摘要
为提高雷达目标识别准确率,提出了一种基于PSO-BP神经网络的雷达一维距离像识别方法。利用粒子群优化算法良好的全局搜寻能力,对BP神经网络的权值和阈值进行了优化,弥补了BP神经网络收敛速度慢、存在多个局部极值点的缺陷。利用实测数据对PSO优化前后的BP神经网络的识别性能进行了对比测试。实验结果表明,PSO-BP神经网络具有更高的识别准确率及噪声鲁棒性,分类性能优良。
In order to improve the radar target recognition accuracy,this paper proposes a high resolution range profile recognition method based on PSO-BP neural network.The good global search ability of particle swarm optimization algorithm is used to optimize the weights and thresholds of BP neural network,which makes up for the shortcomings of slow convergence speed and multiple local extreme points in BP neural network.The measured data are used to make a comparision test of the recognition performance of BP neural network before and after optimization.Experimental results show that PSO-BP neural network has higher recognition accuracy and noise robustness,and its classification performance is excellent.
作者
王泓霖
李伟
许强
徐建业
邹鲲
WANG Hong-lin;LI Wei;XU Qiang;XU Jian-ye;ZOU Kun(Information and Navigation College,Air Force Engineering University,Xi’an 710077,China)
出处
《火力与指挥控制》
CSCD
北大核心
2019年第12期39-44,共6页
Fire Control & Command Control
基金
国家自然科学基金(61302153
61571456)
航空科学基金资助项目(20160196001)
关键词
BP神经网络
PSO
优化算法
高分辨距离像
目标识别
BP neural network
particle swarm optimization
high resolution range profile
target recognition