RCS Reduction Method for Sparse Array Dual-Subarray Based on MAAM-LKN Model

JI Lixia; CHEN Yiqiao; REN Zhigang; ZENG Hao

doi:10.12263/DZXB.20250961

您当前的位置：

首页 >

文章列表页 >

RCS Reduction Method for Sparse Array Dual-Subarray Based on MAAM-LKN Model

更新时间：2026-03-26

- RCS Reduction Method for Sparse Array Dual-Subarray Based on MAAM-LKN Model
- ACTA ELECTRONICA SINICA Pages: 1-9(2026)
- 作者机构：
  
  1.重庆理工大学电气与电子工程学院，重庆 400054
  2.西南电子技术研究所，四川成都 610036
  3.重庆大学微电子与通信工程学院，重庆 400044
- 作者简介：
- 基金信息：
  
  Research Start-up Foundation of Chongqing University of Technology(2025ZDZ025)
- DOI：10.12263/DZXB.20250961
  CLC： TN828;
- Received：15 November 2025，
  
  Accepted：10 December 2025，
  
  Online First：26 March 2026，
- 稿件说明：
移动端阅览
JI Lixia, CHEN Yiqiao, REN Zhigang, et al. RCS Reduction Method for Sparse Array Dual-Subarray Based on MAAM-LKN Model[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-9.
DOI：

JI Lixia, CHEN Yiqiao, REN Zhigang, et al. RCS Reduction Method for Sparse Array Dual-Subarray Based on MAAM-LKN Model[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-9. DOI： 10.12263/DZXB.20250961.

摘要

阵列天线雷达散射截面（Radar Cross Section，RCS）等于天线散射单元因子与散射阵因子的乘积。通常采用稀疏阵列布局优化的方法，实现对散射阵因子峰值的抑制。近年来，基于深度学习的稀疏阵列RCS缩减方法有效提高了阵面的实时隐身性能。稀疏优化难以机械地实时拆除阵列中的天线，通常是通过负载匹配或自动相消的方法缩减无需工作的阵元RCS来实现，进而等效为“删除”阵元。但无论是负载匹配法，还是自动相消法，都无法使关闭阵元的RCS缩减至零，通常只能将其缩减到一个较小的值。然而，现有的基于深度学习的稀疏阵列RCS缩减方法都是针对关闭阵元RCS为零的场景，因此，已有方法不能适用于实际应用场景。为了解决该问题，提出了一种基于多模态与增强注意力机制的轻核网络（Light Kernel Network Based on Multimodal and Augmentation Attention Mechanism，MAAM-LKN）模型的稀疏阵列双子阵RCS缩减方法。具体而言，考虑到关闭阵元RCS通常不为零，引入了关闭阵元RCS因子，建立了稀疏阵列双子阵优化的问题模型与目标函数，利用MAAM-LKN模型同时优化工作子阵与关闭子阵的阵列布局，从而缩减工作子阵与关闭子阵的RCS，最终实现整个阵面的RCS最小。此外，由于现有用于稀疏阵列RCS缩减的神经网络模型缺乏对重要信息的关注，在MAAM-LKN模型中，设计了增强注意力机制，根据特征的重要程度对特征进行加权，解决了特征传播过程中重点特征不够突出的问题，同时，为了提高模型的理解能力，引入多模态思想，实现更有效的重点特征提取与感知。仿真结果表明：在不同关闭阵元RCS因子下，双子阵优化与单子阵RCS优化相比，都能够有效提升稀疏阵列天线的RCS缩减性能，RCS最大缩减值能够提升2.72 dB以上，RCS平均缩减值能够提升0.19 dB以上；当关闭阵元RCS不为零时，MAAM-LKN模型的准确率为91.09%，RCS缩减均值为5.9 dB，均高于其他神经网络模型，同时保持模型复杂度相当。

Abstract

The radar cross section (RCS) of an array antenna equals the product of the antenna scattering element factor and the array factor. Typically

sparse array arrangement optimization is used to suppress the peak value of the scattering array factor. In recent years

deep learning-based methods for sparse array RCS reduction have effectively improved the real-time stealth performance. However

sparse optimization cannot mechanically remove the elements from the array in real time. The load matching and active cancellation methods are used as the equivalent method to delete the passive elements

but these methods cannot reduce the RCS of passive elements to zero

they can only reduce it to a small value. Existing deep learning-based sparse array RCS reduction methods are designed for scenarios where the RCS of passive elements is zero. So

these existing methods unsuitable for practical applications. To address this issue

this paper proposes a sparse array dual-subarray RCS reduction method based on a light kernel network with multimodal and augmentation attention mechanism (MAAM-LKN). Specifically

considering that the RCS of passive elements is usually non-zero

a passive RCS factor of element is introduced. A problem model and objective function for sparse array dual-subarray optimization are established

and the MAAM-LKN model simultaneously optimizes the array arrangements of both the active and passive subarrays. This reduces the RCS of both subarrays and ultimately minimizes the overall RCS of the array. Moreover

since existing neural network models for sparse array RCS reduction lack focus on important information

an augmented attention mechanism is designed in the MAAM-LKN model to weight features according to their importance. This addresses the issue of insufficient emphasis on key features during feature propagation. Additionally

to enhance the model’s comprehension capability

the multimodal is introduced to achieve more effective extraction and perception of key features. Simulation results show that under different passive element RCS factor values

dual-subarray optimization can effectively improve the RCS reduction performance compared to single-subarray RCS optimization. The maximum RCS reduction value can be improved by more than 2.72 dB

and the average RCS reduction value can be improved by more than 0.19 dB. When the RCS of passive elements is non-zero

the MAAM-LKN model achieves an accuracy of 91.09% and an average RCS reduction of 5.9 dB

both higher than other neural network models

while maintaining comparable model complexity.

关键词

Keywords

references

徐鹏颖 , 蔺卡宾 , 韩宝庆 , 等 . 阵列天线电磁-结构-热耦合理论: 现在与未来 [J ] . 电子学报 , 2022 , 50 ( 12 ): 2817 - 2853 .

Xu Pengying , Lin Kabin , Han Baoqing , et al . Electromagnetic-structural-thermal coupling theory for array antenna: Present and future [J ] . Acta Electronica Sinica , 2022 , 50 ( 12 ): 2817 - 2853 . (in Chinese)

Ji Lixia , Ren Zhigang , Chen Yiqiao , et al . Large-scale sparse antenna array optimization for RCS reduction with an AM-FCSN [J ] . IEEE Sensors Journal , 2025 , 25 ( 3 ): 5782 - 5794 .

Zhang Yixuan , Jiao Yongchang , Zhu Mingda , et al . Wideband near-field RCS measurement techniques with improved far-field RCS prediction accuracies [J ] . IEEE Transactions on Instrumentation and Measurement , 2023 , 72 : 8000404 .

Ji Lixia , Mei Ke , Chen Yiqiao , et al . Radar cross section reduction of antenna array with LK-ResNet [J ] . IEEE Antennas and Wireless Propagation Letters , 2023 , 22 ( 12 ): 2993 - 2997 .

涂建军 , 马丁 . 基于粒子群结构寻优的电磁隐身微网格超表面 [J ] . 电子学报 , 2023 , 51 ( 11 ): 3262 - 3270 .

Tu Jianjun , Ma Ding . Electromagnetic stealth micro-grid metasurface based on particle swarm structure optimization [J ] . Acta Electronica Sinica , 2023 , 51 ( 11 ): 3262 - 3270 . (in Chinese)

Wang J , Choi C , Moore R . Precision experimental characterization of the scattering and radiation properties of antennas [J ] . IEEE Transactions on Antennas and Propagation , 1982 , 30 ( 1 ): 108 - 112 .

Elbir A M , Mishra K V . Joint antenna selection and hybrid beamformer design using unquantized and quantized deep learning networks [J ] . IEEE Transactions on Wireless Communications , 2020 , 19 ( 3 ): 1677 - 1688 .

Ha T D , Zhu Liang , Alsaab N , et al . Optically transparent metasurface radome for RCS reduction and gain enhancement of multifunctional antennas [J ] . IEEE Transactions on Antennas and Propagation , 2023 , 71 ( 1 ): 67 - 77 .

EL-Sewedy M F , Abdalla M A . A monostatic and bistatic RCS reduction using artificial magnetic conductor metasurface [J ] . IEEE Transactions on Antennas and Propagation , 2023 , 71 ( 2 ): 1988 - 1992 .

Yu Yufeng , Yu Weiliang , Xie Guotai , et al . Wideband RCS reduction of slot array antenna utilizing 3-D absorptive frequency-selective structure [J ] . IEEE Antennas and Wireless Propagation Letters , 2022 , 21 ( 1 ): 64 - 68 .

Zhang Shun , Yang Xuesong , Chen Bingjie , et al . Miniaturized wideband ±45° dual-polarized metasurface antenna by loading quasi-fractal slot [J ] . IEEE Antennas and Wireless Propagation Letters , 2023 , 22 ( 4 ): 893 - 897 .

Nakamoto N , Takahashi T , Fukasawa T , et al . RCS synthesis of array antenna with circulators and phase shifters and measurement method for deterministic RCS reduction [J ] . IEEE Transactions on Antennas and Propagation , 2021 , 69 ( 1 ): 135 - 145 .

Lu Bao , Gong Shuxi , Zhang Shuai , et al . Optimum spatial arrangement of array elements for suppression of grating-lobes of radar cross section [J ] . IEEE Antennas and Wireless Propagation Letters , 2010 , 9 : 114 - 117 .

Ji Lixia , Ren Zhigang , Chen Yiqiao , et al . RCS reduction for multiple-sparsity-rate arrays with a feature multitask network [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2025 , 61 ( 2 ): 3610 - 3625 .

Ji Lixia , Chen Yiqiao , Ren Zhigang , et al . Transfer learning for RCS reduction of antenna arrays across arbitrary frequency bands [J ] . IEEE Transactions on Antennas and Propagation , 2025 , 73 ( 10 ): 8104 - 8115 .

张玉洪 , 保铮 . 最佳非均匀间隔稀布阵列的研究 [J ] . 电子学报 , 1989 , 17 ( 4 ): 81 - 87 .

Zhang Yuheng , Bao Zheng . Study of optimum thinning arrays by nonuniform spacings [J ] . Acta Electronica Sinica , 1989 , 17 ( 4 ): 81 - 87 . (in Chinese)

Han Wenqi , Geng Jie , Xu Zhengyi , et al . Multimodal heterogeneous hypergraph learning for incomplete multimodal semantic segmentation of remote sensing images [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2025 , 63 : 5639915 .

Sun Kun , Dong Fuxuan , Liu Wenxin , et al . Hyperspectral image classification with spatial-spectral-channel 3-D attention and channel attention [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2025 , 63 : 4412314 .

Zadeh S G , Schmid M . Bias in cross-entropy-based training of deep survival networks [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2021 , 43 ( 9 ): 3126 - 3137 .

Cheng Tianhao , Wang Buhong , Wang Zhen , et al . Lightweight CNNs-based interleaved sparse array design of phased-MIMO radar [J ] . IEEE Sensors Journal , 2021 , 21 ( 12 ): 13200 - 13214 .

Shi Yang , Ding Chenling , Li Shuai , et al . New RNN algorithms for different time-variant matrix inequalities solving under discrete-time framework [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2025 , 36 ( 3 ): 5244 - 5257 .

Fan Yuqi , Liu Jiahao , Ye Han , et al . TA-LSTM: A time and attribute aware LSTM for deep flight track clustering [J ] . IEEE Transactions on Aerospace and Electronic Systems , 2023 , 59 ( 5 ): 7047 - 7060 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Object Detection Based on EIMYOLO for High-Resolution Remote Sensing Images

Single-Image High Dynamic Range Reconstruction Based on Multi-Attention and Perceptual Weighted Learning

Research of Video Dynamic Quality Evaluation Based on Human Perception and Memory

An In-Vehicle Interaction Speech Enhancement and Recognition Method Based on Lightweight Models in Complex Environment

MoGE: Graph Context Enhanced Multi-Task Recommendation Method

Related Author

CAO Feng

ZENG Ke-wen

LI De-yu

LUO Xi-zhao

TAO Chong-ben

KE De-zhang

CHEN Ye-yao

XU Hai-yong

Related Institution

School of Information and Technology, Shanxi University

School of Computer Science and Technology, Soochow University

School of Electronics and Information Engineering, Suzhou University of Science and Technology

Faculty of Information Science and Engineering, Ningbo University

School of Mathematics and Statistics, Ningbo University

⁰