针对舰载相控阵雷达信号在复杂电磁环境中，噪声信号频谱能量超过目标信号，导致雷达信号难以识别这一问题，提出基于高次时频谱特征的舰载相控阵雷达信号降噪识别方法。通过CWD时频变换方法，将原始雷达信号映射到时频域，提取信号二维时频分布信息后，对CWD时频分布信息进行幂处理，计算时频信息中各元素幂次信息，提取信号高次时频谱特征；由广义S变换方法，调节信号高次时频谱特征滤波所用高斯窗函数与时频分辨率，完成雷达信号时频降噪。将降噪后的信号输入循环神经网络中，捕捉降噪信号中时序依赖关系，学习不同信号类型之间区分特征，完成雷达信号降噪识别。经测试，此方法在强电磁干扰下对信号的识别结果准确，可以有效弱化复杂电磁环境干扰影响。
Aiming at the problem that the noise signal spectrum energy of shipborne phased array radar signals exceeds the target signal in complex electromagnetic environments, making it difficult to recognize radar signals, a denoising recognition method for shipborne phased array radar signals based on high-order time-frequency spectrum features is proposed. By using the CWD time-frequency transformation method, the original radar signal is mapped to the time-frequency domain. After extracting the two-dimensional time-frequency distribution information of the signal, the CWD time-frequency distribution information is power processed to calculate the power information of each element in the time-frequency information and extract the high-order time-frequency spectrum characteristics of the signal; By using the generalized S-transform method, the Gaussian window function and time-frequency resolution used for filtering high-order time-frequency spectrum features of the signal are adjusted to achieve time-frequency denoising of radar signals. Input the denoised signal into a recurrent neural network, capture the temporal dependencies in the denoised signal, learn the distinguishing features between different signal types, and complete radar signal denoising recognition. After testing, this method has shown accurate recognition results for signals under strong electromagnetic interference and can effectively weaken the impact of complex electromagnetic environment interference.
2024,46(16): 115-119 收稿日期：2024-01-11
DOI：10.3404/j.issn.1672-7649.2024.16.018
分类号：TN971
作者简介：张克生（1983 – ），男，硕士，讲师，研究方向为物理教学、天线设计与计算电磁学等
参考文献：
[1] 彭晓星, 贾爱鹏, 吴民忠, 等. 一种高稳定大功率雷达电源系统的设计与实现[J]. 船海工程, 2023, 52(1): 98-101.
PENG Xiaoxing, JIA Aipeng, WU Minzhong, et al. Design and implementation of a high stability marine radar power supply system[J]. Ship & Ocean Engineering, 2023, 52(1): 98-101.
[2] 陈斯文, 吕梦琴. 基于任务剖面的舰载雷达任务可靠性评估[J]. 现代雷达, 2021, 43(4): 70-76.
CHEN Siwen, LV Mengqin. Mission reliability evaluation of shipborne radar based on mission profile[J]. Modern Radar, 2021, 43(4): 70-76.
[3] 韩晶晶, 王树红. 基于CEEMD的压缩感知降噪在雷达信号识别中的应用研究[J]. 电子器件, 2022, 45(5): 1094-1099.
HAN Jingjing, WANG Shuhong. The CEEMD and compressed sensing theory de-noising method and its application to radar emitter signal recognition[J]. Chinese Journal of Electron Devices, 2022, 45(5): 1094-1099.
[4] 黄颖坤, 金炜东, 颜康, 等. 基于距离特征的雷达辐射源信号识别方法[J]. 系统仿真学报, 2021, 33(12): 2959-2966.
HUANG Yingkun, JIN Weidong, YAN Kang, et al. Radar emitter signal identification via distance features[J]. Journal of System Simulation, 2021, 33(12): 2959-2966.
[5] 王红卫, 董鹏宇, 陈游, 等. 半监督条件下基于朴素贝叶斯和Choi-Williams时频分布能量积累的雷达信号识别[J]. 电子与信息学报, 2021, 43(3): 589-597.
WANG Hongwei, DONG Pengyu, CHEN You, et al. Recognition method of radar signal based on the energy cumulant of Choi-Williams distribution and improved semi-supervised Na?ve Bayes[J]. Journal of Electronics & Information Technology, 2021, 43(3): 589-597.
[6] YANG R , JIANG H , ZHANG Q , et al. Spectrally compatible multiple-input multiple-output radar waveform design based on alternating direction method of multipliers[J]. IET Signal Processing, 2022, 16(7): 737–749.
[7] 肖易寒, 王亮, 郭玉霞. 基于去噪卷积神经网络的雷达信号调制类型识别[J]. 电子与信息学报, 2021, 43(8): 2300-2307.
XIAO Yihan, WANG Liang, GUO Yuxia. Radar signal modulation type recognition based on denoising convolutional neural network[J]. Journal of Electronics & Information Technology, 2021, 43(8): 2300-2307.
[8] 吴力华, 杨露菁, 袁园. 基于多特征融合的LPI雷达信号调制样式识别[J]. 计算机仿真, 2023, 40(5): 37-42+93.
WU Lihua, YANG Lujing, YUAN Yuan. Modulation recognition of LPI radar signals based on multi-feature fusion[J]. Computer Simulation, 2023, 40(5): 37-42+93.
