基于EGM96模型的神经网络BP算法在GPS高程转换中的应用  

Conversion of GPS Height by the Method of Neural Networks Considering of EGM96

作　　者：刘帅[1] 朱建军[1] 赵伶俐[1] 

机构地区：[1]中南大学信息物理工程学院,湖南长沙410083

出　　处：《测绘与空间地理信息》2005年第5期104-106,共3页Geomatics & Spatial Information Technology

基　　金：湖南省自然科学基金项目资助(02JJY2065)

摘　　要：在一个测区内,从水准联测点上移走EGM96含有的高精度中长波部分后,把余下的高程异常通过BP神经网络进行模拟,最后再对数据进行恢复,使实验达到良好的结果。The EGM96 model and the method of neural networks used for transforming GPS height are introduced briefly in this paper. The processes take full advantages of the two methods and are divided into three steps： Firstly, the height abnormal values on the known points are removed by EGM96. Secondly, the remained values are calculated by the method of neural networks. Finally, resume the height values. A few practicable conclusions are received from the research.

关 键 词：GPS高程 EGM模型 神经网络 BP算法 

分 类 号：O157.5[理学—数学] P228.4[理学—基础数学]