基于贝叶斯算法的天线端到端优化

doi:10.12305/j.issn.1001-506X.2021.12.01

系统工程与电子技术 ›› 2021, Vol. 43 ›› Issue (12): 3413-3419.doi: 10.12305/j.issn.1001-506X.2021.12.01

• 电子技术 • 下一篇

基于贝叶斯算法的天线端到端优化

田春明^1,*, 杨安¹, 叶乐², 李建星¹, 贺雨晨³

1. 西安交通大学信息与通信工程学院, 陕西西安 710049
2. 北京大学微纳电子学系, 北京 100871
3. 西安交通大学电子科学与工程学院, 陕西西安 710049

收稿日期:2021-01-22 出版日期:2021-11-24 发布日期:2021-11-30
通讯作者: 田春明
作者简介:田春明(1974—), 男, 讲师, 博士, 主要研究方向为天线与电波传播、电磁场数值计算、超材料设计|杨安(1988—), 男, 工程师, 硕士, 主要研究方向为毫米波天线设计、机器学习算法|叶乐(1983—), 男, 副教授, 博士, 主要研究方向为绿色智能物联网芯片及植入式微纳集成系统|李建星(1987—), 男, 副教授, 博士, 主要研究方向为新型天线理论与设计、电磁超材料理论与应用、人工智能辅助电磁器件设计|贺雨晨(1987—), 男, 助理教授, 博士, 主要研究方向为量子成像、图像处理、人工智能
基金资助:
国家重点研发计划(2019YFB1803205);陕西省重点研发计划(2019GY-007);强脉冲辐射环境模拟与效应国家重点实验室专项经费(SKLIPR1815)

End-to-end antenna optimization based on Bayesian optimization algorithm

Chunming TIAN^1,*, An YANG¹, Le YE², Jianxing LI¹, Yuchen HE³

1. School of Information and Communications Engineering, Xi'an Jiaotong University, Xi'an 710049, China
2. Institute of Microelectronics, Peking University, Beijing 100871, China
3. School of Electronic Science and Engineering, Xi'an Jiaotong University, Xi'an 710049, China

Received:2021-01-22 Online:2021-11-24 Published:2021-11-30
Contact: Chunming TIAN

摘要/Abstract

摘要：

在确定天线的拓扑结构以后, 通常需要对天线的结构参数开展反复的优化才能达到设计目标, 快速有效的优化算法有利于缩短天线的设计周期。在建立综合目标函数的基础上, 同时考虑天线的多个优化目标和限制条件, 使用贝叶斯优化算法对天线进行端到端优化。基于在线更新的数据集, 高斯过程估计出目标函数的后验分布, 进而使用获得函数进行迭代。通过两种天线模型对提出的优化算法进行仿真验证, 结果表明, 由于建立了天线参数到综合目标函数的映射关系, 整个优化过程以端到端的方式实现, 与传统的优化方法相比, 所提算法的优化结果和优化速度都具有明显的优势。

关键词: 天线优化, 多目标优化, 端到端, 贝叶斯优化算法

Abstract:

Once the topology of an antenna is determined, optimization of various antenna parameters is conducted to achieve the desired objectives. A fast and effective optimization algorithm is significant to shorten the antenna design period. With the use of a comprehensive objective function which fuses multiple targets and constraints into one single function, the antenna is optimized end-to-end by employing Bayesian optimization algorithm. Based on the online updated dataset, the Gaussian process estimates the posterior distribution of the comprehensive objective function, and afterwards acquisition function is utilized for the iteration. To demonstrate the proposed method, two antenna models are simulated and optimized. The results show that because the proposed method is implemented in an end-to-end way through a mapping from the antenna parameters to a comprehensive objective function, it can achieve better optimization results and higher optimization efficiency compared with the conventional methods.

Key words: antenna optimization, multi-objective optimization, end-to-end, Bayesian optimization algorithm

中图分类号:

TN82

田春明, 杨安, 叶乐, 李建星, 贺雨晨. 基于贝叶斯算法的天线端到端优化[J]. 系统工程与电子技术, 2021, 43(12): 3413-3419.

Chunming TIAN, An YANG, Le YE, Jianxing LI, Yuchen HE. End-to-end antenna optimization based on Bayesian optimization algorithm[J]. Systems Engineering and Electronics, 2021, 43(12): 3413-3419.

图/表 11

图1

图2

图3

表1

图4

表2

图5

图6

表3

图7

表4

参考文献 31

1	黄友火, 刘其中, 魏文博, 等. 天线宽带匹配网络的粒子群优化设计[J]. 微波学报, 2007, 23 (5): 11- 13. doi: 10.3969/j.issn.1005-6122.2007.05.003
	HUANG Y H , LIU Q Z , WEI W B , et al. Optimal design of a matching network for a broadband antenna[J]. Journal of Microwaves, 2007, 23 (5): 11- 13. doi: 10.3969/j.issn.1005-6122.2007.05.003
2	徐龙海, 黄进, 谢井. 基于遗传算法的2.45 GHz RFID天线优化设计[J]. 电子器件, 2014, 3, 450- 453.
	XU L H , HUANG J , XIE J . An optimized design of 2.45 GHz RFID tag antenna based on genetic algorithm[J]. Chinese Journal of Electron Devices, 2014, 3, 450- 453.
3	张锋, 王东峰, 纪奕才, 等. 基于模拟退火法的Delta天线的优化设计[J]. 中国科学院大学学报, 2012, 29 (3): 372- 376.
	ZHANG F , WANG D F , JI Y C , et al. Optimization and design of Delta antenna based on simulated annealing[J]. Journal of the Gra-duate School of the Chinese Academy of Sciences, 2012, 29 (3): 372- 376.
4	韩帅涛, 侯德亭, 邹伟, 等. 基于UTD和GA混合算法的无人机载天线布局优化[J]. 太赫兹科学与电子信息学报, 2016, 14 (5): 733- 733.
	HAN S T , HOU D T , ZOU W , et al. Layout optimization of UVA airborne antennas based on GA and UTD[J]. Journal of Terahertz Science and Electronic Information Technology, 2016, 14 (5): 733- 733.
5	FORRESTER A , KEANE A . Recent advances in surrogate-based optimization[J]. Progress in Aerospace Sciences, 2009, 45 (1-3): 50- 79. doi: 10.1016/j.paerosci.2008.11.001
6	SINGH P , ROSSI M , COUCKUYT I , et al. Constrained multi-objective antenna design optimization using surrogates[J]. International Journal of Numerical Modelling, 2017, 30 (6): e2248. doi: 10.1002/jnm.2248
7	LI H T, ZHOU J Z, KANG L, et al. Optimization design of skin antenna based on Bayesian optimization[C]//Proc. of the IEEE 7th International Symposium on Microwave, Antenna, Propagation, and EMC Technologies, 2017: 78-83.
8	WU Q , WANG H M , HONG W . Multi-stage collaborative machine learning and its application to antenna modeling and optimization[J]. IEEE Trans.on Antennas and Propagation, 2020, 68 (5): 3397- 3409. doi: 10.1109/TAP.2019.2963570
9	KOZIEL S , BEKASIEWICZ A . Multi-objective design of antennas using variable-fidelity simulations and surrogate models[J]. IEEE Trans.on Antennas and Propagation, 2013, 61 (12): 5931- 5939. doi: 10.1109/TAP.2013.2283599
10	KOZIEL S , BEKASIEWICZ A , COUCKUYT I , et al. Efficient multi-objective simulation-driven antenna design using Co-Kriging[J]. IEEE Trans.on Antennas and Propagation, 2014, 62 (11): 5900- 5905. doi: 10.1109/TAP.2014.2354673
11	KOZIEL S, OGURTSOV S, ZIENIUTYCZ W, et al. Fast simulation-driven design of a planar UWB dipole antenna with an integrated balun[C]//Proc. of the 9th European Conference on Antennas and Propagation, 2015.
12	KOZIEL S , BEKASIEWICZ A , ZIENIUTYCZ W , et al. Expedited EM-driven multi-objective antenna design in highly dimensional parameter spaces[J]. IEEE Antennas and Wireless Propagation Letters, 2014, 13, 631- 634. doi: 10.1109/LAWP.2014.2313698
13	LIU B , ALIAKBARIAN H , MA Z , et al. An efficient method for antenna design optimization based on evolutionary computation and machine learning techniques[J]. IEEE Trans.on Antennas and Propagation, 2014, 62 (1): 7- 18. doi: 10.1109/TAP.2013.2283605
14	JAIN S K , PATNAIK A , SINHA S N . Design of custom-made stacked patch antennas: a machine learning approach[J]. International Journal of Machine Learning and Cybernetics, 2013, 4 (3): 189- 194. doi: 10.1007/s13042-012-0084-x
15	TAK J , KANTEMUR A , SHARMMA Y , et al. A 3-D-printed W-band slotted waveguide array antenna optimized using machine learning[J]. IEEE Antennas and Wireless Propagation Letters, 2018, 17 (11): 2008- 2012. doi: 10.1109/LAWP.2018.2857807
16	YANG Z B , ZHOU J Z , LI H T , et al. Design of hexagonal circularly polarized antenna array using paralleled dynamic mini-mum lower confidence bound[J]. International Journal of RF and Microwave Computer-Aided Engineering, 2018, 28 (2): e21184. doi: 10.1002/mmce.21184
17	LEDESMA S , RUIZ-PINALES J , CERDA-VILLAFANA G , et al. A hybrid method to design wire antennas: design and optimization of antennas using artificial intelligence[J]. IEEE Antennas and Propagation Magazine, 2015, 57 (4): 23- 31. doi: 10.1109/MAP.2015.2453912
18	RASMUSSEN C E , WILLIAMS C K I . Gaussian processes for machine learning[M]. Cambridge: MIT Press, 2006.
19	SHAHRIARI B , SWERSKY K , WANG Z , et al. Taking the human out of the loop: a review of Bayesian optimization[J]. Proceedings of the IEEE, 2016, 104 (1): 148- 175. doi: 10.1109/JPROC.2015.2494218
20	LYU W L , XUE P , YANG F , et al. An efficient Bayesian optimization approach for automated optimization of analog circuits[J]. EEE Trans.on Circuits and Systems Ⅰ: Regular Papers, 2018, 65 (6): 1954- 1967. doi: 10.1109/TCSI.2017.2768826
21	ZHANG S H, YANG F, ZHOU D, et al. An efficient asynchronous batch Bayesian optimization approach for analog circuit synthesis[C]//Proc. of the IEEE 57th Design Automation Conference, 2020.
22	LYU W L, YANG F, YAN C H, et al. Batch Bayesian optimization via multi-objective acquisition ensemble for automated analog circuit design[C]//Proc. of 35th International Confe-rence on Machine Learning, 2018.
23	TALNIKAR C. Methods for design optimization using high fidelity turbulent flow simulations[D]. Cambridge: Massachusetts Institute of Technology, 2015.
24	AKIBA T, SANO S, YANASE T, et al. Optuna: a next-gene-ration hyperparameter optimization framework[C]//Proc. of the 25th ACM SIGKDD International Conference on Know-ledge Discovery & Data Mining, 2019.
25	JIN H F, SONG Q Q, HU X. Auto-keras: an efficient neural architecture search system[C]//Proc. of the 25th ACM SIGKDD International Conference, 2019.
26	COWEN-RIVERS A, LYU W, WANG Z, et al. HEBO: heteroscedastic evolutionary Bayesian optimization[EB/OL]. [2021-01-10]. https://arXiv:2012.03826, 2020.
27	LIU J, TUNGUZ B, TITERICZ G. GPU accelerated exhaustive search for optimal ensemble of Black-Box optimization algorithms[EB/OL]. [2021-01-10]. https://arXiv:2012.04201, 2020.
28	AWAD N H, SHALA G, DENG D, et al. Squirrel: a switching hyperparameter optimizer[EB/OL]. [2021-01-10]. https://arXiv:2012.08180, 2020.
29	SAZANOVICH M, NIKOLSKAYA A, BELOUSOV Y, et al. Solving black-box optimization challenge via learning search space partition for local Bayesian optimization[EB/OL]. [2021-01-10]. https://arXiv:2012.10335, 2020.
30	WU J, CAO M, SHAN L, et al. Higher performance for AutoML: the benefit of various ensemble Bayesian optimization strategy[EB/OL]. [2020-12-20]. https://valohaichirpprod.blob.core.windows.net/papers/duxiaoman.pdf.
31	FERNANDO N. Bayesian optimization: open source constrained global optimization tool for Python[EB/OL]. [2020-10-10]. https://github.com/fmfn/BayesianOptimization.

序号	真实值	后验均值	后验标准差
1	-70.85	-68.19	3.49
2	-56.49	-55.50	7.98
3	-73.23	-69.23	8.25
4	-84.03	-73.95	4.36
5	-82.06	-82.83	2.61

实验序号	优化后目标函数值	最大S11/dB	最大AR/dB	最小gain/dB
1	6.43	-12.17	2.63	6.23
2	7.39	-17.73	2.66	6.42
3	5.45	-17.79	2.68	6.09

序号	真实值	后验均值	后验标准差
1	18.01	16.64	2.03
2	6.21	7.23	2.08
3	8.47	8.69	3.42
4	14.50	13.00	2.18
5	4.82	5.53	2.10

实验序号	优化后目标函数值	max (S11)/dB	mean (Gain)/dB
1	21.89	-14.47	6.59
2	21.57	-15.42	6.50
3	21.90	-13.96	6.63

[1]	闫世瑛, 颜克斐, 方伟, 陆恒杨. 基于差分进化邻域自适应的大规模多目标算法[J]. 系统工程与电子技术, 2022, 44(7): 2112-2124.
[2]	刘乾, 鲁云军, 陈克斌, 韩梦瑶, 郭亮. 任务主体二元约束下作战任务分解EVA方法[J]. 系统工程与电子技术, 2022, 44(7): 2201-2210.
[3]	来磊, 邹鲲, 吴德伟, 李保中. 交互策略改进MOFA进化的多UAV协同航迹规划[J]. 系统工程与电子技术, 2021, 43(8): 2282-2289.
[4]	崔荣伟, 韩维, 苏析超, 王立国, 刘玉杰. 舰载机甲板机务勤务保障作业调度与资源配置集成优化[J]. 系统工程与电子技术, 2021, 43(7): 1884-1893.
[5]	周晶, 赵晓哲, 许震, 林众, 张晓盼. 基于D-NSGA-Ⅲ算法的无人机群高维多目标任务分配方法[J]. 系统工程与电子技术, 2021, 43(5): 1240-1247.
[6]	夏博远, 杨克巍, 杨志伟, 张小可, 赵丹玲. 基于杀伤网评估的装备组合多目标优化[J]. 系统工程与电子技术, 2021, 43(2): 399-409.
[7]	来磊, 吴德伟, 邹鲲, 韩昆, 李海林. 基于多准则交互膜进化算法的UAV三维航迹规划[J]. 系统工程与电子技术, 2021, 43(1): 138-146.
[8]	王亚东, 石全, 夏伟, 陈材. 基于超启发式算法的备件供应网络结构优化[J]. 系统工程与电子技术, 2020, 42(3): 620-629.
[9]	丁春山. 传感器管理技术研究现状与展望[J]. 系统工程与电子技术, 2020, 42(12): 2761-2770.
[10]	马武彬, 王锐, 王威超, 吴亚辉, 邓苏, 黄宏斌. 基于进化多目标优化的微服务组合部署与调度策略[J]. 系统工程与电子技术, 2020, 42(1): 90-100.
[11]	李瑞阳, 王智学, 禹明刚, 何红悦. 基于鲁棒能力的体系多目标组合优化[J]. 系统工程与电子技术, 2019, 41(5): 1034-1042.
[12]	孙鹏, 武君胜, 王勋, 焦志强, 张杰勇. 基于多目标优化的C2组织平台资源动态调度方法[J]. 系统工程与电子技术, 2019, 41(4): 793-800.
[13]	褚骁庚, 马政伟, 陈行军. 面向多目标优化火力目标分配问题的前瞻式边际贪婪算法[J]. 系统工程与电子技术, 2019, 41(10): 2252-2259.
[14]	徐浩, 邢清华, 王伟. 基于模糊多目标规划的防空反导火力分配[J]. 系统工程与电子技术, 2018, 40(3): 563-570.
[15]	李志亮, 李小将, 张东来. 基于改进DE算法的敏捷成像卫星前摄式调度[J]. 系统工程与电子技术, 2018, 40(2): 353-359.

基于贝叶斯算法的天线端到端优化

End-to-end antenna optimization based on Bayesian optimization algorithm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 31

相关文章 15

编辑推荐

Metrics

本文评价