基于深度BP/ELMAN神经网络的山区GNSS高程转换精度分析  

Accurcy analysis of GNSS height transformation based on deep BP/ELMAN neural network in the mountains

作　　者：魏德宏[1] 禤键豪 杨嘉伟 张兴福[1] 余旭[1] WEI Dehong;XUAN Jianhao;YANG Jiawei;ZHANG Xingfu;YU Xu(Surving and Mapping Engineering Department,Guangdong University of Technology,Guangzhou 510006,China;College of Surveying and Geo-informatics,Tongji University,Shanghai 200092,China;Linyi Natural Resources and Planning Bureau,Linyi 276000,China)

机构地区：[1]广东工业大学测绘工程系,广东广州510006 [2]同济大学测绘与地理信息学院,上海200092 [3]临沂市自然资源和规划局,山东临沂276000

出　　处：《测绘通报》2023年第9期113-116,143,共5页Bulletin of Surveying and Mapping

基　　金：国家自然科学基金(42074003)。

摘　　要：将GNSS测量的大地高以较高精度转换为工程所需的正常高具有重要的实用价值。本文利用GSVS2017项目高精度的GNSS水准数据,分析了深度BP/ELMAN神经网络、广义回归神经网络(GRNN)、径向基函数神经网络(RBFNN)、支持向量机回归(SVR)、二次曲线拟合和曲面拟合等方法用于GNSS高程转换的精度。试验结果表明:①在训练点间距为50、30、15、10、5 km时,采用隐含层激励函数为ReLU的深度BP/ELMAN神经网络,其精度比GRNN、RBFNN、SVR、二次曲线拟合和曲面拟合方法高;②利用隐含层激励函数为ReLU的深度BP/ELMAN神经网络进行GNSS高程转换,5种训练点间距均可使90%以上检核点间的高差满足四等水准测量精度,75%以上满足三等水准测量精度要求,训练点间距为5 km时,55%以上的高差可达到二等水准测量精度要求。It is of great practical value to transform the GNSS geodetic height into the normal height with higher precision in the mountains.This paper uses the high-precision GNSS leveling data of the GSVS2017 project to analyze the accuracy of GNSS height transformation based on deep BP/ELMAN neural network,general regression neural network(GRNN),radial basis function neural network(RBFNN),support vector machine regression(SVR),quadratic curve fitting and surface fitting,etc.The results show that:①When the distance between training points is 50,30,15,10 and 5 km,the deep BP/ELMAN neural network with the hidden layer activation function ReLU can obtain higher precision results,and they are more accurate than GRNN,RBFNN,SVR,quadratic curve fitting and surface fitting.②The deep BP/ELMAN neural network with the hidden layer activation function ReLU are used for GNSS height transformation.Among the five kinds of training point spacing,more than 90%of the height difference can meet the fourth-order leveling accuracy,and more than 75%of height difference can meet the third-order leveling accuracy;when the distance between training points spacing is 5 km,more than 55%of the height difference can meet the second-order leveling accuracy.

关 键 词：深度学习 神经网络 GNSS高程转换 精度分析 

分 类 号：P224[天文地球—大地测量学与测量工程]