径向基函数神经网络在GPS卫星钟差预报中的应用

测绘学报 ›› 2014, Vol. 43 ›› Issue (8): 803-807.

径向基函数神经网络在GPS卫星钟差预报中的应用

王国成¹,柳林涛²,徐爱功³,苏晓庆²,梁星辉²

1. 中科院测量与地球物理研究所
2. 中国科学院测量与地球物理研究所
3. 辽宁工程技术大学

收稿日期:2014-01-06 修回日期:2014-05-12 出版日期:2014-08-20 发布日期:2014-08-27
通讯作者: 柳林涛 E-mail:llt@asch.whigg.ac.cn
基金资助:
现代大地测量及其地学应用的研究

The application of Radial basis function neural network in the GPS satellite clock bias prediction

Received:2014-01-06 Revised:2014-05-12 Online:2014-08-20 Published:2014-08-27

摘要/Abstract

摘要：

GPS卫星钟在空中很容易受到诸多因素的影响，导致其钟差行为很难用线性模型，二次多项式模型，灰色模型等现有模型进行描述和实现可靠的高精度预报。本文利用径向基函数神经网络对几颗GPS卫星钟差连续进行了五分钟、一小时和一天的预报，分别取得了均方根误差优于0.4ns，0.5ns和1ns的预报精度，证明了文中径向基网络结构在钟差预报方面的可靠性。

关键词: GPS卫星钟差, 径向基函数神经网络

Abstract:

For satellite atomic clocks can be easily influenced by various factors in space, the clock behaviour are not sufficiently described and achieved a reliable high-precision prediction by the existed model, such as a linear model, a quadratic polynomial model, grey model and so on. Radial basis function neural network was used to the continuous prediction of many GPS satellite clock bais with five minutes, one hour and one day in this paper, the root mean square error was better than 0.4ns, 0.5ns and 1ns, respectively, these prove the reliability of the radial basis network structure on the clock error forecasting in this paper.

中图分类号:

王国成柳林涛徐爱功苏晓庆梁星辉. 径向基函数神经网络在GPS卫星钟差预报中的应用[J]. 测绘学报, 2014, 43(8): 803-807.

参考文献

[1] 焦月，寇艳红. GPS卫星钟差分析、建模及仿真[J]. 中国科学：物理学力学天文学, 2011, 41(5): 596~601.
Jiao Yue, Kou YanHong. Analysis, modeling simulation of GPS satellite clock errors[J]. Scientia Sinica Phy, Mech & Astron, 2011, 41(5): 596~601.
[2] Senior K L, Ray J R and Beard R L 2008 Characterization of periodic variations in the GPS satellite clocks GPS Solut. 12 2 11~25.
[3] IGS http://igscb.jpl.nasa.gov/.
[4] Y J Heo, J Cho and M B heo. Improving prediction accuracy of GPS satellite clocks with preriodic variation behaviour[J]. Measurement Science and Technology, 2010, 21(7): 073001(8pp).
[5] F. Vernotte, J. Delporte, M. Brunet. Uncertainties of drift coefficients and extrapolation erros: application to clock error predicition[J]. Metrologia, 2001, 38, 325-342.
[6] David W. Allan. Characterization, Optimum Estimation, and Time Prediction of Precision Clocks[J]. IEEE Trans. Ultrason., Ferroelect., Freq. Contr., 1987, vol. 34(6), 647~653.
[7] D. W. Allan. Time and Frequency (Time-Domain) Characterization, Estimation, and Prediction of Precision Clocks and Oscillators. IEEE Trans. Ultrason., Ferroelect., Freq. Contr., 1987, vol. 34, pp. 647~654.
[8] 郑作亚，陈永奇、卢秀山. 灰色模型修正及其在实时GPS卫星钟差预报中的应用研究[J]. 天文学报, 2008, 49(3): 306~320.
ZHENG Zuo-ya, CHEN Yong-qi, LU Xiu-shan. An Improved Grey Model for the Prediction of Real-Time GPS Satellite Clock Bias[J]. ACTA ASTRONOMICA SINICA, 2008, 49(3): 306~320.
[9] 崔先强, 焦文海. 灰色系统模型在卫星钟差预报中的应用[J]. 武汉大学学报.信息科学版, 2005, vol.30. No.5 447~450.
CUI Xianqiang, JIAO Wenhai. Grey System Model for the Satellite Clokc Error Predicting[J]. Geomatics and Information Science of Wuhan University, 2005, vol.30. No.5 447~450.
[10] 朱祥伟，肖华等. 卫星钟差预报的Kalman算法及其性能分析[J]. 宇航学报. 2008, vol.29 (3): 966~970.
ZHU Xiang-wei, XIAO Hua, YONG Shao-wei, ZHUANG Zhao—wen. The Kalman Algorithm Used for Satellite Clock Ofset Prediction and Its Performance Analysis[J]. Joumal of Astronautic, 2008, vol.29(3): 966~970.
[11] Panfilo G and Tavella P. Atomic clock prediction based on stochastic differential equations[J]. Metrologia, 2008, 45(6): s108:s16.
[12] 黄观文，杨元喜，张勤. 开窗分类因子抗差自适应序贯平差用于卫星钟差参数估计与预报[J]. 测绘学报, 2011, 40(1): 15~21.
HUANG Guanwen, YANG Yuanxi, ZHANG Qin. Estimate and Predict Satellite Clock Error Using Adaptively Robust Sequential Adjustment with Classified Adaptive Factors Based on Opening Windows[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(1): 15~21.
[13] 戴文战，娄海川，杨爱萍. 非线性系统神经网络预测控制研究进展[J]. 控制理论与应用, 2009, 26(5): 521~530.
DAI Wen-zhan, LOU Hai-chuan, YANG Ai-ping. An overview of neural network predictive control for nonlinear systems[J]. Control Theory&Applications, 2009, 26(5): 521~530.
[14] SHARAD B, JAMES R W. Benefits of factorized RBF-based NMPC[J]. Computers and Chemical Engineering, 2002, 26(9):1185~1199.
[15] 郭承军，滕云龙. 神经网络在卫星钟差短期预报钟的应用研究[J]. 测绘科学, 2011, 36(4): 198~200.
GUO Cheng-jun, TENG Yun-long. Application of neural network in satellite clock bias short-term prediction[J]. Science of Surveying and Mapping, 2011, 36(4): 198~200.
[16] 从爽. 面向Matlab工具箱的神经网络理论与应用[M].合肥:中国科技大学出版社,1998.
Cong Shuang. Neural Network Theory and Applications with MATLAB Toolboxes[M]. He Fei: Science and Technology University of China Press, 1998.