基于经验模态分解的空中飞机目标分类

Aircraft Classification Based on Empirical Mode Decomposition

该文研究常规窄带雷达体制下喷气式飞机、螺旋桨飞机和直升机目标的分类问题。首先根据微多普勒效应利用多散射中心模型从理论上分析了飞机目标旋转部件的雷达回波模型;然后针对3类飞机目标回波在多普勒域频率调制的不同,提出一种基于经验模态分解(Empirical Mode Decomposition,EMD)算法的特征提取方法;最后基于仿真数据训练、实测数据测试的模式,使用支持矢量机(Support Vector Machine,SVM)分类器的分类结果表明新方法较现有方法在较高信噪比条件下具有更好的分类性能。

This paper studies on the classification issue of turbojet, propeller and helicopter targets by using the conventional radar system. Based on the micro-Doppler effect, the echo signal model for the rotating parts of aircrafts is analyzed theoretically via the multi-scattering center model firstly. Then according to the differences between the frequency modulation properties of the three kinds of airplanes in the Doppler domain, a new feature extraction method is proposed based on the Empirical Mode Decomposition （EMD） algorithm. Finally, the experimental results with the simulated training data, the measured test data and the Support Vector Machine （SVM） show the proposed method can achieve good classification performance under the test condition of relatively high Signal-to-Noise Ratio （SNR）.