基于小波分解和遗传小波神经网络的卫星钟差预报

发布时间：2018-05-08 00:37

本文选题：钟差预报 + 小波分解　；参考：《桂林理工大学学报》2017年01期

【摘要】：星载原子钟在空间环境中受到多种不确定因素的影响以及原子钟本身所具有的复杂特性,导致卫星钟差呈现出非线性和非平稳性变化。为此提出了一种新方法:先采用小波分解将原始钟差序列分解成高频分量和低频分量,然后利用遗传小波神经网络对低频分量和高频分量分别进行预报,最后将各分量的预报结果进行叠加得到最终的预报值,并与灰色模型、最小二乘支持向量机和遗传小波神经网络的预报结果对比分析。结果表明:该方法预报精度较高,预报残差更为平稳,应用于卫星钟差预报是可行有效的。
[Abstract]:The space-borne atomic clock is affected by many uncertain factors in the space environment and the complex characteristics of the atomic clock itself lead to the nonlinear and non-stationary variation of satellite clock difference. In this paper, a new method is proposed: firstly, the original clock difference sequence is decomposed into high frequency component and low frequency component by wavelet decomposition, and then the low frequency component and high frequency component are predicted by genetic wavelet neural network. Finally, the prediction results of each component are superimposed to obtain the final prediction value, and the prediction results are compared with those of grey model, least squares support vector machine and genetic wavelet neural network. The results show that the prediction accuracy of this method is higher and the prediction residual error is more stable. It is feasible and effective to apply this method to satellite clock error prediction.
【作者单位】：桂林理工大学测绘地理信息学院;桂林理工大学广西空间信息与测绘重点实验室;
【基金】：国家自然科学基金项目(41461089) 广西自然科学基金项目(2014GXNSFAA118288) 广西空间信息与测绘重点实验室基金项目(桂科能1207115-07;130511407)
【分类号】：P228

【相似文献】