基于LightGBM的卫星飞轮温度预测

朱家熙; 刘玉荣

doi:10.11728/cjss2021.03.491

基于LightGBM的卫星飞轮温度预测

doi: 10.11728/cjss2021.03.491

朱家熙^1,2,
刘玉荣²

1. 中国科学院大学北京 100049;
2. 中国科学院国家空间科学中心北京 100190

基金项目:

空间科学先导专项科学卫星任务运控技术（XDA15040100）和科学卫星在轨运行项目（Y62211AH5S）共同资助

详细信息

作者简介:
朱家熙,E-mail:448920310@qq.com

中图分类号: V324
计量
- 文章访问数: 450
- HTML全文浏览量: 83
- PDF下载量: 29
- 被引次数: 0
出版历程
- 收稿日期: 2019-11-12
- 修回日期: 2020-06-10
- 刊出日期: 2021-05-15

Temperature Prediction of Satellite Flywheel Based on LightGBM

ZHU Jiaxi^1,2,
LIU Yurong²

1. University of Chinese Academy of Sciences, Beijing 100049;
2. National Space Science Center, Chinese Academy of Sciences, Beijing 100190

摘要

摘要: 为保障卫星的正常在轨运行，地面系统需要对卫星运行状态进行监控预警，其中对卫星各系统的温度监控尤为重要.温度不仅直接反映卫星系统的健康状态，更会对系统器件的性能和寿命造成影响.飞轮作为卫星姿态控制系统的重要组件，其温度变化是识别姿态控制系统状态的重要信息.卫星飞轮温度的预测与预警对卫星在轨稳定运行具有重要意义.本文基于某在轨卫星遥测数据，结合空间环境数据，应用LightGBM机器学习框架研究建立梯度提升决策树模型，对卫星飞轮温度进行预测.经与实际遥测温度值进行对比验证，预测精度可以满足对卫星飞轮温度的监视需求.研究结果可应用于地面系统，对卫星姿态控制系统可能发生的温度异常进行预警，使地面运控人员能够提前规避风险，保障卫星的安全在轨运行.
- 温度预测 /
- 空间环境 /
- 卫星数据 /
- 机器学习
Abstract: In order to ensure the stable operation of satellites, it is important for the ground system to monitor and predict the satellite state, especially the monitoring of flywheel temperature. As an important component of attitude control system of a satellite, the temperature of flywheel is important to identify the state of the system. The prediction of flywheel temperature is of great significance to the stable operation of satellites in orbit. In this paper, based on the LightGBM machine learning framework, a gradient boosting decision tree model is established by using spatial environmental data and in-orbit telemetry data of a satellite, to predict the temperature change of satellite flywheel. By comparing with the actual flywheel temperature, the prediction accuracy can meet the monitoring requirement of satellite flywheel temperature. This model can be applied to warn the ground system the possible temperature anomalies of attitude control system, so that controllers can avoid risks ahead of time and ensure the safe operation of satellites. The research results have certain universality for other satellite flywheel systems.
- Temperature prediction /
- Spatial environment /
- Satellite data /
- Machine learning

HTML全文

参考文献(13)

[1]	ZHANG Guoyun, WANG Dapeng. Method of lifetime prolongation for satellite reaction flywheel[J]. Spacecraft Eng., 2019, 28(1):42-47(张国云, 王大鹏. 一种卫星反作用飞轮延寿方法[J]. 航天器工程, 2019, 28(1):42-47)
[2]	WANG Hui, Wu Junfeng. Design of reaction flywheel systems for small satellites[J]. Opt. Precision Eng., 2014, 22(2):331-337(王辉, 武俊峰. 小卫星用反作用飞轮系统设计[J]. 光学精密工程, 2014, 22(2):331-337)
[3]	XU Fuxiang. An Introduction to Satellite Engineering[M]. Beijing: Astronautic Publishing House, 2003: 341-346(徐福祥. 卫星工程概论[M]. 北京: 宇航出版社, 2003: 341-346)
[4]	WANG Chune, FANG Jiancheng. Thermal design method and experimental research of magnetically suspended reaction flywheel[J]. Acta Aeronaut. Astron. Sin., 2011, 32(4):598-607(王春娥, 房建成. 磁悬浮反作用飞轮热设计方法与实验研究[J]. 航空学报, 2011, 32(4):598-607)
[5]	ZHU Xi, GUO Gan. Particle swarm optimization algorithm of spacecraft thermal balance test temperature prediction[J]. J. Astronaut., 2016, 37(11):1378-1383(朱熙, 郭赣. 航天器热平衡温度预测的粒子群算法[J]. 宇航学报, 2016, 37(11):1378-1383)
[6]	ZHANG Xudong, LI Yunze. Temperature prediction for nano satellite on orbit based on BP neural network[J]. J. Beijing Univ. Aeronaut. Astron., 2008, 34(12):1423-1427(张旭东, 李运泽. 基于BP神经网络的纳卫星轨道温度预测[J]. 北京: 北京航空航天大学学报, 2008, 34(12):1423-1427)
[7]	XU Fangzhou, SONG Xianfeng. A time series prediction model of Ionosphere Ion Temperature(Ti) based on DEMETER satellite dataset[J]. Remote Sens. Inform., 2012, 2:25-30(徐方舟, 宋现锋. 基于DEMETER卫星观测数据的电离层离子温度时间序列预测模型[J]. 遥感信息, 2012, 2:25-30)
[8]	BULUT M, SOZBIR N. Prediction of the solar array temperatures of geostationary earth orbit satellite by using analytical methods[C]//9th International Conference on Recent Advances in Space Technologies. New York: IEEE, 2019:369-372
[9]	GARZÓN A, VILLANUEVA Y A. Thermal analysis of satellite Libertad 2: a guide to CubeSat temperature prediction[J]. J. Aeros. Technol. Manag., 2018, 10:4918-4926
[10]	LIU Yongwei, MENG Lingxin. The application of Nair verification method in valuation practice[J]. Appraisal J. China, 2005, 11:156-163(刘永伟, 孟灵新. 奈尔检验法在评估中的应用[J]. 中国资产评估, 2005, 11:156-163)
[11]	FRIEDMAN J H. Greedy function approximation: a gradient boosting machine[J]. Ann. Statist., 2001, 29(5): 1189-1232
[12]	ZHENG Kaiwen, YANG Chao. Research on short-term load prediction based on gradient boosting decision tree[J]. Guizhou Electr. Power Technol., 2017, 20(2):82-90(郑凯文, 杨超. 基于迭代决策树短期负荷预测研究[J]. 贵州电力技术, 2017, 20(2):82-90)
[13]	HAN Qidi, ZHANG Xiaotong. Lithology identification technology based on gradient boosting decision tree algorithm[J]. Bull. Mineral. Petrol. Geochem., 2018, 37(6):1173-1180(韩启迪, 张小桐. 基于梯度提升决策树算法的岩性识别技术[J]. 矿物岩石地球化学通报, 2018, 37(6):1173-1180)