基于SSA-ANFIS模型的BDS-3卫星钟差短期预报  

Short-Term Prediction of BDS-3 Satellite Clock BiasBased on SSA-ANFIS Model

作　　者：蔡成林 吴明杰 吕开慧 CAI Chenglin;WU Mingjie;L Kaihui(School of Automation and Electronic Information,Xiangtan University,North-Erhuan,Xiangtan 411105,China;School of Mathematics and Computational Science,Xiangtan University,North-Erhuan,Xiangtan 411105,China)

机构地区：[1]湘潭大学自动化与电子信息学院,湖南省湘潭市411105 [2]湘潭大学数学与计算科学学院,湖南省湘潭市411105

出　　处：《大地测量与地球动力学》2024年第9期926-931,共6页Journal of Geodesy and Geodynamics

基　　金：国家重点研发计划(2020YFA0713501)。

摘　　要：针对卫星钟差时间序列具有非线性和非平稳的特性,以及趋势分量与随机分量相互干扰可能会影响预报精度的问题,提出一种以奇异谱分析(singular spectrum analysis, SSA)为基础,融合自适应模糊神经网络(adaptive neuro-fuzzy inference system, ANFIS)的卫星钟差预报模型SSA-ANFIS。首先利用SSA对钟差一次差序列进行分解和重构,从而得到趋势项和残差项;然后,使用ANFIS对重构分量进行预报,并将预报结果叠加还原,得到最终预报钟差值;最后,通过实验对比SSA-ANFIS与GM、QP、LSTM和ANFIS模型的预报效果。结果表明,相较于LSTM和ANFIS模型,该模型预报精度分别提高25.7%~40.7%和39.4%~45.7%。In view of the non-linearity and non-stationary characteristics of satellite clock bias(SCB)time series,as well as the interference between trend and noise components that may affect the accuracy of prediction,this paper proposes a SCB prediction model(SSA-ANFIS)based on singular spectrum analysis(SSA)and adaptive neuro-fuzzy inference system(ANFIS).This paper first uses SSA to decompose and reconstruct the first-order difference sequence of clock bias,obtaining the trend component and the residual component.Then,it uses the ANFIS model to predict the reconstructed components,and superimposes and restores the predicted results to obtain the final predicted clock bias value.Finally,through experiments,this paper compares the proposed model with GM,QP,LSTM and ANFIS models.The results show that SSA-ANFIS model can effectively improve the prediction accuracy of the single model.Compared with the LSTM and ANFIS models,its prediction accuracy increased by 25.7%-40.7%and 39.4%-45.7%,respectively.

关 键 词：卫星钟差 奇异谱分析 自适应模糊神经网络模型 钟差预报 

分 类 号：P228[天文地球—大地测量学与测量工程]