基于GA-BP神经网络的BDS轨道误差模型研究

在对导航卫星轨道误差数据进行研究时发现,卫星广播星历轨道误差客观存在着一些不确定性的规律现象,针对这一无法用现有确定性模型表示的误差信息,建立了基于遗传算法优化BP神经网络的轨道误差预测模型。利用遗传算法来全局寻优BP神经网络的初始权值与阈值,同时根据广播星历解算出的卫星位置和速度,结合参考时刻及摄动改正项对神经网络进行训练和测试。试验结果表明,上述模型能较好的预测轨道误差,应用该模型进行卫星轨道解算时能有效提高轨道精度,降低轨道误差。

Research on BDS Orbit Error Model Based on GA-BP Neural Network

In the study on navigation satellite orbit error data,it is found that there are some uncertain phenomena in the satellite broadcast ephemeris orbit error.For this error information that cannot be represented by the existing deterministic model,a genetic algorithm optimization was established For the error prediction model of BP neural network.The genetic algorithm was used to globally optimize the initial weight and threshold of the BP neural network,and the neural network was trained and tested according to the satellite position and velocity calculated by the broadcast ephemeris,combined with the reference time and the perturbation correction term.The experimental results show that the model can predict the orbit error better,and the model can effectively improve the orbit accuracy and reduce the orbit error when using the satellite orbit solution.