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.
Signal interruption is one of the primary causes for SNR decreasing in the ech- o spectrum of high frequency surface wave radar HFSWR. Based on the traditional sig- nal recovery AR model method, a new signal recovery method with BP neural network is proposed. The performances of both methods are validated by the experimental results. It is shown that： the prediction error with BP method is less than AR model; and the er- ror rate is less than AR model with the growing prediction step; the power loss of sea echo is smaller using BP recovery method.
出处
《电波科学学报》
EI
CSCD
北大核心
2014年第4期758-762,共5页
Chinese Journal of Radio Science
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)
