航空学报 > 2020, Vol. 41 Issue (4): 223391-223391   doi: 10.7527/S1000-6893.2019.23391

月球风化层钻取采样过程密实度分类研究

郑燕红1, 邓湘金1, 庞勇2, 金晟毅1, 姚猛1, 赵志晖1   

  1. 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 出版日期:2020-04-15 发布日期:2019-10-17
  • 通讯作者: 郑燕红 E-mail:zhengyhsince2018@hotmail.com
  • 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 Yanhong1, DENG Xiangjin1, PANG Yong2, JIN Shengyi1, YAO Meng1, ZHAO Zhihui1   

  1. 1. Beijing Institute of Space System and Engineering, Beijing 100094, China;
    2. Beijing Spacecrafts, Beijing 100094, China
  • Received:2019-08-19 Revised:2019-10-22 Online:2020-04-15 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。

关键词: 月球, 钻取采样, 月壤密实度, 循环神经网络, 在线分类

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.

Key words: moon, drilling, lunar soil relative density, recurrent neural network, online classification

中图分类号: