基于SVRGD的机载预警雷达自适应波束形成算法

doi:10.3969/j.issn.1001-506X.2021.01.11

系统工程与电子技术 ›› 2021, Vol. 43 ›› Issue (1): 83-90.doi: 10.3969/j.issn.1001-506X.2021.01.11

基于SVRGD的机载预警雷达自适应波束形成算法

彭芳¹(), 吴军^2,*(), 王帅¹(), 向建军¹()

1. 空军工程大学航空工程学院, 陕西西安 710038
2. 空军工程大学空管领航学院, 陕西西安 710051

收稿日期:2020-06-10 出版日期:2020-12-25 发布日期:2020-12-30
通讯作者: 吴军 E-mail:wuboy0210@163.com;2320251817@qq.com;xiang787419@163.com
作者简介:彭芳(1973-),女,副教授,博士,主要研究方向为雷达信号处理、机载预警探测技术。E-mail:wuboy0210@163.com|王帅(1996-),男,硕士研究生,主要研究方向为传感器管理。E-mail:2320251817@qq.com|向建军(1975-),男,副教授,博士,主要研究方向为雷达信号处理。E-mail:xiang787419@163.com
基金资助:
航空基金(20175596020)

Adaptive beamforming algorithm for airborne early warning radar based on SVRGD

Fang PENG¹(), Jun WU^2,*(), Shuai WANG¹(), Jianjun XIANG¹()

1. Aeronautics and Astronautics Engineering School, Air Force Engineering University, Xi'an 710038, China
2. Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an 710051, China

Received:2020-06-10 Online:2020-12-25 Published:2020-12-30
Contact: Jun WU E-mail:wuboy0210@163.com;2320251817@qq.com;xiang787419@163.com

摘要/Abstract

摘要：

自适应波束形成是机载预警雷达数字信号处理的一个关键环节。针对传统最小均方误差(least mean square, LMS)算法在短快拍数条件下的波束形成性能下降以及因迭代震荡易收敛于局部最优值的问题,提出了一种基于机器学习的随机方差减小梯度下降(stochastic variance reduction gradient descent, SVRGD)自适应波束形成方法。首先,建立面阵列接收信号数据模型。其次,基于随机梯度下降原理,引入方差缩减法通过内外循环迭代方式进行梯度修正,以减小随机梯度估计的方差,建立算法模型与实现流程。最后，通过设置平面阵列仿真场景,分析SVRGD自适应波束形成算法在波束形成、抗干扰、收敛速度等方面的性能,验证了该算法在低快拍数、强干扰和强噪声背景下具有的优良能力。

关键词: 机载预警雷达, 自适应波束形成, 随机梯度下降, 随机方差减小梯度下降, 机器学习

Abstract:

Adaptive beamforming is a key step of digital signal processing in airborne early warning radar. To solve the problem that the beamforming performance of traditional least mean square (LMS) algorithms is reduced under the condition of short snapshot and the algorithm tend to converge to local optimal value because iterative oscillation, an adaptive beamforming approach for stochastic variance reduction gradient descent (SVRGD) based on machine learning is proposed. Firstly, the data model of planar array receiving signal is established. Secondly, based on the stochastic gradient descent principle, the variance reduction method is introduced to modify the gradient through internal and external iteration for reducing the variance of the stochastic gradient estimation, and the algorithm model and implementation process are established. Finally, by setting up a planar array simulation scene, the performance of the SVRGD algorithm in the aspects of beamforming, anti-jamming and convergence speed is analyzed, and the excellent capability of algorithm in the background of short snapshot number, strong interference and noise is verified.

Key words: airborne early warning radar, adaptive beamforming, stochastic gradient descent (SGD), stochastic variance reduction gradient descent (SVRGD), machine learning

中图分类号:

TN959.73

彭芳, 吴军, 王帅, 向建军. 基于SVRGD的机载预警雷达自适应波束形成算法[J]. 系统工程与电子技术, 2021, 43(1): 83-90.

Fang PENG, Jun WU, Shuai WANG, Jianjun XIANG. Adaptive beamforming algorithm for airborne early warning radar based on SVRGD[J]. Systems Engineering and Electronics, 2021, 43(1): 83-90.

图/表 11

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

参考文献 24

1	张良, 祝欢, 杨予昊, 等. 机载预警雷达技术及信号处理方法综述[J]. 电子与信息学报, 2016, 38 (12): 3298- 3306.
	ZHANG L , ZHU H , YANG Y H , et al. Overview on airborne early warning radar technology and signal processing methods[J]. Journal of Electronics & Information Technology, 2016, 38 (12): 3298- 3306.
2	TALISA S H , O'HAVER K W , COMBERIATE T M , et al. Benefits of digital phased array radars[J]. Proceedings of the IEEE, 2016, 104 (3): 530- 543.
3	ECKHARDT J M , NIKO J , ADRIAN F , et al. FMCW multiple-input multiple-output radar with iterative adaptive beamforming[J]. IET Radar, Sonar & Navigation, 2018, 12 (11): 1187- 1195.
4	HU B , WU X C , ZHANG X , et al. Adaptive beamforming based on compressed sensing with gain/phase uncertainties[J]. IEICE Trans.on Fundamentals of Electronics, Communications and Computer Sciences, 2018, 101 (8): 1257- 1262.
5	ASHWINI D , ZALAWADIA K . Performance analysis of LMS adaptive beamforming algorithm for smart antenna system[J]. International Journal of Computer Applications, 2018, 179 (28): 34- 37.
6	SHI W L , LI Y S , YIN J W . Improved constraint NLMS algorithm for sparse adaptive array beamforming control applications[J]. Applied Computational Electromagnetics Society Journal, 2019, 34 (3): 419- 424.
7	杨志伟, 张攀, 陈颖, 等. 导向矢量和协方差矩阵联合迭代估计的稳健波束形成算法[J]. 电子与信息学报, 2018, 40 (12): 2874- 2879.
	YANG Z W , ZHANG P , CHEN Y , et al. Steering vector and covariance matrix joint iterative estimations for robust beamforming[J]. Journal of Electronics & Information Technology, 2018, 40 (12): 2874- 2879.
8	霍立平, 毛兴鹏, 石运梅, 等. 基于最小敏感度的广义线性自适应波束形成算法[J]. 系统工程与电子技术, 2019, 41 (3): 471- 475.
	HUO L P , MAO X P , SHI Y M , et al. Widely linear adaptive beamforming algorithm based on minimum sensitivity[J]. Systems Eggineering and Electronics, 2019, 41 (3): 471- 475.
9	唐寅州, 赵高泽. 改进粒子群优化算法自适应波束形成技术[J]. 舰船科学技术, 2018, 40 (9): 111- 115.
	TANG Y Z , ZHAO G Z . Adaptive beamforming technique based on a modified particle swarm optimization[J]. Ship Science and Technology, 2018, 40 (9): 111- 115.
10	CHAUDHARI P, SOATTO S. Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks[C]//Proc.of the IEEE Information Theory and Applications Workshop, 2018.
11	SHI W L , LI Y S , SUN L J , et al. Norm constrained noise-free algorithm for sparse adaptive array beamforming[J]. Applied Computational Electromagnetics Society Journal, 2019, 34 (5): 709- 715.
12	YAO Z , SAXE A M , ADVANI M S , et al. Energy-entropy competition and the effectiveness of stochastic gradient descent in machine learning[J]. Molecular Physics, 2018, 116 (21): 3214- 3223.
13	BOTTARELLI L , LOOG M . Gaussian process variance reduction by location selectior[J]. Pattern Recognition Letters, 2019, 125 (7): 727- 734.
14	LIU S T , JIANG H L , LIU L B , et al. Gradient descent using stochastic circuits for efficient training of learning machines[J]. IEEE Trans.on Computer-Aided Design of Integrated Circuits and Systems, 2018, 37 (11): 2530- 2541.
15	PHILIP C , JIM R , HUBERT D B . Estimating neural sources using a worst-case robust adaptive beamforming approach[J]. Biomedical Signal Processing and Control, 2019, 52, 330- 340.
16	KHAN Z A , CHAUDHARY N I , ZUBAIR S . Fractional stochastic gradient descent for recommender systems[J]. Electronic Markets, 2019, 29 (2): 275- 285.
17	JOHNSON R, ZHANG T. Accelerating stochastic gradient descent using predictive variance reduction[C]//Proc.of the 27th Annual Conference on Neural Information Processing Systems, 2013: 315-323.
18	YANG Z , WANG C , ZHANG Z M , et al. Random Barzilai-Borwein step size for mini-batch algorithms[J]. Engineering Applications of Artificial Intelligence, 2018, 72 (6): 124- 135.
19	MIN E X , LONG J , CUI J J . Analysis of the variance reduction in SVRG and a new acceleration method[J]. IEEE Access, 2018, 4, 16165- 16175.
20	CHEN L , ZHOU S S , ZHANG Z . SVRG for a non-convex problem using graduated optimization algorithm[J]. Journal of Intelligent & Fuzzy Systems, 2018, 4, 34 (1): 153- 165.
21	RAMAZANLI I, NGUYEN H, PHAM H, et al. Adaptive sampling distributed stochastic variance reduced gradient for heterogeneous distributed datasets[J].[2020-06-10]. http://arxiv.org/abs/2002.08528v1.
22	MING Y W , ZHAO Y W , WU C K , et al. Distributed and asynchronous stochastic gradient descent with variance reduction[J]. Neurocomputing, 2018, 281, 27- 36.
23	YANG Z , WANG C , ZHANG Z M , et al. Accelerated stochastic gradient descent with step size selection rules[J]. Signal processing, 2019, 159 (6): 171- 186.
24	LUO Z J , QIAN Y T . Stochastic sub-sampled Newton method with variance reduction[J]. International Journal of Wavelets, Multiresolution and Information Processing, 2019, 17 (6): 62- 68.

[1]	王春政, 胡明华, 杨磊, 赵征. 空中交通延误预测研究综述[J]. 系统工程与电子技术, 2022, 44(3): 863-874.
[2]	张心宇, 刘源, 宋佳凝. 基于LSTM神经网络的短期轨道预报[J]. 系统工程与电子技术, 2022, 44(3): 939-947.
[3]	刘奕彬, 王春阳, 宫健, 谭铭. 基于频控阵MIMO雷达的低复杂度稳健波束形成算法[J]. 系统工程与电子技术, 2022, 44(11): 3388-3396.
[4]	赵凡, 金虎. 基于GAN的通信干扰波形生成技术[J]. 系统工程与电子技术, 2021, 43(4): 1080-1088.
[5]	赵英健, 田波, 王春阳, 宫健, 谭铭. 基于频控阵的改进ESB波束形成算法[J]. 系统工程与电子技术, 2021, 43(11): 3151-3159.
[6]	宋波, 叶伟, 孟祥辉. 基于多智能体强化学习的动态频谱分配方法综述[J]. 系统工程与电子技术, 2021, 43(11): 3338-3351.
[7]	秦超, 高晓光, 陈大庆. 基于Bagging-Down SGD算法的分布式深度网络[J]. 系统工程与电子技术, 2019, 41(5): 1021-1027.
[8]	霍立平, 毛兴鹏, 石运梅, 贾绍文, 李广岩. 基于最小敏感度的广义线性自适应波束形成算法[J]. 系统工程与电子技术, 2019, 41(3): 471-475.
[9]	张菁, 何友, 彭应宁, 李刚. 新一代战斗机技术特征论证[J]. 系统工程与电子技术, 2018, 40(8): 1754-1759.
[10]	颛孙少帅, 杨俊安, 刘辉, 黄科举. 基于正强化学习和正交分解的干扰策略选择算法[J]. 系统工程与电子技术, 2018, 40(3): 518-525.
[11]	王邑, 孙金标, 肖明清, 罗继勋. 基于类型2区间模糊K近邻分类器的动态武器目标分配方法研究[J]. 系统工程与电子技术, 2016, 38(6): 1314-1319.
[12]	沈锋, 宋金阳. 基于容积卡尔曼滤波的约束恒模波束形成算法[J]. 系统工程与电子技术, 2016, 38(12): 2700-2704.
[13]	顾斌杰, 潘丰. 改进的v-支持向量回归机的v解路径算法[J]. 系统工程与电子技术, 2016, 38(1): 205-214.
[14]	陈成增，吴建新，王彤，吴亿锋. 基于鉴角曲线拟合的自适应单脉冲测角方法[J]. Journal of Systems Engineering and Electronics, 2013, 35(7): 1403-1408.
[15]	宋志杰, 王良. 单Chirp脉冲时域自适应波束形成和参数估计[J]. Journal of Systems Engineering and Electronics, 2012, 34(8): 1592-1596.

基于SVRGD的机载预警雷达自适应波束形成算法

Adaptive beamforming algorithm for airborne early warning radar based on SVRGD

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 24

相关文章 15

编辑推荐

Metrics

本文评价