首页> 外文期刊>Mathematical Problems in Engineering >Predicting IGS RTS Corrections Using ARMA Neural Networks
【24h】

Predicting IGS RTS Corrections Using ARMA Neural Networks

机译:使用ARMA神经网络预测IGS RTS校正

获取原文
获取原文并翻译 | 示例
           

摘要

An autoregressive moving average neural network (ARMANN) model is applied to predict IGS real time service corrections. ARMA coefficients are determined by applying a neural network to IGS02 orbit/clock corrections. Other than the ARMANN, the polynomial and ARMA models are tested for comparison. An optimal order of each model is determined by fitting the model to the correction data. The data fitting period for training the models is 60 min. and the prediction period is 30 min. The polynomial model is good for the fitting but bad for the prediction. The ARMA and ARMANN have a similar level of accuracies, but the RMS error of the ARMANN is smaller than that of the ARMA. The RMS error of the ARMANN is 0.046 m for the 3D orbit correction and 0.070 m for the clock correction. The difference between the ARMA and ARMANN models becomes significant as the prediction time is increased.
机译:将自回归移动平均神经网络(ARMANN)模型应用于预测IGS实时服务校正。通过将神经网络应用于IGS02轨道/时钟校正来确定ARMA系数。除ARMANN之外,还对多项式和ARMA模型进行了比较测试。通过将模型拟合到校正数据来确定每个模型的最佳顺序。训练模型的数据拟合时间为60分钟。预测期为30分钟。多项式模型适合拟合,但不利于预测。 ARMA和ARMANN的精度水平相似,但是ARMANN的RMS误差小于ARMA的RMS误差。 ARMANN的RMS误差对于3D轨道校正为0.046 m,对于时钟校正为0.070 m。随着预测时间的增加,ARMA和ARMANN模型之间的差异变得很明显。

著录项

  • 来源
    《Mathematical Problems in Engineering》 |2015年第11期|851761.1-851761.11|共11页
  • 作者

    Kim Mingyu; Kim Jeongrae;

  • 作者单位

    Korea Aerosp Univ, Sch Aerosp & Mech Engn, Goyang City 412791, South Korea.;

    Korea Aerosp Univ, Sch Aerosp & Mech Engn, Goyang City 412791, South Korea.;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号