| 多种方法在似大地水准面拟合中的应用 |
| |
| 引用本文： | 刘庆元,黄书捷,郝立良,朱三昱.多种方法在似大地水准面拟合中的应用[J].全球定位系统,2014(3):62-66. |
| |
| 作者姓名： | 刘庆元 黄书捷 郝立良 朱三昱 |
| |
| 作者单位： | 中南大学地球科学与信息物理学院,湖南长沙410083 |
| |
| 摘 要： | 文主要研究了二次曲面，多面函数，BP神经网络以及改进的BP神经网络在似大地水准面拟合中的应用。针对BP神经网络收敛速度慢，容易陷入极小值的缺点，提出了利用粒子群算法的全局寻优的特点对其进行改进，通过对实验数据进行拟合，分析比较了不同算法的优缺点。由实验结果可以看出：改进后的神经网络很大程度上减少了训练次数，缩短了收敛的时间，并且提高了精度，验证了改进算法的有效性。
|
| 关 键 词： | 二次曲面 多面函数 BP神经网络 粒子群算法 似大地水准面 |
The Application of Various Methods in Geoid Fitting |
| |
| LIU Qingyuan,HUANG Shujie,HAO Liliang,ZHU Sanyu.The Application of Various Methods in Geoid Fitting[J].Gnss World of China,2014(3):62-66. |
| |
| Authors: | LIU Qingyuan HUANG Shujie HAO Liliang ZHU Sanyu |
| |
| Institution: | (School of Geoscience and Info-Physics, Central South University, Changsha Hunan 410083, China) |
| |
| Abstract: | T his paper studies the application of the quadratic surface ,multi-faceted func-tion ,BP neural network ,and improved BP neural network in geoid fitting .Because of the shortcomings of BP neural network ,such as slow convergence rate and falling into the mini-mum value easily ,this paper proposes that the global optimization features of particle swarm can be used to overcome the shortcomings .By fitting the experimental data ,this paper ana-lyzes and compares the advantages and disadvantages of different algorithms .T he experimen-tal results shows that the improved neural network has considerably reduced the number of training and short the time of convergence and increasing accuracy ,verify the effectiveness of the improved algorithm . |
| |
| Keywords: | Quadratic surface multi-faceted function BP neural network particle swarm optimization quasigeoid |
| 本文献已被 维普 等数据库收录！ |
