基于多相参处理间隔频响特征聚类的有源假目标鉴别方法

韦文斌; 彭锐晖; 孙殿星; 谭顺成; 宋颖娟; 张家林

doi:10.11999/JEIT231012

基于多相参处理间隔频响特征聚类的有源假目标鉴别方法

doi: 10.11999/JEIT231012

1.
哈尔滨工程大学青岛创新发展基地青岛 266000
2.
海军航空大学信息融合研究所烟台 264001

基金项目: 航天科技集团稳定支持项目(ZY0110020009)，中国博士后科学基金(2021M693003)，国家自然科学基金(61731023)

详细信息

作者简介:
韦文斌：博士生，研究方向为雷达抗干扰、雷达信号处理

彭锐晖：博士，副教授，研究方向为雷达抗干扰、雷达目标特性

孙殿星：博士，副教授，研究方向为雷达抗干扰、目标跟踪

谭顺成：博士，副教授，研究方向为雷达抗干扰、目标跟踪

宋颖娟：硕士生，研究方向为雷达抗干扰、深度学习

张家林：硕士生，研究方向为雷达抗干扰、深度学习

通讯作者:
彭锐晖　pengruihui@hrbeu.edu.cn

中图分类号: TN974
计量
- 文章访问数: 233
- HTML全文浏览量: 101
- PDF下载量: 53
- 被引次数: 0
出版历程
- 收稿日期: 2023-09-18
- 修回日期: 2023-11-30
- 网络出版日期: 2023-12-06
- 刊出日期: 2024-07-29

Active False Target Identification Method Based on Frequency Response Features Clustering in Multi-Coherent Processing Intervals

1.
Qingdao Innovation and Development Center, Harbin Engineering University, Qingdao 266000, China
2.
Institute of Information Fusion, Navy Aeronautical University, Yantai 264001, China

Funds: China Aerospace Science and Technology Corporation Stabilization Support Project (ZY0110020009), China Postdoctoral Science Foundation (2021M693003), The National Natural Science Foundation of China (61731023)

摘要

摘要: 现有真-假目标智能识别算法大多基于监督学习，且在低信噪比条件下表现不好。针对上述问题，该文分别利用真、假目标在多个相参处理间隔(CPIs)内散射特性的时变性和唯一性，提出一种多相参处理间隔频响特征聚类的真、假目标无监督鉴别方法。首先，在快-慢时域中沿快时间维度对真、假目标进行加窗截断，提取快-慢时间域频率响应特征用于构建初步样本集；然后，通过Agglomerative聚类和特征融合网络组成的两步识别算法对真-假目标进行识别；最后，提出一种多相参处理间隔联合决策方法提升识别性能和可靠性。经仿真和实测数据检验，证明了所提方法可实现真实目标和多种有源假目标的有效分离。
- 有源假目标 /
- 多相参处理间隔 /
- 散射特性 /
- 快-慢时间域频率响应 /
- 无监督 /
- Agglomerative聚类
Abstract: Most of the existing intelligent algorithms for identifying real and false targets are based on supervised learning and perform poorly under a low signal-to-noise ratio. Considering the above problems, an unsupervised clustering identification method of real and false targets based on frequency response features in multi-Coherent Processing Intervals(CPIs) is proposed by using the variability and uniqueness of the scattering characteristics of real and false targets in multi-CPIs, respectively. Firstly, the real and false targets are windowed and truncated along the fast time dimension in the fast-slow time domain, and the fast-slow time domain frequency response features are extracted to construct a preliminary sample set. Then, the real and false targets are identified by a two-step recognition algorithm composed of an Agglomerative clustering and a feature fusion network. Finally, a multi-CPI joint decision method is proposed to improve the recognition performance and reliability. It is proved by simulation and measured data that the proposed method can effectively identify real targets and multiple active false targets.
- Active false target /
- Multi Coherent Processing Intervals(CPIs) /
- Scattering characteristics /
- Fast-slow time domain frequency response /
- Unsupervised /
- Agglomerative clustering

HTML全文

图 1 特征提取流程图

下载: 全尺寸图片幻灯片

图 2 聚类结果示意图

下载: 全尺寸图片幻灯片

图 3 算法流程

下载: 全尺寸图片幻灯片

图 4 信号脉压和相参累积结果

下载: 全尺寸图片幻灯片

图 5 真实目标和欺骗干扰假目标的快-慢时间域幅频响应特征对比

下载: 全尺寸图片幻灯片

图 6 仿真识别结果

下载: 全尺寸图片幻灯片

图 7 聚类结果可视化

下载: 全尺寸图片幻灯片

表 1 仿真参数

参数	取值	参数	取值
载频	10 GHz	脉冲重复频率	3 kHz
脉宽	70${\text{ μs}}$	相参累积脉冲数量	64
带宽	25 MHz	矩形窗口长度	128
采样频率	60 MHz	截断后FFT点数	256
真实目标距离	10.5 km	真实目标速度	18 m/s
假目标个数	4	假目标距离	真实目标附近2 km

下载: 导出CSV

表 2 1DCNN-LSTM参数

上通道	卷积核大小	激活函数	池化
卷积层1	8 × 1 × 4	ReLU	2 × 1
卷积层2	8 × 1 × 4	ReLU	2 × 1
卷积层3	8 × 1 × 4	ReLU	2 × 1

下载: 导出CSV

表 3 实测数据实验参数

参数	取值	参数	取值
载频	10 GHz	脉冲重复频率	3 kHz
脉宽	60${\text{ μs}}$	相参累积脉冲数量	64
带宽	30 MHz	真实目标距离	8.5 km
采样频率	80 MHz	假目标距离	真实目标附近1 km

下载: 导出CSV

表 4 实测数据上识别结果(%)

决策方法	平均识别率	真实目标识别率	假目标识别率
独立决策法	86.7	88.3	85.1
联合决策法	95.8	96.7	95.0

下载: 导出CSV

表 5 平均识别率与文献[14]对比结果

信噪比(dB)	本文方法(%)	文献[14]方法(%)
–12	99.2	53.6
–11	99.4	65.2
–10	99.3	80.5
–9	99.7	90.3
–8	99.8	95.8
–7	100.0	98.7
–6	100.0	99.7

下载: 导出CSV

表 6 平均识别率与文献[6]对比结果

信噪比(dB)	本文方法(%)	文献[6]方法(%)
–8	99.8	78.2
–7	99.8	84.6
–6	100.0	91.3
–5	99.9	93.2
–4	100.0	95.1
–3	100.0	97.2
–2	100.0	98.4

下载: 导出CSV

表 7 平均识别率与文献[25]对比结果

信噪比(dB)	本文方法(%)	文献[25]方法(%)
–8	99.1	92.4
–7	99.3	91.8
–6	99.3	92.7
–5	99.7	91.5
–4	99.8	92.7
–3	100.0	93.4
–2	100.0	92.9

下载: 导出CSV

参考文献(25)

[1]	温镇铭, 王国宏, 张亮, 等. 基于正负频偏脉冲压缩相参积累的移频干扰鉴别方法[J]. 电子与信息学报, 2023, 45(8): 2936–2944. doi: 10.11999/JEIT220873. WEN Zhenming, WANG Guohong, ZHANG Liang, et al. Frequency-shift jamming identification methods based on positive and negative frequency shift pulse compression coherent integration[J]. Journal of Electronics & Information Technology, 2023, 45(8): 2936–2944. doi: 10.11999/JEIT220873.
[2]	张洋, 位寅生, 于雷. 抗主瓣多假目标欺骗干扰EPC-MIMO波形自适应优化设计技术[J]. 电子学报, 2022, 50(3): 513–523. doi: 10.12263/DZXB.20210329. ZHANG Yang, WEI Yinsheng, and YU Lei. Adaptive optimization design technology of EPC-MIMO waveform against mainlobe multiple false targets deception jamming[J]. Acta Electronica Sinica, 2022, 50(3): 513–253. doi: 10.12263/DZXB.20210329.
[3]	王国宏, 孙殿星, 白杰, 等. 基于预估-反馈联合处理的射频噪声干扰抑制算法[J]. 航空学报, 2018, 39(3): 321500. doi: 10.7527/ S1000-6893.2017.21500. WANG Guohong, SUN Dianxing, BAI Jie, et al. Radio frequency noise interference suppression based on estimation-feedback integration[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(3): 321500. doi: 10.7527/S1000-6893.2017.21500.
[4]	孙闽红, 丁辰伟, 张树奇, 等. 基于统计相关差异的多基地雷达拖引欺骗干扰识别[J]. 电子与信息学报, 2020, 42(12): 2992–2998. doi: 10.11999/JEIT190634. SUN Minhong, DING Chenwei, ZHANG Shuqi, et al. Recognition of deception jamming based on statistical correlation difference in a multistatic radar system[J]. Journal of Electronics & Information Technology, 2020, 42(12): 2992–2998. doi: 10.11999/JEIT190634.
[5]	WU Qihua, ZHAO Feng, AI Xiaofeng, et al. Two-dimensional blanket jamming against ISAR using Nonperiodic ISRJ[J]. IEEE Sensors Journal, 2019, 19(11): 4031–4038. doi: 10.1109/JSEN.2019.2897363.
[6]	ZHOU Hongping, DONG Chengcheng, WU Ruowu, et al. Feature fusion based on bayesian decision theory for radar deception jamming recognition[J]. IEEE Access, 2021, 9: 16296–16304. doi: 10.1109/ACCESS.2021.3052506.
[7]	XU Chang, YU Lei, WEI Yinsheng, et al. Research on active jamming recognition in complex electromagnetic environment[C]. 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP), Chongqing, China, 2019: 1–5. doi: 10.1109/ICSIDP47821.2019.9173455.
[8]	HAO Zhimei, YU Wen, and CHEN Wei. Recognition method of dense false targets jamming based on time-frequency atomic decomposition[J]. The Journal of Engineering, 2019, 2019(20): 6354–6358. doi: 10.1049/joe.2019.0147.
[9]	SU Detao and GAO Meiguo. Research on jamming recognition technology based on characteristic parameters[C]. 2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP), Nanjing, China, 2020: 303–307. doi: 10.1109/ICSIP49896.2020.9339393.
[10]	周红平, 王子伟, 郭忠义. 雷达有源干扰识别算法综述[J]. 数据采集与处理, 2022, 37(1): 1–20. doi: 10.16337/j.1004-9037.2022.01.001. ZHOU Hongping, WANG Ziwei, and GUO Zhongyi. Overview on recognition algorithms of radar active jamming[J]. Journal of Data Acquisition and Processing, 2022, 37(1): 1–20. doi: 10.16337/j.1004-9037.2022.01.001.
[11]	BHATTI F A, KHAN M J, SELIM A, et al. Shared spectrum monitoring using deep learning[J]. IEEE Transactions on Cognitive Communications and Networking, 2021, 7(4): 1171–1185. doi: 10.1109/TCCN.2021.3071149.
[12]	韦文斌, 彭锐晖, 孙殿星, 等. 基于频响特性的大起伏密集假目标干扰识别技术[J]. 兵工学报, 2023, 44(10): 3204–3217. doi: 10.12382/bgxb.2022.0610. WEI Wenbin, PENG Ruihui, SUN Dianxing, et al. Recognition of dense false target jamming with large fluctuations using frequency response characteristics[J]. Acta Armamentarii, 2023, 44(10): 3204–3217. doi: 10.12382/bgxb.2022.0610.
[13]	LIU Qiang and ZHANG Wei. Deep learning and recognition of radar jamming based on CNN[C]. 2019 12th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou, China, 2019: 208–212. doi: 10.1109/ISCID.2019.00054.
[14]	LV Qinzhe, QUAN Yinghui, FENG Wen, et al. Radar deception jamming recognition based on weighted ensemble CNN with transfer learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5107511. doi: 10.1109/TGRS.2021.3129645.
[15]	张顺生, 陈爽, 陈晓莹, 等. 面向小样本的多模态雷达有源欺骗干扰识别方法[J]. 雷达学报, 2023, 12(4): 882–891. doi: 10.12000/JR23104. ZHANG Shunsheng, CHEN Shuang, CHEN Xiaoying, et al. Active deception jamming recognition method in multimodal radar based on small samples[J]. Journal of Radars, 2023, 12(4): 882–891. doi: 10.12000/JR23104.
[16]	LIU Jin, HE Siyuan, ZHANG Lei, et al. An automatic and forward method to establish 3-D parametric scattering center models of complex targets for target recognition[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(12): 8701–8716. doi: 10.1109/TGRS.2020.2989856.
[17]	PENG Ruihui, WEI Wenbin, SUN Dianxing, et al. A positive-unlabeled radar false target recognition method based on frequency response features[J]. IEEE Signal Processing Letters, 2023, 30: 1067–1071. doi: 10.1109/LSP.2023.3305192.
[18]	DAI Fengzhou, LIU Jiang, TIAN Long, et al. An end-to-end approach for rigid-body target micro-Doppler analysis based on the asymmetrical autoencoding network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1–19. doi: 10.1109/TGRS.2023.3255863.
[19]	FISHER P O and AL-SARAWI S F. An optimized segmented quasi-memoryless nonlinear behavioral modeling approach for RF power amplifiers[J]. IEEE Transactions on Microwave Theory and Techniques, 2018, 66(1): 294–305. doi: 10.1109/TMTT.2017.2723010.
[20]	邢孟道, 王彤, 李真芳, 等. 雷达信号处理基础[M]. 北京: 电子工业出版社, 2008: 143–144. XING Mengdao, WANG Tong, LI Zhenfang, et al. Fundamentals of Radar Signal Processing[M]. Beijing: Publishing House of Electronics Industry, 2008: 143–144.
[21]	SUN Kun and TAO Wenbing. A constrained radial agglomerative clustering algorithm for efficient structure from motion[J]. IEEE Signal Processing Letters, 2018, 25(7): 1089–1093. doi: 10.1109/LSP.2018.2839022.
[22]	YU Zhengyang, TANG Jianlong, and WANG Zhao. GCPS: A CNN performance evaluation criterion for radar signal intrapulse modulation recognition[J]. IEEE Communications Letters, 2021, 25(7): 2290–2294. doi: 10.1109/LCOMM.2021.3070151.
[23]	WEI Shunjun, QU Qizhe, ZENG Xiangfeng, et al. Self-attention Bi-LSTM networks for radar signal modulation recognition[J]. IEEE Transactions on Microwave Theory and Techniques, 2021, 69(11): 5160–5172. doi: 10.1109/TMTT.2021.3112199.
[24]	PAN Mian, JIANG Jie, KONG Qingpeng, et al. Radar HRRP target recognition based on t-SNE segmentation and discriminant deep belief network[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(9): 1609–1613. doi: 10.1109/LGRS.2017.2726098.
[25]	孙殿星, 陈翔, 万建伟, 等. 基于多特征的密集假目标干扰融合识别与抑制[J]. 系统工程与电子技术, 2018, 40(10): 2207–2215. doi: 10.3969/j.issn.1001-506X.2018.10.08. SUN Dianxing, CHEN Xiang, WAN Jianwei, et al. Fusion identification and suppression technique against concentrated false targets jamming based on multiple features[J]. Systems Engineering and Electronics, 2018, 40(10): 2207–2215. doi: 10.3969/j.issn.1001-506X.2018.10.08.