一种有效的常规雷达目标识别方法

摘要

An efficient method for the radar target identification is proposed based on the combination of wavelet transform and evolutionary network. The Mallat algorithm is used to select and compress the features of the range profiles,and a hybrid evolutionary algorithm based on evolutionary programming is used to optimally design the classifier,which is made up of the feed-forward netw. ork. The experimental results show that the whole target identification system has a relatively simple structure and good generalization ability.%基于小波变换和进化网络提出一种有效的常规雷达目标识别方法。即首先利用Mallat算法对雷达目标一维距离像进行特征提取和压缩，然后在进化规划的基础上提出一种混合进化算法来优化设计由多层前向网络构成的分类器。实验结果表明，整个目标识别系统的结构简单，同时具有较好的推广能力。