基于MEA-BP神经网络的卫星钟差预报

doi:10.11947/j.AGCS.2020.20200002

摘要/Abstract

摘要： 卫星钟差是影响导航定位精度的重要因素之一，建立高精度的钟差预报模型对高精度定位有重要意义。针对常用模型卫星钟差在短期预报中随时间增加误差积累，以及传统BP神经网络不稳定，容易出现过拟合等问题，本文提出一种基于思维进化算法（MEA）优化的BP神经网络钟差预报模型和算法。首先对原始钟差数据进行一次差处理；然后利用思维进化算法对BP神经网络的初始权值和阈值进行优化，给出该模型进行钟差预报的具体步骤；选用IGS站提供的多天GPS精密钟差产品数据进行试验分析，使用GPS一天中前12 h数据建模，进行2、3、6和12 h的钟差预报。结果表明：利用MEA-BP模型得到的上述4种时段的预报精度分别优于0.36、0.38、0.62和1.56 ns，预报误差曲线变化起伏较小，说明新模型的预报性能优于3种传统模型，新模型在钟差预报短期预报中的实用性及稳定性是较佳的。

关键词: 卫星钟差, 一次差, 思维进化算法, BP神经网络, 钟差预报

Abstract: The satellite clock bias is one of the important factors that affect the accuracy of navigation and positioning, so establishing a high-precision clock bias prediction model is of great significance to high-precision positioning. Aiming at the problem that satellite clock bias error accumulates by common models over time in short-term prediction, and the easy overfitting and instability of the traditional BP neural network, this paper proposed a model and algorithm of clock bias prediction based on BP neural network optimized by the mind evolutionary algorithm(MEA). First, original clock bias data made once difference to obtain the corresponding once difference sequences. Then, the initial weights and thresholds of the BP neural network were optimized by the mind evolutionary algorithm, the specific steps of using this model for the clock bias prediction were given. The multi-day GPS precision clock bias product data provided by the IGS station is used for experimental analysis. The article used the GPS data for the first 12 h of the day for modeling were listed, and made short-term clock bias prediction within 2, 3, 6 and 12 h. The results showed that the above four periods of prediction precision obtained by using the MEA-BP model were better than 0.36, 0.38, 0.62 and 1.56 ns, respectively. The fluctuation of the prediction error curve was small, and the prediction performance of the new model was better than the three traditional models, which showed the new model is better in practicability and stability in the short-term prediction of clock bias.

Key words: satellite clock bias, once difference, mind evolutionary algorithm(MEA), BP neural network, clock bias prediction

中图分类号:

P228

吕栋, 欧吉坤, 于胜文. 基于MEA-BP神经网络的卫星钟差预报[J]. 测绘学报, 2020, 49(8): 993-1003.

LÜ Dong, OU Jikun, YU Shengwen. Prediction of the satellite clock bias based on MEA-BP neural network[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(8): 993-1003.

参考文献

[1] 杨元喜, 李晓燕. 微PNT与综合PNT[J]. 测绘学报, 2017, 46(10):1249-1254. DOI:10.11947/j.AGCS.2017.20170249. YANG Yuanxi, LI Xiaoyan. Micro-PNT and comprehensive PNT[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10):1249-1254. DOI:10.11947/j.AGCS.2017.20170249.
[2] 王宇谱. GNSS星载原子钟性能分析与卫星钟差建模预报研究[J]. 测绘学报, 2018, 47(7):1026. DOI:10.11947/j.AGCS.2018.20170467. WANG Yupu. Research on modeling and prediction of the satellite clock bias and performance evaluation of GNSS satellite clocks[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(7):1026. DOI:10.11947/j.AGCS.2018.20170467.
[3] YANG Yuanxi. Resilient PNT concept frame[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(3):1-7.
[4] 盛剑锋. 高频GNSS准实时钟差估计及其应用[D]. 武汉:中国地震局地震研究所, 2019. SHENG Jianfeng. Estimation and applications of the high frequency quasi-real-time GNSS clock[D]. Wuhan:Institute of Seismology, China Earthquake Administration, 2019.
[5] YANG Yuanxi, XU Yangyin, LI Jinlong, et al. Progress and performance evaluation of BeiDou global navigation satellite system:data analysis based on BDS-3 demonstration system[J]. Science China Earth Sciences, 2018, 61(5):614-624.
[6] HUANG Guanwen, ZHANG Qin, XU Guochang. Real-time clock offset prediction with an improved model[J]. GPS Solutions, 2014, 18(1):95-104.
[7] YANG H, XU C, GAO Y. Analysis of GPS satellite clock prediction performance with different update intervals and application to real-time PPP[J]. Survey Review, 2019, 51(364):43-52.
[8] ZHOU Haoyin, NI Kai, ZHOU Qian, et al. An SfM algorithm with good convergence that addresses outliers for realizing mono-SLAM[J]. IEEE Transactions on Industrial Informatics, 2016, 12(2):515-523.
[9] 李超, 党亚民, 谷守周. 灰色模型的GLONASS卫星钟差预报[J]. 导航定位学报, 2016, 4(4):24-29, 35. LI Chao, DANG Yamin, GU Shouzhou. Prediction of GLONASS satellite clock error based on grey model[J]. Journal of Navigation and Positioning, 2016, 4(4):24-29, 35.
[10] 艾青松, 徐天河, 孙大伟, 等. 顾及周期项误差和起点偏差修正的北斗卫星钟差预报[J]. 测绘学报, 2016, 45(S2):132-138. DOI:10.11947/j.AGCS.2016.F034. AI Qingsong, XU Tianhe, SUN Dawei, et al. The prediction of BeiDou satellite clock bias based on periodic term and starting point deviation correction[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(S2):132-138. DOI:10.11947/j.AGCS.2016.F034.
[11] XI Chao, CAI Chenglin, LI Simin, et al. Long-term clock bias prediction based on an ARMA model[J]. Chinese Astronomy and Astrophysics, 2014, 38(3):342-354.
[12] 宋会杰, 董绍武, 屈俐俐, 等. 基于Sage窗的自适应Kalman滤波用于钟差预报研究[J]. 仪器仪表学报, 2017, 38(7):1809-1816. SONG Huijie, DONG Shaowu, QU Lili, et al. Research on clock difference prediction using adaptive Kalman filter based on Sage window[J]. Chinese Journal of Scientific Instrument, 2017, 38(7):1809-1816.
[13] WANG Dongxia, GUO Rui, XIAO Shenghong, et al. Atomic clock performance and combined clock error prediction for the new generation of BeiDou navigation satellites[J]. Advances in Space Research, 2019, 63(9):2889-2898.
[14] LU Jicang, ZHANG Chao, ZHENG Yong, et al. Fusion-based satellite clock bias prediction considering characteristics and fitted residue[J]. Journal of Navigation, 2018, 71(4):955-970.
[15] 徐超, 李博, 刘军良, 等. 一种改进的高精度频率源钟差仿真方法[J]. 宇航学报, 2017, 38(9):998-1004. XU Chao, LI Bo, LIU Junliang, et al. A modified method for clock error simulation of high precision frequency source[J]. Journal of Astronautics, 2017, 38(9):998-1004.
[16] ZHU Jiangmiao, SUN Panpan, GAO Yuan, et al. Clock differences prediction algorithm based on EMD-SVM[J]. Chinese Journal of Electronics, 2018, 27(1):128-132.
[17] 王国成, 柳林涛, 徐爱功, 等. 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, 817. DOI:10.13485/j.cnki.11-2089.2014.0078. WANG Guocheng, LIU Lintao, XU Aigong, et al. The application of radial basis function neural network in the GPS satellite clock bias prediction[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(8):803-807, 817. DOI:10.13485/j.cnki.11-2089.2014.0078.
[18] WANG Yupu, LU Zhiping, QU Yunying, et al. Improving prediction performance of GPS satellite clock bias based on wavelet neural network[J]. GPS Solutions, 2017, 21(2):523-534.
[19] 雷雨, 赵丹宁, 蔡宏兵. 利用结构自适应极端学习机预报导航卫星钟差[J]. 武汉大学学报(信息科学版), 2018, 43(5):664-668, 718. LEI Yu, ZHAO Danning, CAI Hongbing. Prediction of navigation satellite clock offset by adaptive extreme learning machine[J]. Geomatics and Information Science of Wuhan University, 2018, 43(5):664-668, 718.
[20] LI Haojun, LIAO Xilin, LI Bofeng, et al. Modeling of the GPS satellite clock error and its performance evaluation in precise point positioning[J]. Advances in Space Research, 2018, 62(4):845-854.
[21] HUANG Guanwen, CUI Bobin, ZHANG Qin, et al. An improved predicted model for BDS ultra-rapid satellite clock offsets[J]. Remote Sensing, 2018, 10(2):60.
[22] HU Chao, WANG Qianxin, MIN Yanghai, et al. An improved model for BDS satellite ultra-rapid clock offset prediction based on BDS-2 and BDS-3 combined estimation[J]. Acta Geodaetica et Geophysica, 2019, 54(4):513-543.
[23] WANG Qianxin, HU Chao, ZHANG Kefei. A BDS-2/BDS-3 integrated method for ultra-rapid orbit determination with the aid of precise satellite clock offsets[J]. Remote Sensing, 2019, 11(15):1758.
[24] HAN Tao. Fractal behavior of BDS-2 satellite clock offsets and its application to real-time clock offsets prediction[J]. GPS Solutions, 2020, 24:35.
[25] 肖恭伟, 欧吉坤, 刘国林, 等. 基于改进的BP神经网络构建区域精密对流层延迟模型[J]. 地球物理学报, 2018, 61(8):3139-3148. XIAO Gongwei, OU Jikun, LIU Guolin, et al. Construction of a regional precise tropospheric delay model based on improved BP neural network[J]. Chinese Journal of Geophysics, 2018, 61(8):3139-3148.
[26] SUN Chengyi, SUN Yan, XIE Keming. Mind-evolution-based machine learning and applications[C]//Proceedings of the 3rd World Congress on Intelligent Control and Automation. Hefei, China:IEEE, 2000:112-117.
[27] WANG Wenxu, TANG Ruichun, LI Cheng, et al. A BP neural network model optimized by mind evolutionary algorithm for predicting the ocean wave heights[J]. Ocean Engineering, 2018, 162:98-107.
[28] WANG Zhenhua, MA Gengsheng, GONG Dianyao, et al. Application of mind evolutionary algorithm and artificial neural networks for prediction of profile and flatness in hot strip rolling process[J]. Neural Processing Letters, 2019, 50(3):2455-2479.
[29] 王宇谱, 吕志平, 崔阳, 等. 利用遗传小波神经网络预报导航卫星钟差[J]. 武汉大学学报(信息科学版), 2014, 39(7):809-814. WANG Yupu, LÜ Zhiping, CUI Yang, et al. Predicting navigation satellite clock bias using a genetic wavelet neural network[J]. Geomatics and Information Science of Wuhan University, 2014, 39(7):809-814.
[30] 王宇谱, 吕志平, 陈正生, 等. 卫星钟差预报的小波神经网络算法研究[J]. 测绘学报, 2013, 42(3):323-330. WANG Yupu, LÜ Zhiping, CHEN Zhengsheng, et al. Research on the algorithm of wavelet neural network to predict satellite clock bias[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(3):323-330.