基于无监督学习的均匀圆阵二维测向方法

doi:10.12305/j.issn.1001-506X.2026.02.05

摘要/Abstract

摘要：

为解决均匀圆阵二维超分辨测向问题，提出一种基于无监督深度神经网络的测向框架。首先，将二维波达方向估计问题转化为稀疏功率谱重构，采用深度神经网络建立空域协方差向量到二维稀疏谱的端到端映射。进一步，通过构造稀疏特征约束的损失函数，实现无监督模式下二维稀疏谱的空间结构特征学习。网络训练完成后，通过对网络输出进行聚类后处理获得二维角度的准确估计。仿真表明，所提方法在二维方向上实现了准确的角度估计，对未知场景具有较好的泛化性和鲁棒性，并且在低信噪比和小快拍数的情况下具有较高的估计精度。

关键词: 均匀圆阵, 超分辨二维测向, 深度神经网络, 无监督学习

Abstract:

An direction finding framework based on unsupervised deep neural networks is proposed for the uniform circular array super-resolution direction finding problem. First, a two-dimensional direction of arrival （DOA） estimation problem is transformed into sparse power spectrum reconstruction, where a deep neural network establishes an end-to-end mapping from spatial covariance vectors to sparse spectrum. Furthermore, a loss function with sparse feature constraints is constructed to learn two-dimensional spatial structural features of sparse spectrum in an unsupervised manner. Upon the completion of network training, accurate two-dimensional angle estimates are obtained through clustering post-processing of network outputs. Simulation results demonstrate that the proposed method achieves accurate angle estimation in two dimensions, excellent generalization and robustness in unknown scenarios, achieving high estimation accuracy in low signal-to-noise ratio and limited snapshots.

Key words: uniform circular array, super-resolution two-dimensional direction finding, deep neural network, unsupervised learning

中图分类号:

TN 911.7

吴双, 蒲泓宇, 付泰, 罗太元. 基于无监督学习的均匀圆阵二维测向方法[J]. 系统工程与电子技术, 2026, 48(2): 422-429.

Shuang WU, Hongyu PU, Tai FU, Taiyuan LUO. 2D direction finding method with uniform circular array based on unsupervised learning[J]. Systems Engineering and Electronics, 2026, 48(2): 422-429.

图/表 7

图1

图2

图3

图4

图5

图6

图7

参考文献 32

4	MALIOUTOV D, CETIN M, WILLSKY A S. A sparse signal reconstruction perspective for source localization with sensor arrays[J]. IEEE Trans. on Signal Processing, 2005, 53 (8): 3010- 3022. doi: 10.1109/TSP.2005.850882
5	YANG Z, XIE L H, ZHANG C S. Off-grid direction of arrival estimation using sparse bayesian inference[J]. IEEE Trans. on Signal Processing, 2013, 61 (1): 38- 43. doi: 10.1109/TSP.2012.2222378
6	STOICA P, BABU P, LI J. SPICE: a sparse covariance-based estimation method for array processing[J]. IEEE Trans. on Signal Processing, 2011, 59 (2): 629- 638. doi: 10.1109/TSP.2010.2090525
7	WANG W, WU R. High resolution direction of arrival （DOA） estimation based on improved orthogonal matching pursuit （OMP） algorithm by iterative local searching[J]. Sensors, 2013, 13 (9): 11167- 11183. doi: 10.3390/s130911167
8	LIANG J, LIU D. Joint elevation and azimuth direction finding using L-shaped array[J]. IEEE Trans. on Antennas and Propagation, 2010, 58 (6): 2136- 2141. doi: 10.1109/TAP.2010.2046838
9	梁浩, 崔琛, 余剑. 基于ESPRIT算法的十字型阵列MIMO雷达降维DOA估计[J]. 电子与信息学报, 2016, 38 (1): 80- 89.
	LIANG H, CUI C, YU J. Reduced-dimensional DOA estimation based on ESPRIT algorithmin monostatic MIMO radar with cross array[J]. Journal of Electronics & Information Technology, 2016, 38 (1): 80- 89.
10	常虹, 赵国庆. 适用于宽带接收阵列的无模糊二维DOA估计[J]. 北京邮电大学学报, 2010, 33 (5): 47- 50. doi: 10.3969/j.issn.1007-5321.2010.05.010
	CHANG H, ZHAO G Q. Unambiguous two dimensional DOA estimation suitable for wideband Receiving array[J]. Journal of Beijing University of Posts and Telecommunications, 2010, 33 (5): 47- 50. doi: 10.3969/j.issn.1007-5321.2010.05.010
11	崔开博, 黄敬健, 陈曦, 等. 基于均匀圆阵模式空间和多重旋转不变子空间算法的完备二维DOA估计算法[J]. 系统工程与电子技术, 2017, 39 (12): 2646- 2651. doi: 10.3969/j.issn.1001-506X.2017.12.02
	CUI K B, HUANG J J, CHEN X, et al. Closed form 2D DOA estimation based on mode space of uniform circular arrays and multiple invariance ESPRIT[J]. Systems Engineering and Electronics, 2017, 39 (12): 2646- 2651. doi: 10.3969/j.issn.1001-506X.2017.12.02
12	孟祥天, 经哲涵, 曹丙霞, 等. 基于实值子空间线性变换的非均匀圆形阵列高效二维测向方法[J]. 电子与信息学报, 2024, 46 (11): 4328- 4334. doi: 10.11999/JEIT240188
	MENG X T, JING Z H, CAO B X, et al. Efficient 2-D direction finding based on the real-valued subspace linear transformation with nonuniform circular array[J]. Journal of Electronics & Information Technology, 2024, 46 (11): 4328- 4334. doi: 10.11999/JEIT240188
13	蒋林峰, 宁运, 柳文, 等. 均匀圆阵特征矢量重构Root-MUSIC快速解相干算法[J]. 湘潭大学学报（自然科学版）, 2024, 46 (5): 39- 47.
	JIANG L F, NING Y, LIU W, et al. Root-MUSIC fast decoherence algorithm for uniform circular array eigenvector reconstruction[J]. Journal of Xiangtan University (Natural Science Edition), 2024, 46 (5): 39- 47.
14	汪亚东, 姜迪, 孙建东, 等. 基于模式空间-极化平滑的均匀圆阵解相干算法[J]. 制导与引信, 2024, 45 (3): 1- 7. doi: 10.3969/j.issn.1671-0576.2024.03.001
	WANG D Y, JIANG D, SUN J D, et al. Uniform circular array decoherence algorithm based on mode space-polarization smoothing[J]. Guidance and Fuse, 2024, 45 (3): 1- 7. doi: 10.3969/j.issn.1671-0576.2024.03.001
15	MATHEWS C P, ZOLTOWSKI M D. Eigenstructure techniques for 2-D angle estimation with uniform circular arrays[J]. IEEE Trans. on Signal Processing, 1994, 42 (9): 2395- 2407. doi: 10.1109/78.317861
16	ELBIR A M, TUNCER T E. 2-D DOA and mutual coupling coefficient estimation for arbitrary array structures with single and multiple snapshots[J]. Digital Signal Processing, 2016, 54, 75- 86. doi: 10.1016/j.dsp.2016.03.011
17	SU X L, LIU Z, LIU T P, et al. A Sparse representation method for coherent sources angle estimation with uniform circular array[J]. International Journal of Antennas and Propagation, 2019, 2019, 1- 9.
18	吴敏, 黎子皓, 郝程鹏, 等. 基于压缩感知的低复杂度超分辨角度估计方法[J]. 系统工程与电子技术, 2024, 46 (6): 1831- 1837.
	WU M, LI Z H, HAO C P, et al. Low complexity super-resolution angle estimation method based on compressive sensing[J]. Systems Engineering and Electronics, 2024, 46 (6): 1831- 1837.
19	郎荣玲, 唐泽文. 范数在稀疏重构类DOA估计领域的应用[J]. 高等数学研究, 2024, 27 (4): 119- 121. doi: 10.3969/j.issn.1008-1399.2024.04.034
	LANG R L, TANG Z W. The application of norm in the field of sparse reconstruction class DOA Estimation[J]. Advanced Mathematics Research, 2024, 27 (4): 119- 121. doi: 10.3969/j.issn.1008-1399.2024.04.034
20	HUANG H J, YANG J, HUANG H, et al. Deep learning for super-resolution channel estimation and DOA estimation based massive MIMO system[J]. IEEE Trans. on Vehicular Technology, 2018, 67 (9): 8549- 8560. doi: 10.1109/TVT.2018.2851783
21	WU L L, LIU Z M, HUANG Z T. Deep convolution network for direction of arrival estimation with sparse prior[J]. IEEE Signal Processing Letters, 2019, 26 (11): 1688- 1692. doi: 10.1109/LSP.2019.2945115
22	GUO Y, ZHANG Z, HUANG Y Z, et al. DOA estimation method based on cascaded neural network for two closely spaced Sources[J]. IEEE Signal Processing Letters, 2020, 27, 570- 574. doi: 10.1109/LSP.2020.2984914
23	FEINTUCH S, TABRIKIAN J, BILIK I, et al. Neural-network-based DOA estimation in the presence of non-gaussian interference[J]. IEEE Trans. on Aerospace and Electronic Systems, 2024, 60 (1): 119- 132. doi: 10.1109/TAES.2023.3268256
1	KRIM H, VIBERG M. Two decades of array signal processing research: the parametric approach[J]. IEEE Signal Processing Magazine, 1996, 13 (4): 67- 94. doi: 10.1109/79.526899
2	SCHMIDT R O. Multiple emitter location and signal parameter estimation[J]. IEEE Trans. on Antennas and Propagation, 1986, 34 (3): 276- 280. doi: 10.1109/TAP.1986.1143830
3	ROY R, KAILATH T. ESPRIT-estimation of signal parameters via rotational invariance techniques[J]. IEEE Trans. on Acoustics, Speech, and Signal Processing, 1989, 37 (7): 984- 995. doi: 10.1109/29.32276
24	吴双, 袁野, 马育红. 用于大规模深度卷积分类网络DOA估计的标签分解方法[J]. 信号处理, 2021, 37 (1): 1- 10.
	WU S, YUAN Y, MA Y H, et al. Deep convolution neural network label decomposition method for large scale DOA estimation[J]. Journal of Signal Processing, 2021, 37 (1): 1- 10.
25	LIU Z M, ZHANG C W, YU P S. Direction-of-arrival estimation based on deep neural networks with robustness to array imperfections[J]. IEEE Trans. on Antennas and Propagation, 2018, 66 (12): 7315- 7327. doi: 10.1109/TAP.2018.2874430
26	CHEN P, CHEN Z M, LIU L, et al. SDOA-Net: an efficient deep-learning-based DOA estimation network for imperfect array[J]. IEEE Trans. on Instrumentation and Measurement, 2024, 73
27	YUAN Y, WU S, WU M, et al. Unsupervised learning strategy for direction-of-arrival estimation network[J]. IEEE Signal Processing Letters, 2021, 28, 1450- 1454. doi: 10.1109/LSP.2021.3096117
28	HARTIGAN J A, WONG M A. A k-means clustering algorithm[J]. Journal of the Royal Statistical Society, 2013, 28 (1): 100- 108.
29	AKAIKE H. A new look at the statistical model identification[J]. IEEE Trans. on Automatic Control, 1974, 19 (6): 716- 723. doi: 10.1109/TAC.1974.1100705
30	CHEN W, WONG K M, REILLY J P. Detection of the number of signals: a predicted eigen-threshold approach[J]. IEEE Trans. on Signal Processing, 1991, 39 (5): 1088- 1098. doi: 10.1109/78.80959
31	SHAN T J, PAULRAJ A, KAILATH T. On smoothed rank profile tests in eigenstructure methods for directions-of-arrival estimation[J]. IEEE Trans. on Acoustics speech and Signal Process, 1987, 35 (10): 1377- 1385. doi: 10.1109/TASSP.1987.1165048
32	WU H T, YANG J F, CHEN F K. Source number estimators using transformed gerschgorin radii[J]. IEEE Trans. on Signal Processing, 1995, 43 (6): 1325- 1333. doi: 10.1109/78.388844

[1]	张瑞斌, 朱梦韬, 李云杰. 对调制识别网络隐身的雷达发射信号生成方法[J]. 系统工程与电子技术, 2024, 46(7): 2256-2268.
[2]	李震, 何华锋, 周涛, 张鑫, 韩晓斐, 王栗沅. 基于UCA-FDA雷达距离补偿的DOA估计方法[J]. 系统工程与电子技术, 2024, 46(6): 1967-1974.
[3]	崔永生, 詹亚锋, 陈泰伊, 方鑫. 基于DNN的低复杂度联合解调译码迭代同步算法[J]. 系统工程与电子技术, 2024, 46(11): 3893-3900.
[4]	曲熠, 陈莹. 基于边缘强化的无监督单目深度估计[J]. 系统工程与电子技术, 2024, 46(1): 71-79.
[5]	沈季, 万显荣, 易建新, 刘燕, 程丰. 复杂干扰场景下的稳健自适应波束形成[J]. 系统工程与电子技术, 2023, 45(4): 941-949.
[6]	邓嘉宁, 李海旭, 安强林, 沙恩来, 王泽, 吴宇. 基于指标关联的舰载机出动架次率预测方法[J]. 系统工程与电子技术, 2023, 45(11): 3507-3515.
[7]	王冠, 茹海忠, 张大力, 马广程, 夏红伟. 弹性高超声速飞行器智能控制系统设计[J]. 系统工程与电子技术, 2022, 44(7): 2276-2285.
[8]	刘步花, 丁丹, 杨柳, 薛乃阳, 刘仲谦. 基于DNN的无人机数据OFDM传输技术[J]. 系统工程与电子技术, 2022, 44(2): 696-702.
[9]	许耀华, 朱成龙, 王翊, 蒋芳, 丁梦琴, 王慧平. 基于神经网络的高并行大规模MIMO信号检测算法[J]. 系统工程与电子技术, 2022, 44(12): 3843-3849.
[10]	胥彪, 李翔, 李爽, 张金鹏. 基于非线性模型预测控制的火星大气进入智能制导方法[J]. 系统工程与电子技术, 2021, 43(7): 1943-1953.
[11]	崔邦彦, 田润澜, 王东风, 崔钢, 石静苑. 基于注意力机制和改进CLDNN的雷达辐射源识别[J]. 系统工程与电子技术, 2021, 43(5): 1224-1231.
[12]	阳榴, 朱卫纲, 吕守业, 马爽. 面向非协作多功能雷达的波形单元提取方法[J]. 系统工程与电子技术, 2021, 43(10): 2843-2850.
[13]	汪鹏, 熊钊, 于俊鹏, 田勇, 李万春. 基于均匀圆阵伪协方差矩阵的单快拍测向方法[J]. 系统工程与电子技术, 2021, 43(10): 2812-2818.
[14]	孙艺聪, 田润澜, 王晓峰, 董会旭, 戴普. 基于改进CLDNN的辐射源信号识别[J]. 系统工程与电子技术, 2021, 43(1): 42-47.
[15]	苏志刚, 陈欣然, 郝敬堂. 基于粒子群优化的圆阵列波束形成方法[J]. 系统工程与电子技术, 2020, 42(7): 1449-1454.