基于多重同步压缩变换的雷达辐射源分选识别

针对低信噪比条件下雷达信号分选识别算法识别率低且复杂度高的问题,提出了一种基于多重同步压缩变换(MSST)的雷达辐射源分选识别算法。首先通过MSST得到信号的时频图像矩阵;然后,对时频图像进行预处理,提取出时频图像的灰度共生矩阵纹理特征和Zernike矩特征;同时提取了信号的功率谱参数特征和平方谱统计特征,组成特征参数向量;最后利用支持向量机分类器实现了对雷达信号的自动分选识别。仿真结果表明,在信噪比为-2 dB时,该算法对9种雷达信号(CW、LFM、NLFM、BPSK、MPSK、Costas、LFM/BPSK、LFM/FSK和BPSK/FSK)的整体平均识别成功率大于96.5%。

Radar Emitter Sorting and Recognition Based on Multi-synchrosqueezing Transform

To solve the problem of the low recognition rate and high complexity of radar signal sorting and recognition algorithm under low signal-to-noise ratio(SNR), a radar emitter sorting and recognition algorithm based on multi-synchrosqueezing transform(MSST) is proposed. Firstly, the time-frequency image matrix of the signal is obtained through MSST, and then the time-frequency image is preprocessed to extract the gray level co-occurrence matrix(GLCM) texture features and Zernike moment features of the time-frequency image. At the same time, the power spectrum parameter features and square spectrum statistical features of the signal are extracted to form the characteristic parameter vector. Finally, the automatic radar signal sorting and recognition is realized via using the support vector machine classifier. Simulation results show that when the SNR is-2 dB, the overall average recognition success rate(RSR) of the proposed method for 9 kinds of radar signals(CW, LFM, NLFM, BPSK, MPSK, Costas, LFM/BPSK, LFM/FSK and BPSK/FSK) reaches more than 96.5%.