基于PSO-PNN算法的雷达点迹真伪鉴别方法

The Identification Method of True and False Plots Based On PSO-GNN Algorithm

针对雷达目标检测后的剩余杂波,提出了一种将粒子群优化算法(PSO)与概率神经神经网络(PNN)相结合的雷达点迹真伪鉴别方法。方法可以在目标检测后进一步区分目标点迹和杂波点迹。同时,将其雷达点迹鉴别结果与BP神经网络(BPNN)对雷达点迹鉴别结果作了对比,发现上述方法的整体识别率可达91.13%,目标识别率可达93.78%,较BPNN分别提升1.55%和3.55%。结果表明,PSO-PNN能够有效鉴别雷达点迹真伪。

For the residual clutter after radar detection, a method of radar plots identification based on the combination of particle swarm optimization(PSO) and probabilistic neural network(PNN) is proposed.This method can further distinguish the target plots and clutter plots after the target detection.At the same time, compared with BP neural network(BPNN) radar plots identification results, it is found that the overall recognition rate of the proposed method can reach 91.13%, and the target recognition rate can reach 93.78%, which are 1.55% and 3.55% higher than BPNN, respectively.The results show that PSO-PNN can effectively identify the authenticity of radar plots.