在卫星钟源无法与地面钟源进行实时比对的时段中，准确预报卫星钟差对于维持卫星的稳定运行具有重要意义。针对卫星钟差的中短期预报问题，选择多项式模型对钟差进行建模分析，设计了一种基于滑动窗模型的正交迭代泛函网络算法。利用泛函网络的非线性学习能力对钟差预报模型进行拟合分析，采用正交函数作为泛函网络的基函数簇，并引入滑动窗思想来更新输入层元素进行迭代训练，获得较小的预报误差。分析表明，预报时间小于12 h 时，预报误差为0.2~0.5 ns，预报精度与IGU P精度相当；当预报时间为24 h 时，预报误差总体在1 ns，预报精度略次于IGU P 精度；当预报时间为1 个卫星周时，最大误差达130 ns，难以满足卫星运行对钟源的要求。研究表明：该算法适合于短期卫星钟差预报，不适合中长期钟差预报。
Accurate satellite clock error prediction is of vital importance for satellite stable operation when satellites' clocks are not able to compare with those on the ground. Aiming at the problem of intermediate and short-term clock error prediction, a polynomial model is chosen to predict the clock error, and an orthogonal iterative functional networks algorithm based on a sliding window model is designed, which takes advantage of the non-linear learning ability of functional networks to fit and analyze the clock error model. The analysis shows that when the prediction time is less than 12 h, the predicted errors are between 0.2 ns and 0.5 ns, which is equivalent to IGU P. When the prediction time is 24 h, the overall errors are around 1ns, which is slightly less than IGU P. When the prediction time is a satellite week, the maximum error may reach 130 ns, which does not meet the reqirement of the satellites. It is concluded that the algorithm of the paper is suited for the short-term clock error prediction but not the intermediate and longtime prediction.
[1] 刘强, 孙际哲, 陈西宏, 等. CPSO-LSSVM在自回归钟差预报中的应用分析[J]. 吉林大学学报: 工学版, 2014, 44(3): 807-811. Liu Qiang, Sun Jizhe, Chen Xihong, et al. Application analysis of CPSO-LSSVM algorithm in AR clock error prediction [J]. Journal of Jilin University: Engineering and Technology Edition, 2014, 44(3): 807-811.
[2] 季利鹏, 徐波, 高有涛. 泛函网络在导航卫星钟差中长期预报中的应用[J]. 天文学报, 2013, 54(2): 176-188. Ji Lipeng, Xu Bo, Gao Youtao. The application of functional network in medium-and long-term prediction of clock error of navigation satellite[J]. Acta Astronomica Sinica, 2013, 54(2): 176-188.
[3] 王颖, 徐波, 杨旭海. 一种利用泛函网络进行导航卫星钟差预报的方法研究[J]. 宇航学报, 2012, 33(10): 1401-1406. Wang Ying, Xu Bo, Yang Xuhai. Research on the navigation satellite clock error prediction using functional network[J]. Journal of Astronautics, 2012, 33(10): 1401-1406.
[4] Xu B, Wang Y, Yang X H. Navigation satellite clock error prediction based on functional network[J]. Neural Processing Letters, 2013, 38(2): 305-320.
[5] Xu B, Wang Y, Yang X H. A hybrid model for navigation satellite clock error prediction[J]. Computational Intelligence, 2013, 465: 307-316.
[6] Martinez F G, Waller P. GNSS clock prediction and integrity[C]// Proceedings of The 22nd European Frequency and Time Forum. France: IEEE, 2009: 1137-1142.
[7] Castillo E. Functional networks[J]. Neural Processing Letters, 1998, 7 (3): 151-159.
[8] Castillo E, Gutiérrez J M. Nonlinear time series modeling and prediction using functional networks. extracting information masked by chaos[J]. Physics Letters A, 1998, 244(1): 71-84.
[9] Castillo E, Gutiérrez J M, Cobo A, et al. A minimax method for learning functional networks[J]. Neural Processing Letters, 2000, 11(1): 39-49.
[10] Castillo E, Hadi A S, Lacruz B. Optimal transformations in multiple linear regression using functional networks[C]. Proceedings of Connectionist Models of Neurons, Learning Processes and Artificial Intelligence, 6th International Work-Conference on Artificial and Natural Neural Networks, IWANN 2001 Granada, Spain, June 13-15, 2001. doi: 10.1007/3-540-45720-8_36.
[11] 周永权, 焦李成. 层次泛函网络整体学习算法[J]. 计算机学报, 2005, 28(8): 1277-1286. Zhou Yongquan, Jiao Licheng. Universal learning algorithm of hierarchical function networks[J]. Chinese Journal of Computers, 2005, 28(8): 1277-1286.
[12] 周永权, 赵斌, 焦李成. 序列泛函网络模型及其学习算法与应用[J]. 计算机学报, 2008, 31(7): 1073-1081. Zhou Yongquan, Zhao Bin, Jiao Licheng. Serial function networks method and learning algorithm with applications[J]. Chinese Journal of Computers, 2008, 31(7): 1073-1081.
[13] Fallani F D V, Rodrigues F A, Costa L D F, et al. Multiple pathways analysis of brain functional networks from eeg signals an application to real data[J]. Brain Topogr, 2011, 23: 344-354.
[14] Castellanos N P, Leyva I, Buldú J M, et al. Principles of recovery from traumatic brain injury: reorganization of functional networks[J]. NeuroImage, 2011, 55: 1189-1199.
[15] 周永权, 何登旭, 焦李成, 等. 层次泛函网络学习算法及其在时间序列分析中的应用[J]. 数据采集与处理, 2006, 21(2): 123-127. Zhou Yongquan, He Dengxu, Jiao Licheng, et al. Learning algorithm of hierarchical functional network and its application in time series analysis[J]. Journal of Data Acquisition & Processing, 2006, 21(2): 123-127.
[16] 周永权, 吕咏梅, 申芸. 正交泛函网络函数逼近理论及算法[J]. 计算机科学, 2009, 36(1): 138-141. Zhou Yongquan, Lu Yongmei, Shen Yun. Orthogonal function network approximate theory and learning algorithm[J]. Computer Science, 2009, 36(1): 138-141.
