宇航学报

宇航学报 ›› 2013, Vol. 34 ›› Issue (7): 926-931.doi: 10.3873/j.issn.1000-1328.2013.07.006

• 制导、导航与控制 • 上一篇    下一篇

基于BP神经网络的自主定轨自适应Kalman滤波算法

尚琳，刘国华，张锐，李国通   

  1. 1.上海微小卫星工程中心，上海 200050； 2.中科院上海微系统与信息技术研究所，上海 200050
  • 收稿日期:2012-09-18 修回日期:2012-11-26 出版日期:2013-07-15 发布日期:2013-07-25
  • 基金资助:

    上海市科学技术委员会课题（10DZ2291700）；上海市自然科学基金（11ZR1443500）

An Adaptive Kalman Filtering Algorithm for Autonomous Orbit Determination Based on BP Neural Network

SHANG Lin,  LIU Guo hua,  ZHANG Rui,  LI Guotong   

  1. 1.Shanghai Micro Satellite Engineering Center,  Shanghai  200050, China；
     2.Shanghai Institute of Micro System and Information Technology,  Shanghai  200050, China
  • Received:2012-09-18 Revised:2012-11-26 Online:2013-07-15 Published:2013-07-25

PDF

867

摘要：

针对Sage Husa自适应滤波方法存在的窗函数开窗大小选择问题，提出一种基于BP神经网络学习估计系统协方差矩阵的自适应Kalman滤波算法。该算法以Kalman滤波预测残差向量作为网络输入，通过网络分段离线学习确定预测残差向量与预测残差协方差矩阵间的非线性关系，自适应地估计Kalman滤波系统协方差矩阵。将其应用到自主定轨系统，仿真结果表明利用本文算法自主定轨60天星座平均URE误差小于1.9米，且能够快速跟踪到系统噪声的突变，较Kalman滤波方法和Sage Husa自适应滤波方法具有更好的性能。

关键词: BP神经网络, 自主定轨, 自适应Kalman滤波, 用户测距误差

Abstract:

In this paper, an adaptive covariance matrix estimation algorithm based on BP neural network learning is proposed to solve the window size selection problem in Sage Husa adaptive filtering way. The innovation vector derived from the Kalman filter (KF) is employed as the input to the BP neural network and the nonlinear function between the innovation vector and the innovation covariance matrix can be determined through learning of the network. The covariance matrix estimation algorithm proposed in this paper is applied to the autonomous orbit determination system. The simulation results show that the mean constellation URE of autonomous orbit determination will be within 1.9 meters in 60 days and it has better performance than the Sage Husa adaptive filtering in the estimation of the system covariance matrix of the autonomous orbit determination algorithm.

Key words: BP neural network; , Autonomous orbit determination, Adaptive Kalman filter, URE

中图分类号: