基于改进SFLA-lman神经网络的电离层杂波抑制方法

针对高频地波雷达目标检测中电离层杂波的干扰问题，提出了一种基于改进混合蛙跳算法优化Elman神经网络预测抑制电离层杂波的策略。为解决混合蛙跳算法初始种群分布不均匀、收敛精度低、易陷于局部极值等问题，引入Cubic混沌映射、莱维飞行策略、非线性平衡因子和复制操作，增强种群多样性，提高算法搜索能力。利用改进后的算法和其他算法分别优化Elman神经网络预测抑制模型，结果表明，改进后的算法无论是在收敛精度和稳定性上，还是在临近距离单元电离层杂波的预测抑制上，都取得了显著的提升。在基本保留目标信号的基础上，平均信杂比较原始回波提升18.52 dB，较原始混合蛙跳算法提升1.08 dB，对于电离层杂波的抑制具有较高应用价值。

Ionospheric Clutter Suppression Based on Improved SFLA-lman Neural Network

For the interference problem of ionospheric clutter in high frequency surface wave radar(HFSWR) target detection,a strategy to suppress ionospheric clutter based on the improved Shuffled Frog Leaping Algorithm(SFLA) with optimized Elman neural network prediction is proposed.To solve the problems of uneven initial population distribution,low convergence accuracy and easy to be trapped in local extremes of the SFLA,the Cubic chaos mapping,Lévy flight strategy,nonlinear balance factor and replication operation are introduced to enhance the population diversity and improve the search capability of the algorithm.The improved algorithm and other algorithms are used to optimize the Elman neural network prediction suppression model respectively.The results show that the improved algorithm achieves a significant improvement not only in convergence accuracy and stability,but also in the prediction suppression of ionospheric clutter in the proximity unit.In the condition of basic preservation of the target signal,the average signal spurious is improved by 18.52 dB compared with the original echo and 1.08 dB compared with shuffled frog leaping algorithm,which is of high application value for the suppression of ionospheric clutter.