Correction of Atmospheric Model Through Data Mining With Historical Data of Two-Line Element

被引:4
作者
Bai, Xue [1 ]
Liao, Chuan [2 ]
Xu, Ming [1 ]
Zheng, Yaru [1 ]
机构
[1] Beihang Univ, Sch Astronaut, Beijing 100191, Peoples R China
[2] China Elect Technol Grp Corp, Res Inst 10, Chengdu 610036, Peoples R China
基金
中国国家自然科学基金;
关键词
Data mining; atmospheric mass density model; random forest; artificial neural network; support vector machine; two-line element; MACHINE; ACCURACY;
D O I
10.1109/ACCESS.2020.3007705
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The existing atmospheric mass density models (AMDM) would produce considerable errors in orbital prediction for Low Earth Orbit (LEO) satellites. In order to reduce these errors and correct the AMDM, this paper presents methods based on data mining with historical data of two-line element (TLE). Starting from a typical LEO satellite, TIANHUI, two orbital dynamical models are firstly proposed as the simulation environment to generate training data. The historical TLE data are regarded as actual space environment and used to generate application data. Secondly, three data mining methods, Random Forest (RF), Artificial Neural Network (ANN) and Support Vector Machine (SVM), are combined with the training data to investigate their feasibility in recovering the known deviation of AMDM under simulation environment. Training results show that RF displays the best performance and achieves the accuracy of 99.99%, while the other two methods only achieve 86.83% and 71.90% respectively. Thirdly, under the actual space environment, this paper uses new training and application data to research the ability of the three methods in recovering the unknown deviation of the AMDM and improve the accuracy of orbital prediction. Numerical results are evidential to the accuracy of the proposed methods based on data mining. It is concluded that the capabilities of the data mining for correction for the atmospheric model are very promising, with great potential to advance practical applications on on-orbit propagation.
引用
收藏
页码:123272 / 123286
页数:15
相关论文
共 50 条
[41]   Refinement of structural heuristics for model checking of concurrent programs through data mining [J].
Milewicz, Reed ;
Pirkelbauer, Peter .
COMPUTER LANGUAGES SYSTEMS & STRUCTURES, 2017, 47 :170-188
[42]   Hybrid model approach in data mining [J].
Bakirarar, Batuhan ;
Cosgun, Erdal ;
Elhan, Atilla Halil .
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2024, 53 (10) :4998-5007
[43]   Data mining model and algorithm in IDS [J].
Huang, TS ;
Xiong, P ;
Zhu, TQ .
APOC 2003: ASIA-PACIFIC OPTICAL AND WIRELESS COMMUNICATIONS; NETWORK ARCHITECTURES, MANAGEMENT, AND APPLICATIONS, PTS 1 AND 2, 2003, 5282 :570-576
[44]   A proximate dynamics model for data mining [J].
Yin, Yunfei .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (06) :9819-9833
[45]   Data mining for hierarchical model creation [J].
Youngblood, G. Michael ;
Cook, Diane J. .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2007, 37 (04) :561-572
[46]   A Generalized Model for Predictive Data Mining [J].
James V. Hansen ;
James B. McDonald .
Information Systems Frontiers, 2002, 4 :179-186
[47]   A generalized model for predictive data mining [J].
Hansen, JV ;
McDonald, JB .
INFORMATION SYSTEMS FRONTIERS, 2002, 4 (02) :179-186
[48]   A Data Mining Model in Knowledge Grid [J].
Huang, Feixue ;
Li, Zhijie ;
Sun, Xiaoli .
2008 4TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, NETWORKING AND MOBILE COMPUTING, VOLS 1-31, 2008, :5589-+
[49]   Research On Response Model Of Data Mining [J].
Li, Sheng ;
He, Lili ;
Shao, Binfei .
2014 IEEE 17th International Conference on Computational Science and Engineering (CSE), 2014, :793-796
[50]   Sports result prediction using data mining techniques in comparison with base line model [J].
Praphula Kumar Jain ;
Waris Quamer ;
Rajendra Pamula .
OPSEARCH, 2021, 58 :54-70