遗传算法优化的BP神经网络卫星钟差预报

针对BP (Back Propagation)神经网络模型预测卫星钟差中权值和阈值的最优化问题, 提出了基于遗传算法优化的BP神经网络卫星钟差短期预报模型, 给出了遗传算法优化BP神经网络的基本思想、具体方法和实施步骤. 为验证该优化模型的有效性和可行性, 利用北斗卫星导航系统(BeiDou navigation satellite system, BDS)卫星钟差数据进行钟差预报精度分析, 并将其与灰色模型(GM(1,1))和BP神经网络模型预报的结果比较分析. 结果表明: 该模型在短期钟差预报中具有较好的精度, 优于GM(1,1)模型和BP神经网络模型.

Genetic Algorithm Optimization in the Prediction of Satellite Clock Bias by BP Neural Network

Aiming at the optimization problem of the weight and the threshold value in the prediction of satellite clock bias by BP (Back Propagation) neural network model, a short-term prediction model of satellite clock bias based on genetic algorithm is proposed, the basic idea, the specific method, and the implementation steps of genetic algorithm optimization of BP neural network are presented. In order to verify the validity and feasibility of the optimization model, the accuracy of clock bias prediction is analyzed by using the data of BDS (BeiDou navigation satellite system) satellite clock bias, and the prediction precisions are compared with the GM(1,1) (Grey Model(1,1)) and BP neural network model. The results show that the prediction precision for the proposed method is better than those for the GM(1,1) and BP neural network models.