Low Probability of Intercept Radar Signal Detection Algorithm Based on Convolutional Neural Networks
-
摘要: 为了解决雷达截获接收机对低截获概率(LPI)雷达信号检测效果不理想的问题，针对截获信号中有效信号脉宽长度来定义信号和噪声，该文提出一种基于卷积神经网络(CNN)的LPI雷达信号检测方法，利用卷积核与匹配滤波器结构上的相似性，在低信噪比下能够提高信号的检测准确率。利用大量的基于4种典型LPI雷达信号(线性调频信号(LFM)、非线性调频信号(NLFM)、二相编码信号(BPSK)、COSTAS频率编码信号)和白噪声信号的模拟数据集进行CNN模型训练，同时增加少量实测信号(LFM, BPSK)作为验证集进行适配，更好地拟合实测信号的检测模型。最终利用实际信号进行测试，实验结果表明：该文算法在低信噪比的情况下具有较好的检测效果，对多种调制方式、不同信噪比下的LPI雷达信号具有泛化能力。Abstract: In order to solve the problem of radar intercepting receiver’s unsatisfactory detection effect on Low Probability of Intercept (LPI) radar signal, a method of LPI radar signal detection based on Convolutional Neural Networks (CNN) is proposed, which defines signal and noise by effective signal pulse width in intercepted signal. The similarity of the convolution kernel and the matched filter in the structure can improve the detection accuracy of the signal under the low SNR.A large number of analog data sets based on four typical LPI radar signals (Linear Frequency Modulation signal (LFM), NonLinear Frequency Modulation signal (NLFM), Binary Phase Shift Keying signal (BPSK), COSTAS frequency coded signal) and white noise signals are used for CNN model training. At the same time, a small amount of measured signals (Linear Frequency Modulation signal (LFM), Binary Phase Shift Keying signal (BPSK)) are added as verification set for adaptation, so as to match better the detection model of measured signals. Finally, the experimental results show that the proposed algorithm has a good detection effect in the case of low SNR, and has the ability to generalize the LPI radar signals under various modulation modes and different SNR.
-
表 1 LPI雷达信号检测的CNN网络结构参数
层名称 结构参数 输入层 2×2000 第1, 2层 Conv1-64@2×32(步长：1×4) & Maxpooling@1×4(步长：1×2) 第3, 4层 Conv1-128@1×16(步长：1×4) & Maxpooling@1×4(步长：1×2) 第5, 6层 Conv1-256@1×8(步长：1×4) & Maxpooling@1×4(步长：1×2) 第7层 FC-1024 第8层 FC-256 输出层 2 
下载: 导出CSV
表 2 模拟信号的调制参数
调制方式 瞬时相位$\phi (t)$ 载频fc
(MHZ)带宽B
$({\rm{MHz}})$子脉冲宽度(μs) 巴克码 跳频序列${a_N}$ LFM $2{\rm{\pi } }\left({f_c} \times t + \dfrac{\mu }{2} \times {t^2}\right)$
调频斜率$\mu = B/\tau $50～70 20～40 __ __ __ NLFM $2{\rm{\pi } }\left({f_c} \times t + \dfrac{1}{2}{a_1} \times {t^2} + \dfrac{1}{3}{a_2} \times {t^3}\right)$
${a_1} = B/(2 \times \tau )$, ${a_2} = B/(2 \times {\tau ^2})$50～70 20～40 __ __ __ BPSK $2\pi {f_c}t + \theta ,\theta \in \left\{ {0,\pi } \right\}$ 50～70 __ 0.5～1 [1 1 1 1 1 –1–1 1 1 –1 1 –1 1] __ COSTAS $2{\rm{\pi } }({f_c} \times {a_N})t$${a_N} = \left\{ { {a_1},{a_2},\cdots,{a_n} } \right\}$ 5～10 __ 0.5～1 __ [8, 9, 6, 4, 10, 3, 2, 5, 7, 1]
下载: 导出CSV
表 3 实测信号的调制参数
调制方式 主要参数 取值范围 LFM 载频${f_c}{\rm{(MHz)} }$ 50～70 带宽$B{\rm{(MHz)} }$ 20～40 BPSK 载频${f_c}{\rm{(MHz)} }$ 50～70 子脉冲宽度(μs) 0.5～1 巴克码 [1 1 1 1 1 –1 –1 1 1 –1 1 –1 1]
下载: 导出CSV
-
[1] 鲍庆龙, 王森, 潘嘉蒙, 等. 非合作雷达辐射源目标探测系统关键技术分析[J]. 电波科学学报, 2020, 35(4): 496–503.BAO Qinglong, WANG Sen, PAN Jiameng, et al. Key technology analysis of target detection system based on non-cooperative radar illuminator[J]. Chinese Journal of Radio Science, 2020, 35(4): 496–503. [2] 李娜, 王珂, 李保珠. 低截获概率雷达信号检测方法的优化及应用[J]. 光学精密工程, 2014, 22(11): 3122–3128.Li Na, Wang Ke, Li Baozhu. Optimization and application of LPI radar signal detection method[J]. Optics and Precision Engineering, 2014, 22(11): 3122–3128. [3] LIU Yongjian, XIAO Peng, WU Hongchao, et al. LPI radar signal detection based on radial integration of Choi-Williams time-frequency image[J]. Journal of Systems Engineering and Electronics, 2015, 26(5): 973–981. doi: 10.1109/JSEE.2015.00106 [4] 朱文涛, 郑纪彬, 苏涛, 等. 线性调频连续波信号的检测和参数估计[J]. 电子与信息学报, 2013, 35(7): 1562–1568. doi: 10.3724/SP.J.1146.2012.01356ZHU Wentao, ZHENG Jibing, SU Tao, et al. Detection and parameter estimation of linear frequency modulation continuous wave signal[J]. Journal of Electronics &Information Technology, 2013, 35(7): 1562–1568. doi: 10.3724/SP.J.1146.2012.01356 [5] 刘锋, 徐会法, 陶然. 基于FRFT的对称三角LFMCW信号检测与参数估计[J]. 电子与信息学报, 2011, 33(8): 1864–1870.LIU Feng, XU Huifa, and TAO Ran. Detection and parameter estimation of symmetrical triangular LFMCW signal based on fractional Fourier transform[J]. Journal of Electronics &Information Technology, 2011, 33(8): 1864–1870. [6] 徐会法, 胡晓峰, 张明智. 基于FRFT的几种典型相位编码信号检测与参数估计[J]. 兵工学报, 2012, 33(9): 1048–1054.XU Huifa, HU Xiaofeng, and ZHANG Mingzhi. Detection and parameter estimation of polyphase code signals based on fractional Fourier transform[J]. Acta Armamentarii, 2012, 33(9): 1048–1054. [7] 黄宇, 刘锋, 王泽众, 等. 基于周期FRFT的多分量LFMCW雷达信号分离[J]. 航空学报, 2013, 34(4): 846–854.HUANG Yu, LIU Feng, WANG Zezhong, et al. Periodic FRFT-based multi-component LFMCW radar signal separating[J]. Acta Aeronautica et Astronautica Sinica, 2013, 34(4): 846–854. [8] 陈艳丽, 郭良浩, 宫在晓. 简明分数阶傅里叶变换及其对线性调频信号的检测和参数估计[J]. 声学学报, 2015, 40(6): 761–771.CHEN Yanli, GUO Lianghao, and GONG Zaixiao. The concise fractional Fourier transform and its application in detection and parameter estimation of the linear frequency-modulated signal[J]. Acta Acustica, 2015, 40(6): 761–771. [9] 李硕, 李天昀. 短波信道下的跳频信号检测[J]. 电子学报, 2019, 47(3): 623–629.LI Shuo and LI Tianyun. Frequency hopping signal detection over the Short-Wave Channel[J]. Acta Electronica Sinica, 2019, 47(3): 623–629. [10] GHADIMI G, NOROUZI Y, BAYDERKHANI R, et al. Deep learning-based approach for low probability of intercept radar signal detection and classification[J]. Journal of Communications Technology and Electronics, 2020, 65(10): 1179–1191. doi: 10.1134/S1064226920100034 [11] WANG Li, TANG Jun, and LIAO Qingmin. A study on radar target detection based on deep neural networks[J]. IEEE Sensors Letters, 2019, 3(3): 7000504. [12] WANG Chao, WANG Jian, and ZHANG Xudong. Automatic radar waveform recognition based on time-frequency analysis and convolutional neural network[C]. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, USA, 2017. [13] 黄宇涛, 普运伟, 吴海潇, 等. 基于栈式自编码机和模糊函数主脊的雷达辐射源信号识别[J]. 电波科学学报, 2020, 35(5): 689–698.HUANG Yutao, PU Yunwei, WU Haixiao, et al. Radar emitter signal recognition based on stackedauto-encoder and ambiguity function main ridge[J]. Chinese Journal of Radio Science, 2020, 35(5): 689–698. [14] 徐雅楠, 刘宁波, 丁昊, 等. 利用CNN的海上目标探测背景分类方法[J]. 电子学报, 2019, 47(12): 2505–2514.XU Yanan, LIU Ningbo, DING Hao, et al. Background classification method for marine target detection based on CNN[J]. Acta Electronica Sinica, 2019, 47(12): 2505–2514. [15] 赵文静, 刘畅, 刘文龙, 等. K分布海杂波背景下基于最大特征值的雷达信号检测算法[J]. 电子与信息学报, 2018, 40(9): 2235–2241. doi: 10.11999/JEIT171092ZHAO Wenjing, LIU Chang, LIU Wenlong, et al. Maximum eigenvalue based radar signal detection method for K distribution sea clutter environment[J]. Journal of Electronics &Information Technology, 2018, 40(9): 2235–2241. doi: 10.11999/JEIT171092 -
图(4) / 表(3)
计量
- 文章访问数: 1754
- HTML全文浏览量: 883
- PDF下载量: 226
- 被引次数: 0
下载:
