现代信息科技2025，Vol.9Issue(17)：38-44,7.DOI:10.19850/j.cnki.2096-4706.2025.17.008
基于多层感知器神经网络的单频观测伪距精度优化研究
Research on Pseudo-range Accuracy Optimization of Single-frequency Observation Based on Multi-layer Perceptron Neural Network
摘要
Abstract
Aiming at the problem that the positioning accuracy of single-frequency receiver is limited due to ionospheric delay,the Multi-Layer Perceptron(MLP)neural network is used to predict the ionospheric delay to improve the pseudo-range accuracy of single-frequency observation.The observation data and broadcast ephemeris files of IGS data center of Wuhan University are collected,and the MLP neural network model is constructed after preprocessing.The model takes the pseudo-range of single-frequency observation and its related characteristics as input,and the ionospheric delay corrected by the observation data of the dual-frequency receiver as the prediction target.The experimental results show that the average prediction accuracy of the model on the test set is 81.71%,which is significantly better than the traditional Klobuchar model(the average compensation accuracy is about 50%～60%).关键词
单频观测伪距/多层感知器神经网络/电离层延迟/Klobuchar模型/精度优化Key words
single-frequency observed pseudo-range/Multi-Layer Perceptron neural network/ionospheric delay/Klobuchar model/accuracy optimization分类
信息技术与安全科学引用本文复制引用
季东霖,孙苏艺,郭昱伯,叶毅铷,韩松,石海岩..基于多层感知器神经网络的单频观测伪距精度优化研究[J].现代信息科技,2025,9(17):38-44,7.基金项目
中央高校基本科研业务费专项资金资助 （）
中国矿业大学(北京)大学生创新训练项目(202414019) （北京）
