节点文献
GPS高程转换的神经元网络方法分析
The research on neural network model used fof GPS heigth conversion
【摘要】 GPS高程转换是GPS高程应用的关键问题之一 ,试图应用神经元网络方法来进行GPS高程的转换 ,并在网络的拓扑结构与网络结构的改进等方面作了分析 ,通过GPS高程转换的二次曲面法和神经元网络法进行了比较试验 ,结果表明了神经元网络转换GPS高程的可行性和可靠性 ,对于应用神经网络转换GPS高程具有实际的指导意义。
【Abstract】 Comparing with fitting method that simulates Geoid using quadric polynomial for conversion of GPS height, this paper further shows the feasibility of GPS height conversion by using artificial neural network. Theoretical and practical computations have shown that artificial neural network is suitable for GPS height conversion. At the same time, some problems, such as improving structure of BP network model are deeply investigated. Some conclusions the paper drown has the theoretical guiding function for the GPS trasformation using neural network.
【关键词】 神经网络;
GPS高程;
BP算法;
高程转换;
【Key words】 artificial neural network; GPS leveling, algorithm of BP; structure of network.;
【Key words】 artificial neural network; GPS leveling, algorithm of BP; structure of network.;
【基金】 国家自然科学基金资助项目 (4 0 1710 82 1)
- 【文献出处】 全球定位系统 ,Gnss World of China , 编辑部邮箱 ,2004年02期
- 【分类号】P228.4
- 【被引频次】21
- 【下载频次】153