粒子群算法优化的神经网络短期钟差预报

Prediction of the short-term satellite clock error based on particle swarm optimization neural network

针对导航卫星钟差短期预报精度上的不足,该文提出了一种基于粒子群算法优化的BP神经网络钟差预报模型,通过粒子群算法来对BP神经网络的权值和阈值进行优化,利用IGS的钟差数据进行实验,并与灰色GM(1,1)模型、二次多项式模型和BP神经网络模型的预报结果进行对比分析。结果表明,粒子群优化算法的BP神经网络模型钟差预报效果良好,3h预报精度能够达到0.3ns,体现了本文钟差预报模型的实用性。

Aiming at the shortcomings of the short-term prediction of satellite clock error,this paper proposed a model of clock error prediction based on BP neural network optimized by the particle swarm optimization algorithm,the weights and thresholds of the BP neural network were optimized by the particle swarm optimization algorithm,and then the clock error data provided by IGS were tested and compared with the results of the gray GM(1,1)model,the quadratic polynomial model and the BP neural network model.The results showed that the BP neural network optimized by the particle swarm optimization algorithm worked well,the predicting accuracy can reach 0.3 ns,which reflected the practicality of the model.