中文核心期刊
CSCD来源期刊
中国科技核心期刊
RCCSE中国核心学术期刊

重庆交通大学学报(自然科学版) ›› 2012, Vol. 31 ›› Issue (4): 815-818.DOI: 10.3969/j.issn.1674-0696.2012.04.20

• • 上一篇    下一篇

基于神经网络的GPS 高程拟合方法优选及精度分析

强明1,郭春喜2,周红宇3   

  1. 1. 西安科技大学测绘科学与技术学院,陕西西安710054; 2. 陕西省测绘局大地测量数据处理中心,陕西西安710054; 3. 重庆交通大学土木建筑学院,重庆400074
  • 收稿日期:2011-11-22 修回日期:2011-11-24 出版日期:2012-08-15 发布日期:2015-03-12
  • 作者简介:强明( 1985—) ,男,宁夏中宁人,硕士研究生,主要从事大地水准面精化方面的研究。E-mail:qmgogojiayouqm@sina.com.

Optimization and Precision Evaluation with GPS Elevation Fitting Method Based on Neural Network

Qiang Ming1,Guo Chun-xi2,Zhou Hong-yu3   

  1. 1.College of Geomatics,Xi’an University of Science & Technology,Xi’an 710054,Shaanxi,China; 2.Geodetic Survey Data Processing Center,Shaanxi Bureau of Surveying & Mapping,Xi’an 710054,Shaanxi,China; 3.School of Civil Engineering & Architecture,Chongqing Jiaotong University,Chongqing 400074,China
  • Received:2011-11-22 Revised:2011-11-24 Online:2012-08-15 Published:2015-03-12

摘要: 针对现有的几种神经网络GPS高程拟合方法,讨论了利用遗传算法(GA)、粒子群算法(PSO)优化BP神经网 络权值和阀值的原理;结合分布较均匀、现势性较好的GPS和水准联测数据,试算了基于神经网络的GPS高程拟 合。拟合结果表明:基于PSO算法优化的BP神经网络的拟合精度优于GA算法,误差相对更小。

关键词: 遗传算法, BP神经网络, 径向基神经网络, 粒子群优化算法

Abstract: According to current elevation fitting methods of networks,the genetic algorithms( GA) and particle swarm optimization( PSO) methods were employed to optimization of the weights and threshold of BP neural networks; with evenly distributed GPS data,GPS elevation fitting based on neural network is calculated. The fitting results show that optimization of the BP neutral network by PSO is better than that by GA and the error is relatively small.

Key words: genetic algorithms( GA) , BP neural network, RBF, particle swarm optimization ( PSO)

中图分类号: