J]. Geomatics and Information Science of Wuhan University, 2012, 37(3): 274-277.
[7]	XU Kai, QIN Kun, DU Yi. Classification for Remote Sensing Data with Decision Level Fusion[J]. Geomatics and Information Science of Wuhan University, 2009, 34(7): 826-829.
[8]	ZHAO Yindi, ZHANG Liangpei, LI Pingxiang. A Texture Classification Algorithm Based on Feature Fusion[J]. Geomatics and Information Science of Wuhan University, 2006, 31(3): 278-281.
[9]	JIA Yonghong, LI Deren. An Approach of Classification Based on Pixel Level and Decision Level Fusion of Multi-source Images in Remote Sensing[J]. Geomatics and Information Science of Wuhan University, 2001, 26(5): 430-434.
[10]	Li Linhui, Wang Yu, Liu Yueyan, Li Lei, Huang Jincheng, Zhou Yi, Cao Songlin. A Fast Fusion Model for Multi-Source Heterogeneous Data Of Real Estate Based on Feature Similarity[J]. Geomatics and Information Science of Wuhan University. DOI: 10.13203/j.whugis20220742

Cited By

Get Citation

PDF

XML

Article views (107) PDF downloads (29)

Robust Gaussian Mixture Model for Maneuver Detection Using TLE Data

Abstract

References

Related Articles

Catalog

Related

Robust Gaussian Mixture Model for Maneuver Detection Using TLE Data

Abstract

References

Related Articles

Catalog

Related

Export File

Citation

Format

Content