高频地波雷达中断信号恢复方法研究
发布时间：2019-03-22 17:05
【摘要】：信号中断是造成高频地波雷达回波谱信噪比下降的主要原因之一.在传统的中断信号恢复方法-自回归(Autoregressive,AR)模型的基础上,提出了基于反向传播(Back Propagation,BP)神经网络的信号恢复方法.通过实测数据验证了两种方法的处理效果,结果表明:BP神经网络的预测误差小于AR模型的预测误差,随着预测点数的增加,误差增长率小于AR模型,同时BP神经网络恢复方法对海洋回波信号能量损失较小.
[Abstract]:Signal interruption is one of the main reasons for the decrease of signal-to-noise ratio (SNR) in the echo spectrum of HF ground wave radar. Based on the traditional interrupt signal recovery method-autoregressive (Autoregressive,AR) model, a signal recovery method based on back propagation (Back Propagation,BP) neural network is proposed. The results show that the prediction error of BP neural network is smaller than that of AR model, and the error growth rate is smaller than that of AR model with the increase of the number of prediction points. At the same time, the energy loss of ocean echo signal by BP neural network restoration method is small.
【作者单位】： 武汉大学电子信息学院;
【基金】：“十二五”863计划(No.2012AA091701) 国家自然科学基金(No.60571065) 中央高校基本科研业务费专项资金(No.2012212020207)
【分类号】：TN958.93
[Abstract]:Signal interruption is one of the main reasons for the decrease of signal-to-noise ratio (SNR) in the echo spectrum of HF ground wave radar. Based on the traditional interrupt signal recovery method-autoregressive (Autoregressive,AR) model, a signal recovery method based on back propagation (Back Propagation,BP) neural network is proposed. The results show that the prediction error of BP neural network is smaller than that of AR model, and the error growth rate is smaller than that of AR model with the increase of the number of prediction points. At the same time, the energy loss of ocean echo signal by BP neural network restoration method is small.
【作者单位】： 武汉大学电子信息学院;
【基金】：“十二五”863计划(No.2012AA091701) 国家自然科学基金(No.60571065) 中央高校基本科研业务费专项资金(No.2012212020207)
【分类号】：TN958.93
【参考文献】
相关期刊论文 前6条
1 黄亮,文必洋,邓巍;高频地波雷达抑制瞬态干扰研究[J];电波科学学报;2004年02期
2 王世凯,焦培南,柳文,凡俊梅;利用人工神经网络重构区域电离层临界频率分布[J];电波科学学报;2004年06期
3 吴雄斌;尹微;程丰;柯亨玉;;宽波束高频雷达海洋回波的统计特性[J];电波科学学报;2006年03期
4 魏e，
本文编号：2445767
本文链接：https://www.wllwen.com/kejilunwen/wltx/2445767.html
