神经网络辅助双频U型槽贴片天线优化

doi:10.16180/j.cnki.issn1007-7820.2025.07.005

电子科技 ›› 2025, Vol. 38 ›› Issue (7): 34-39.doi: 10.16180/j.cnki.issn1007-7820.2025.07.005

神经网络辅助双频U型槽贴片天线优化

张斌¹^,², 丁海兵¹(), 王晶¹^,², 薛谦忠¹^,²

1.中国科学院空天信息创新研究院,北京 100190
2.中国科学院大学电子电气与通信工程学院,北京 100408

收稿日期:2023-12-29 修回日期:2024-01-27 出版日期:2025-07-15 发布日期:2025-07-10
通讯作者: 丁海兵(1977-),男,E-mail:dinghb@aircas.ac.cn,博士,研究员。研究方向:微波毫米波电子器件、毫米波天线及应用。
作者简介:张斌(1999-),男,硕士研究生。研究方向:天线设计与优化。
王晶(1998-),女,博士研究生。研究方向:天线理论及应用。
基金资助:
国家自然科学基金(12075247)

Dual-Band U-Slot Patch Antenna Optimization Using Neural Network Model

ZHANG Bin¹^,², DING Haibing¹(), WANG Jing¹^,², XUE Qianzhong¹^,²

1. Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100190,China
2. School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Science,Beijing 100408,China

Received:2023-12-29 Revised:2024-01-27 Online:2025-07-15 Published:2025-07-10
Supported by:
National Natural Science Foundation of China(12075247)

摘要/Abstract

摘要： 为了提高天线设计效率,利用机器学习辅助天线优化设计,文中基于PSO-BPNN (Particle Swarm Optimization-Back Propagation Neural Network)模型设计了一款双频U型槽贴片天线,其工作频率覆盖IEEE802.11y (3.65 GHz)和IEEE802.11a (5.20 GHz)两个频段。将所设计的天线与基于PSO算法设计的天线进行对比,根据仿真模型加工天线实物,并进行了测试实验。结果表明,在5.20 GHz谐振频率处,PSO-BPNN模型和PSO模型算法设计的天线回波损耗接近,而在3.65 GHz谐振频率处,基于PSO-BPNN模型设计的天线回波损耗为-22.65 dB,阻抗带宽为0.205 GHz,相比PSO算法设计的回波损耗和阻抗带宽分别提升了47.85%和11.41%。测试结果表明,基于PSO-BPNN模型算法设计的天线辐射特性与实测结果吻合较好。

关键词: BP神经网络, 粒子群算法, 天线优化设计, 双频, 贴片天线, U型槽, 电磁仿真, 回波损耗

Abstract:

In order to improve the efficiency of antenna design, a double-frequency U-slot patch antenna based on PSO-BPNN (Particle Swarm Optimization-Back Propagation Neural Network) model is designed using machine learning to assist antenna optimization design. The operating frequency covers IEEE802.11y (3.65 GHz) and IEEE802.11a (5.20 GHz), and is compared with the antenna designed based on PSO algorithm. According to the simulation model, the antenna is fabricated and tested. The results show that at the resonant frequency of 5.20 GHz, the antenna return loss designed by PSO-BPNN model and PSO model algorithm is close. At the resonant frequency of 3.65 GHz, the return loss of the antenna designed based on the PSO-BPNN model is -22.65 dB and the impedance bandwidth is 0.205 GHz, which is 47.85% and 11.41% higher than that designed by the PSO algorithm, respectively. Test results reveal that the radiation characteristics of the antenna designed based on the PSO-BPNN model algorithm are in good agreement with the measured results.

Key words: BP neural network, particle swarm algorithm, antenna optimization design, dual frequency, patch antenna, U-slot, electromagnetic simulation, return loss

中图分类号:

TN82

张斌, 丁海兵, 王晶, 薛谦忠. 神经网络辅助双频U型槽贴片天线优化[J]. 电子科技, 2025, 38(7): 34-39.

ZHANG Bin, DING Haibing, WANG Jing, XUE Qianzhong. Dual-Band U-Slot Patch Antenna Optimization Using Neural Network Model[J]. Electronic Science and Technology, 2025, 38(7): 34-39.

图/表 10

图1

图2

图3

表1

图4

表2

表3

图5

图6

图7

参考文献 19

[1]	Radavaram S, Pour M. Wideband radiation reconfigurable microstrip patch antenna loaded with two inverted U-Slots[J]. IEEE Transactions on Antennas and Propagation, 2019, 67(3):1501-1508.
[2]	Fan T Q, Jiang B T, Liu R Z, et al. A novel double U-Slot microstrip patch antenna design for low-profile and broad bandwidth applications[J]. IEEE Transactions on Antennas and Propagation, 2022, 70(4):2543-2549.
[3]	Misilamni H M, Naous T, Khatib S K. A review on the design and optimization of antennas using machine learning algorithms and techniques[J]. International Journal of RF and Microwave Computer-Aided Engineering, 2020, 30(10):1-28.
[4]	Zhang J P, Xu J W, Chen Q, et al. Machine-learning-assisted antenna optimization with data augmentation[J]. IEEE Antennas and Wireless Propagation Letters, 2023, 22(8):1932-1936.
[5]	Wang Z B, Fang S J, Wang Q, et al. An ANN-based synthesis model for the single-feed circularly-polarized square microstrip antenna with truncated corners[J]. IEEE Transactions on Antennas and Propagation, 2012, 60(12):5989-5992.
[6]	Sharma Y, Zhang H H, Xin H. Machine learning techniques for optimizing design of double T-shaped monopole antenna[J]. IEEE Transactions on Antennas and Propagation, 2020, 68(7):5658-5663.
[7]	Shi D, Lian C, Cui K Y, et al. An intelligent antenna synthesis method based on machine learning[J]. IEEE Transactions on Antennas and Propagation, 2022, 70(7):4965-4976.
[8]	Mcculloch W S, Pitts W. A logical calculus of the ideas immanent in nervous activity[J]. Bulletin of Mathematical Biology, 1990, 52(1-2):99-115.
[9]	Anuradha D, Patnkaik A, Sinha S N. Design of custom-made fractal multi-band antennas using ANN-PSO[J]. IEEE Antennas and Propagation Magazine, 2011, 53(4):94-101.
[10]	李文华, 牛国波, 刘羽佳. 基于遗传算法优化BP神经网络的液压系统故障诊断[J]. 机床与液压, 2023, 51(8):159-164.
	Li Wenhua, Niu Guobo, Liu Yujia. Hydraulic system fault diagnosis based on genetic algorithm optimized BP neural network[J]. Machine Tool and Hydraulics, 2023, 51(8):159-164.
[11]	丁慧慧, 邵婷婷, 乔曦. 基于BP神经网络的小角度井斜方位角误差补偿研究[J]. 电子科技, 2022, 35(5):33-37.
	Ding Huihui, Shao Tingting, Qiao Xi. Research on azimuth error compensation based on BP neural network at small-angle deviation[J]. Electronic Science and Technology, 2022, 35(5):33-37.
[12]	周志华. 机器学习[M]. 北京: 清华大学出版社, 2016:101-106.
	Zhou Zhihua. Machine learning[M]. Beijing: Tsinghua University Press, 2016:101-106.
[13]	王闪闪. 基于群智能算法的神经网络建模研究[J]. 电子科技, 2017, 30(4):56-59.
	Wang Shanshan. Research of neural network model based on swarm intelligence algorithm[J]. Electronic Science and Technology, 2017, 30(4):56-59.
[14]	黄泽明, 单志勇. 基于火烈鸟搜索算法的天线优化设计[J]. 电子科技, 2024, 37(9):14-19.
	Huang Zeming, Shan Zhiyong. Antenna optimal design based on flamingo search algorithm[J]. Electronic Science and Technology, 2024, 37(9):14-19.
[15]	周驰, 高海兵, 高亮, 等. 粒子群优化算法[J]. 计算机应用研究, 2003, 20(12):7-11.
	Zhou Chi, Gao Haibing, Gao Liang, et al. Particle swarm optimization algorithm[J]. Application Research of Computers, 2003, 20(12):7-11.
[16]	Tian Y B, Zhang S L, Li J Y. Modeling resonant frequency of microstrip antenna based on neural network ensemble[J]. International Journal of Numerical Modelling-Electronic Networks Devices and Fields, 2011, 24(1):77-86.
[17]	Dhaliwai B S, Pattnaik S S. Development of PSO-ANN ensemble hybrid algorithm and its application in compact crown circular fractal patch antenna design[J]. Wireless Personal Communications, 2017, 96(1):135-152.
[18]	Dong J, Qin W W, Wang M. Fast multi-objective optimization of multi-parameter antenna structures based on improved BPNN surrogate model[J]. IEEE Access, 2019(7):77692-77701.
[19]	潘昊, 侯清兰. 基于粒子群优化算法的BP网络学习研究[J]. 计算机工程与应用, 2006(16):41-43,66.
	Pan Hao, Hou Qinglan. A BP neural networks learning algorithm research based on particle swarm optimizer[J]. Computer Engineering and Applications, 2006(16):41-43,66.

结构参数	数值/mm	结构参数	数值/mm
L_g	50.00	V	1.25
W_g	55.00	U_l	8.00~9.00
L	23.00	U_w	12.00~14.00
W	27.00	U_d	6.00~7.00
X_f	0.00	R_l	3.00~4.00
Y_f	2.25	R_w	17.00~19.00

网络模型类别	MSE最小值	MSE平均值
BPNN	0.061 32	0.067 47
PSO-BPNN	0.055 11	0.061 96

优化方法	U_l/mm	U_w/mm	U_d/mm	R_l/mm	R_w/mm
PSO	8.7	13.0	6.9	3.0	17.7
PSO-BPNN	8.5	13.0	6.5	3.5	18.0

神经网络辅助双频U型槽贴片天线优化

Dual-Band U-Slot Patch Antenna Optimization Using Neural Network Model

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 19

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	杨远星, 丁绪东, 王俊超, 吴东. 基于Smith预估器的制冷系统BP神经网络PID控制算法[J]. 电子科技, 2025, 38(8): 42-48.
[2]	张海博, 潘鹏程, 郑峰. 基于改进鲸鱼算法优化的接地网腐蚀速率预测[J]. 电子科技, 2025, 38(5): 8-14.
[3]	叶翔宇, 林晓会, 丁江乔, 解维坤. 基于优化BPNN的FPGA内嵌高速接口总抖动预测方法[J]. 电子科技, 2025, 38(2): 70-77.
[4]	满延露, 刘敏. 基于WLS-AUKF混合算法的主动配电网联合状态估计[J]. 电子科技, 2025, 38(2): 93-102.
[5]	黄泽明, 单志勇. 基于火烈鸟搜索算法的天线优化设计[J]. 电子科技, 2024, 37(9): 14-19.
[6]	袁傲, 齐金鹏, 贾灿, 薛宇鑫, 郭阳阳. 一种基于深度学习的时序病变数据段分类方法[J]. 电子科技, 2024, 37(6): 84-91.
[7]	林翔宇, 曾卫华. 双频一体化超宽带探地雷达天线设计[J]. 电子科技, 2024, 37(4): 25-29.
[8]	李婷婷, 娄柯, 王园, 徐华超. 基于多目标粒子群的电动汽车优化充电策略[J]. 电子科技, 2024, 37(3): 51-56.
[9]	王泽学, 李玉松, 龙浩骑, 明玉周. 基于电磁仿真的冷坩埚电源参数优化[J]. 电子科技, 2024, 37(11): 70-77.
[10]	张大桂,周志峰,张怡. 基于遗传算法的平面麦克风阵列构型优化方法[J]. 电子科技, 2023, 36(7): 24-31.
[11]	李帅,杨健,王涛,黄鑫,麻士峰. 一种低功耗射频能量采集系统的仿真与分析[J]. 电子科技, 2023, 36(6): 50-56.
[12]	蔺琳,王万雄. 基于EMD-GWO-SVR组合模型的短期风速预测[J]. 电子科技, 2023, 36(5): 1-8.
[13]	刘金芝,张会林,马立新,王昊,唐政. 考虑可平移负荷的综合能源系统动态优化调度策略[J]. 电子科技, 2023, 36(4): 78-83.
[14]	王欣阳,王瑞阳,魏云冰. 基于算术优化算法的低压配电网故障区段定位方法[J]. 电子科技, 2023, 36(12): 25-31.
[15]	徐平,马天乙,刘飞. 一种新型双频带无人机载共形天线[J]. 电子科技, 2023, 36(12): 95-98.