基于灰狼算法优化BP神经网络的GNSS高程拟合
GNSS elevation fitting based on grey wolf algorithm optimized BP neural network
闫少霞1
作者信息
- 1. 广州南方测绘科技股份有限公司,广东 广州 510000
- 折叠
摘要
为了提高GNSS高程拟合精度,提出了一种基于灰狼算法优化BP神经网络的GNSS高程拟合方法.采用GWO算法对BP神经网络的初始阈值和权值进行优化,建立了基于GWO-BP神经网络的GNSS高程拟合模型.采用工程实例进行仿真分析,并与其他GNSS拟合方法进行对比,结果表明,所提GNSS高程拟合方法的拟合残差更小,稳定性更好,有利于提高GNSS高程拟合精度,为GNSS高程拟合提供了一种新方法.
Abstract
In order to improve the accuracy of GNSS elevation fitting,a GNSS elevation fitting method based on grey wolf algorithm optimized BP neural network is proposed.The GWO algorithm was used to optimize the initial threshold and weight of the BP neural network,and a GNSS elevation fitting model based on the GWO-BP neural network was established.After using engineering examples for simulation analysis and comparing with other GNSS fitting methods,the results show that the proposed GNSS elevation fitting method has smaller fitting residuals and higher stability,which is conducive to improving the accuracy of GNSS elevation fitting and provides a new method for GNSS elevation fitting.
关键词
高程拟合/灰狼优化算法/BP神经网络Key words
elevation fitting/grey wolf optimization algorithm/BP neural network引用本文复制引用
基金项目
陆海一体化北斗三号精密定位服务与示范应用项目(2023B1111050013)
出版年
2024
NETL
NSTL
万方数据