首页 >

GNSS拒止下神经网络辅助的航天器集群协同导航

刘明, 吴姣()   

  1. 哈尔滨工业大学 微小型航天器快速设计与智能集群全国重点实验室,哈尔滨 150001
  • 收稿日期:2025-05-28 修回日期:2025-06-27 接受日期:2025-09-03 出版日期:2025-09-05 发布日期:2025-09-05
  • 通讯作者: 吴姣 E-mail:wn941030@163.com
  • 基金资助:
    国家自然科学基金基础科学中心项目(62188101);国家重点研发计划(2024YFF0504702);国家自然科学基金(62273116);思源人工智能科学与技术协同创新联盟基金(HTKJ2023SY502003)

Neural network-assisted cooperative navigation of spacecraft clusters under GNSS denials

Ming LIU, Jiao WU()   

  1. State Key Laboratory of Micro-Spacecraft Rapid Design and Intelligent Cluster,Harbin Institute of Technology,Harbin 150001,China
  • Received:2025-05-28 Revised:2025-06-27 Accepted:2025-09-03 Online:2025-09-05 Published:2025-09-05
  • Contact: Jiao WU E-mail:wn941030@163.com
  • Supported by:
    Science Center Program of National Natural Science Foundation of China(62188101);National Key Research and Development Program of China(2024YFF0504702);National Natural Science Foundation of China(62273116);SiYuan Collaborative Innovation Alliance of Artificial Intelligence Science and Technology(HTKJ2023SY502003)

摘要:

针对航天器集群在轨自主导航时全球卫星导航系统(GNSS)短期拒止情况下的导航发散问题,引入航天器间基于数据链(DL)的相对测距系统及神经网络辅助系统,提升拒止期间导航品质。考虑到惯性导航系统(INS)、GNSS及DL系统采样频率不同,构建具有即插即用特点的因子图(FG)架构,并采用置信传播规则动态融合INS/GNSS/DL多源测量信息,实现多航天器协同导航。为避免数据链测距信息解算时的误差放大,设计基于旋转矩阵的相对测距信息解算方法;设计基于惯性积分状态及历史测量残差的复合故障诊断环节,结合因子图即插即用特点,实现GNSS故障及DL故障的检测与隔离;此外,针对GNSS拒止情况,设计广义回归神经网络(GRNN)与Elman神经网络(ENN)组合的辅助系统,对历史时刻GNSS与INS导航数据之间的潜在关系进行拟合,并对缺失GNSS导航数据进行在线预测与补偿。将GNSS预测数据与INS/DL数据进一步融合,获得GNSS拒止情况下的组合导航结果。仿真结果表明,在所设计的基于因子图的协同框架下,组合使用基于数据链的相对测距信息及GRNN-ENN神经网络辅助系统能有效缓解GNSS拒止情况下的导航发散情况。

关键词: 航天器协同定位, 组合导航, 因子图, Elman神经网络, 置信传播

Abstract:

To address the problems of navigation dispersion in the Global Navigation Satellite System (GNSS) short-term denial scenario during the on-orbit autonomous navigation of spacecraft clusters, we introduce a Data-Link-based (DL) relative ranging system and a neural network auxiliary module to improve the navigation effect under GNSS denial. Considering the different sampling frequencies of INS, GNSS, and DL systems, this paper constructs the Factor Graph (FG) architecture, which has the feature of plug-and-play, and adopts the belief propagation rules to dynamically fuse the multi-source measurement information of INS/GNSS/DL, enabling spacecraft cooperative positioning. To avoid the error amplification when solving the ranging information of the data links, a relative ranging information solving method based on the rotation matrix is designed. A composite fault diagnosis mechanism based on the inertial integral state and the historical measurement residuals is designed, which together with the plug-and-play characteristics of the FG, enables detection and isolation of the GNSS faults and DL faults. Moreover, for the GNSS denial case, an auxiliary system combining General Regression Neural Network (GRNN) and Elman Neural Network (ENN) is designed to fit the potential relationship between GNSS and INS navigation data at historical moments and provide an online prediction and compensation of missed GNSS navigation data. The predicted GNSS data are further fused with the INS/DL data to obtain the combined navigation results under the GNSS denial case. The simulation results show that the introduction of datalink-based relative ranging information and the GRNN-ENN neural network-assisted system can effectively mitigate the navigation divergence in the GNSS denial case.

Key words: multi-spacecraft cooperative navigation, combined navigation, factor graph, Elman neural network, belief propagation

中图分类号: