| 基于神经网络的似大地水准面模型精化方法研究 |
| |
| 引用本文： | 杨小青,胡伍生.基于神经网络的似大地水准面模型精化方法研究[J].测绘工程,2008,17(4):8-11. |
| |
| 作者姓名： | 杨小青 胡伍生 |
| |
| 作者单位： | 东南大学交通学院,江苏,南京,210096;东南大学交通学院,江苏,南京,210096 |
| |
| 摘 要： | 似大地水准面的精化与高程异常的求解是同一个概念，为提高似大地水准面精化的精度，采用格网＋神经网络方法，借助神经网络BP方法，建立高程异常与坐标之间的函数关系；用训练好的神经网络模型和固定间隔的格网，建立格网模型；在已建好的格网模型中，内插出给定点的高程异常值。结合江苏省C级GPS水准网进行试验，拟合效果有明显的改进，克服了目前研究中存在的问题。
|
| 关 键 词： | GPS高程 正常高 似大地水准面 BP神经网络 格网 |
Research on the measures of accurating quasi geoid model based on Neural Network |
| |
| YANG Xiao-qing,HU Wu-sheng.Research on the measures of accurating quasi geoid model based on Neural Network[J].Engineering of Surveying and Mapping,2008,17(4):8-11. |
| |
| Authors: | YANG Xiao-qing HU Wu-sheng |
| |
| Institution: | YANG Xiao-qing, HU Wu-sheng (School of Transportation, Southeast university, Nanjing 210096, China) |
| |
| Abstract: | Refinement of quasi geoid is the same conception as solution of undulation. In order to improve the accuracy of quasi geoid refined, the process of applying a Back-Propagation Artifical Neural Network, establish the functional relationgship between the point＇s plane coordinates and its undulation using the BP ANN, develop a grid model with a fixed grid interval and the trained BP ANN, develop an undulation δ interpolation to estimate a specific point＇s undulation using the generated grid model. GPS leveling network of Jiangsu can be used to conduct test, the measure overcomes some difficulties in research presently and improves the effect of account. |
| |
| Keywords: | GPS height normal height quasi geoid Back-Propagation Artifical Neural Network grid |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
