一种基于Kohonen神经网络的雷达回波特征识别和分类方法研究

A radar echo classification method based on Kohonen neural network

本文针对雷达三维目标回波特征抽取和分类问题,提出了一种基于均值滤波器和Kohonen自组织映射神经网络相结合的方法。仿真实验表明该方法抽取的特征具有良好的稳定性,且精度高,比单一的自组织分类器有更强的优势,最后通过采用实地录取的两组雷达目标回波数据进行检验,实验数据表明该方法可以使准确率达到90%以上,具有良好的提取效果和实用性。

The paper focuses on the research and application of neural network for feature extraction from the radar echo data, proposed a method of combining the mean filter and Kohonen neural network to resolve it. Simulation results show that the proposed method in the paper is feasible, the results is more stable and more accurate, apparently has an advantage over the ordinary self-organization neural network. To validate this method by applied to two groups of real radar data set. Result show that the proposed method is practical with ninety percent accuracy.