固体力学与飞行器总体设计

月球风化层钻取采样过程密实度分类研究

  • 郑燕红 ,
  • 邓湘金 ,
  • 庞勇 ,
  • 金晟毅 ,
  • 姚猛 ,
  • 赵志晖
展开
  • 1. 北京空间飞行器总体设计部, 北京 100094;
    2. 北京卫星制造厂, 北京 100094

收稿日期: 2019-08-19

  修回日期: 2019-10-22

  网络出版日期: 2019-10-17

基金资助

国家探月工程重大科技专项

Research on classification of relative density in lunar regolith drilling

  • ZHENG Yanhong ,
  • DENG Xiangjin ,
  • PANG Yong ,
  • JIN Shengyi ,
  • YAO Meng ,
  • ZHAO Zhihui
Expand
  • 1. Beijing Institute of Space System and Engineering, Beijing 100094, China;
    2. Beijing Spacecrafts, Beijing 100094, China

Received date: 2019-08-19

  Revised date: 2019-10-22

  Online published: 2019-10-17

Supported by

China's Lunar Exploration Project

摘要

钻取采样是月球风化层土壤样品获取的重要方式,密实度是重要的风化层月壤原位特性,对钻进过程中的策略制定有重要影响。本文结合钻取采样过程特点,提出了通过采样机构的力、速度、电流、温度等传感器获取的瞬时信息感知月壤密实度的方法,利用深度学习方法构建一类适应于可变长度序列数据的门控型循环神经网络,实现钻进过程月壤密实度在线分类。研究表明,该分类方法在风化层钻进过程中月壤密实度感知滞后时间约为33 s,对未知序列数据识别正确率大于89.36%,具有较高的分类精度和泛化能力。

本文引用格式

郑燕红 , 邓湘金 , 庞勇 , 金晟毅 , 姚猛 , 赵志晖 . 月球风化层钻取采样过程密实度分类研究[J]. 航空学报, 2020 , 41(4) : 223391 -223391 . DOI: 10.7527/S1000-6893.2019.23391

Abstract

Drilling is an important approach to acquire samples from lunar regolith. The relative density is an in situ characteristic of lunar regolith and will influence the strategy of drilling process. According to the working principle of drilling, the perception scheme of lunar soil relative density is proposed with the instantaneous information derived from sensors of force, velocity, current, and temperature. Based on the deep learning method, a class of gated recurrent unit neural network is constructed for variable length data sequence. The network can achieve the online classification of relative density of lunar soil. The delay time for relative density perception is about 33 s and the correct ratio is higher than 89.36% to unknown data sequence, indicating that the method has high classification precision and generality.

参考文献

[1] 彭兢,黄昊,向开恒,等.月球无人采样返回任务概念设想[J].航天器工程, 2010, 19(5):99-104. PENG J, HUANG H, XIANG K H, et al. Conception design of a lunar robotic sampling and return mission[J]. Spacecraft Engineering, 2010, 19(5):99-104(in Chinese).
[2] LI F, MAO Y, YAN J G,et al. A simulation of the four-way lunar lander-orbiter tracking mode for the Chang'E-5 mission[J]. Advances in Space Research, 2016, 2016(57):2376-2384.
[3] KELLY T J. A review of the Apollo lunar module program and its lessons for future space missions[C]//AIAA Space Programs and Technologies Conference.Reston,VA:AIAA, 1990:1-7.
[4] ROBINSON M S, PLESCIA J B, JOLLIFF B L, et al. Soviet lunar sample return missions:Landing site identification and geologic context[J]. Planetary and Space Science, 2012, 69(2012):76-88.
[5] DJACHKOVA M V, LITVAK M L, MITROFANOV I G, et al. Selection of Luna-25 landing sites in the south polar region of the moon[J]. Solar System Research, 2017, 51(3):185-195.
[6] 郑燕红,邓湘金,赵志晖,等.地外天体采样任务特点及关键技术发展建议[J].探矿工程(岩土钻掘工程), 2014, 41(9):71-74. ZHENG Y H, DENG X J, ZHAO Z H, et al. The character and key technology suggestion of extraterrestrial sampling mission[J].Exploration Engineering (Rock&Soil Drilling and Tunneling), 2014, 41(9):71-74(in Chinese).
[7] NASA. National space exploration campaign report.[R].Washington, D.C.:NASA,2018.
[8] HEIKEN G H, VANIMAN D T, FRENCH B M. Lunar sourcebook a user's guide to the moon[M]. New York:Cambrige University Press,1991.
[9] 唐钧跃.基于可钻性在线辨识的月面钻取采样钻进规程研究[D].哈尔滨:哈尔滨工业大学,2014. TANG J Y. Research on drilling strategy of lunar drilling and coring based on real-time recognition of drillability[D].Harbin:Harbin Institute of Technology,2014(in Chinese).
[10] STATHAM S, HANAGUD S, RUZZENE M, et al. Design and validation of an LDV-Based structural health monitoring in drilling automation for mars exploration[C]//48th AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Confe4rence. Reston,VA:AIAA,2007:1-13.
[11] 王丽丽,刘志全,吴伟仁,等.月球钻取采样机构的钻杆结构与运动参数分析[J].航空学报,2016, 37(2):738-748. WANG L L, LIU Z Q, WU W R, et al. Analysis of drill stem structural and kinematic parameters of lunar drilling sampling mechanism[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(2):738-748(in Chinese).
[12] 邓宗全,田野,唐德威,等.用于地外星体探测的一种新结构取心钻头研究[J].机械工程学报,2013, 49(19):104-110. DENG Z Q, TIAN Y, TANG D W, et al. Research on new structure coring bit for extraterrestrial bodies exploration[J]. Journal of Mechanical Engineering, 2013, 49(19):104-110(in Chinese).
[13] 赖小明.月壤剖面模拟及其钻进负载特性研究[D].长沙:国防科技大学,2016:68-69. LAI X M. The cross-section simulant of lunar regolith and research on drilling load feature[D].Changsha:National University of Defense Technology, 2016:68-69(in Chinese).
[14] 庞勇,冯亚杰,孙启臣,等.月壤大颗粒对钻进力载影响的仿真及实验研究[J].北京大学学报(自然科学版),2019, 55(3):397-403. PANG Y, FENG Y J, SUN Q C, et al. Simulation and experimental study on the effect of large granular rocks in lunar soil on drilling load[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2019, 55(3):397-403(in Chinese).
[15] LAMBE T W, WHITMAN R V. Soil mechanics[M]. New York:John Wiley&Sons, 1969.
[16] 郑燕红,邓湘金,姚猛,等.一类月面钻进采样机构的鲁棒控制[J].空间控制技术与应用,2014,40(5):36-41. ZHENG Y H, DENG X J, YAO M, et al. Robust control for a class of lunar drill sampling mechanism[J]. Aero-space Control and Application,2014, 40(5):36-41(in Chinese).
[17] 贾阳,申振荣,党兆龙,等.模拟月壤研究及其在月球探测工程中的应用[J].航天器环境工程,2014,31(3):241-247. JIA Y, SHENG Z R, DANG Z L, et al. Lunar soil simulant and its engineering application in lunar exploration program[J].Spacecraft Environment Engineering,2014, 31(3):241-247(in Chinese).
[18] 邹猛,李建桥,何玲,等.不同粒径分布模拟月壤承压特性试验研究[J].航空学报,2012,33(12):2338-2345. ZOU M, LI J Q, HE L, et al. Experiment study on the pressure-sinkage characteristic of the simulant lunar regolith with different particle size distribution[J]. Acta Aeronautica et Astronautica Sinica, 2012,33(12):2338-2345(in Chinese).
[19] GRAVES A. Supervised sequence labeling with recurrent neural networks[M]. Berlin Heidelberg:Springer-Verlag, 2012.
[20] 王鑫,吴际,刘超,等.基于LSTM循环神经网络的故障时间序列预测[J].北京航空航天大学学报,2018, 44(4):772-784. WANG X, WU J, LIU C, et al. Exploring LSTM based recurrent neural network for failure time series prediction[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(4):772-784(in Chinese).
[21] LIPTON Z C, BERKOWITZ J. A critical review of recurrent neural networks for sequence learning[J]. Computer Science, 2015:23-30.
[22] DEY R, SALEM F M. Gate-variants of gated recurrent unit (GRU) neural networks[C]//Circuits and Systems, 2017 IEEE 60th International Midwest Symposium. Piscataway,NJ:IEEE Press,2017.
[23] GOODFELLOW I, BENGIO Y, COURVILLE A. Deep learning[M]. Massachusetts:MIT Press, 2016:203-218.
[24] 石叶楠,郑国磊.三种用于加工特征识别的神经网络方法综述[J].航空学报,2019, 40(9):022840. SHI Y N, ZHENG G L. A review of three neural network methods for manufacturing feature recognition[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(9):022840(in Chinese).
文章导航

/