基于神经网络-高斯赫尔默特模型联合多点GNSS定位方法  

Joint Multi-Point GNSS Positioning Method Based on Neural Network-Gauss-Helmert Model

作　　者：林海飞 彭友志 夏玉国 何浩鹏 LIN Haifei;PENG Youzhi;XIA Yuguo;HE Haopeng(Key Laboratory of Earthquake Geodesy,CEA,40 Hongshance Road,Wuhan 430071,China;Wuhan Seismic Metrological Verification and Surveying Engineering Institute Co Ltd,40 Hongshance Road,Wuhan 430071,China)

机构地区：[1]中国地震局地震大地测量重点实验室,武汉市430071 [2]武汉地震计量检定与测量工程研究院有限公司,武汉市430071

出　　处：《大地测量与地球动力学》2025年第3期303-307,共5页Journal of Geodesy and Geodynamics

基　　金：湖北省自然科学基金(2021CFB515)。

摘　　要：为降低复杂环境下GNSS定位误差,提出一种联合高精度测站和距离交会精确估计定位点坐标的方法。该方法首先将观测方程构建为非线性高斯-赫尔默特模型,针对其中的非线性问题,引入反向传播(back-propagation,BP)神经网络进行辅助处理。与传统线性化方法相比,BP神经网络能够有效拟合复杂的非线性函数关系。仿真和实测结果表明,该方法能有效降低复杂环境对定位精度的影响,E、N、U方向定位精度分别提高78.1%、72.8%、79.2%。To reduce the positioning errors of global navigation satellite system(GNSS)in complex environments,we propose a method that combines high-precision points with distance intersection to accurately estimate the coordinates of an undetermined point.The observation equation is constructed as a nonlinear Gauss-Helmert model.To address the nonlinearity within this model,we introduce a back-propagation(BP)neural network for auxiliary processing.Compared with the traditional linearization methods,the BP neural network can effectively fit complex nonlinear functional relationships.The simulation experiments and actual measurement results show that this method can significantly reduce the impact of complex environments on positioning accuracy,and improve the positioning accuracy in E,N and U directions by 78.1%,72.8%,and 79.2%,respectively.

关 键 词：GNSS 复杂环境 高斯-赫尔模特模型 反向传播神经网络 误差估计 

分 类 号：P228[天文地球—大地测量学与测量工程]