一种雷达辐射源信号分类新方法 - 科学网—博客.pdf

一种雷达辐射源信号分类新方法 邹兴文，张葛祥，李明，李序 （西南交通大学电气工程学院，四川 成都 610031） 摘要：针对复杂体制雷达辐射源信号分类问题，提出一种基于时频分析、图像处理和支持向量机的辐射源信号分 类新方法。该方法将辐射源信号分类问题转换为图像处理及识别问题，先对辐射源信号进行时频分析，获得时频 分布图，并将其转化为灰度图像和作归一化处理，再用支持向量机对处理后的图像进行分类。五种典型辐射源信 号分类实验表明，该方法在信噪比高于 2.5dB 时，平均正确分类率达 92%以上。本文工作对电子对抗信号处理具 有一定的参考价值。 关键字：雷达辐射源信号；自动分类；时频分析；图像处理；支持向量机 中图法分类号：TN974；TP391 文献标识码：A A Novel Method for Classifying Radar Emitter Signals ZOU Xing-wen, ZHANG Ge-xiang, LI Ming, LI Xu (School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China) Abstract: To correctly classify advanced radar emitter signals, this paper present a novel method consisting of time-frequency analysis, image processing and support vector machine. This method transforms the classification of emitter signals into image processing and image recognition. Emitter signals are analyzed in time-frequency domain and their time-frequency images are obtained. These images are transformed into grayscale images and normalized. Support vector machines are applied to design classifiers for recognizing the processed images, which correspond to different radar emitter signals. Experiments conducted on five typical emitter signals show that the introduced method achieves more than 92% correct classification rate on condition that the signal-to-noise ratio is above 2.5dB. This work has certain reference values to signal processing in electronic warfare. Keywords: Radar emitter signals; automatic classification; time-frequency analysis; image processing; support vector machine 用时频分析对辐射源信号进行分类的算法[3-4] 。但这 1 引言 些方法有一些共同的