Elman Neural Network Based on Particle Swarm Optimization for Prediction of GPS Rapid Clock Bias
作者单位：Naval Univ.of Engineering
会议名称：《第十三届中国卫星导航年会》
会议日期：2022年
学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081802[工学-地球探测与信息技术] 081104[工学-模式识别与智能系统] 08[工学] 081105[工学-导航、制导与控制] 0818[工学-地质资源与地质工程] 0804[工学-仪器科学与技术] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
关 键 词：Satellite atomic clock Clock bias prediction Elman neural network Particle Swarm optimization
摘 要：To improve the accuracy of the satellite rapid clock bias, a modified Elman neural network clock bias prediction method based on particle swarm optimization（PSO） algorithm is proposed. The Elman recurrent neural network is introduced to predict the clock bias, its weights and thresholds are improved by PSO algorithm to improve the training speed and prediction accuracy. Then,the optimization method is applied to the rapid clock bias prediction, and the steps of using this method for the rapid clock bias prediction are given. Finally,the optimization method is compared with common quadratic polynomial model, gray model and ultra rapid clock bias product IGU-P. The results show that the PSO-Elman model achieves high accuracy and stability for four different types of GPS satellite clock, and its prediction accuracy and stability improved by 85%, 74%, 89% and 71%, 53%, 28% compared with QPM,GM（1,1） and IGU-P products, respectively.