-
共形超构表面具有灵活的外形,便于适应复杂的平台结构,在移动载体散射调控方面具有显著的应用优势。但共形超构表面散射场电磁仿真时间周期长、优化复杂,难以支撑共形超构表面的敏捷设计。本文提出了一种基于迁移学习的共形超构表面散射场高效智能计算方法。首先,根据天线理论和全波电磁仿真在物理机理上的同一性,预先用大量理论数据训练源域模型,构建相位分布与散射场的初始映射模型;然后,将少量全波仿真训练数据作为目标域样本,依托预训练、参数冻结和模型微调实现初始模型的有效迁移,完成超构表面相位分布到散射场映射模型的构建;最后,针对不同的共形几何结构,在迁移学习模型基础上进行了二次迁移。结果表明,本文所提方法的散射场计算时间较全波仿真下降3个数量级,在少样本条件下应用迁移学习后散射场计算精度平均提升19.8%,训练数据量仅占未迁移学习模型的42.9%,数据集收集时间缩短50.1%,同时在超构表面共形结构发生改变时具有一定泛化性。Conformal metasurfaces with flexible structures are able to fit complicated platforms which have obvious advantages in moving platforms scattering manipulations. However, conformal metasurfaces far-field simulations is high time consumption and hard to optimize, making the its agile designing difficult. Here, an efficient and intelligent scattering field calculation method is proposed based on transfer learning for conformal metasurfaces. Firstly, according to the uniformity in physical mechanism between antenna theory and full wave simulation, the initial mapping model between phase distribution and far-field of metasurface is constructed and pre-trained based on a large amount of theoretical data in source domain. Secondly, by pre-training, parameter freezing and model fine-tuning, the far-field prediction model for full wave simulation is transferred and achieved successfully, based on small amount full wave simulation data in target domain. Finally, the transfer learning model for far-field prediction is transferred once again for conformal metasurfaces with different structures. Results indicate that, the proposed method only consumes 0.1% time of full wave simulation for conformal metasurface far-field calculation. In cases of fewer samples, the model with transfer learning can improve the average accuracy by 19.8%, training data account for only 42.9% for the that of model without transfer learning, which reduce training data collection time by 50.1%. Moreover, our far-field calculation method demonstrates good transfer performance between conformal metasurfaces with different structures.
-
Keywords:
- conformal metasurface /
- transfer learning /
- scattering field
-
[1] . Liu K Y, Wang G M, Cai T, Guo W L, Zhuang Y Q, Liu G 2018Chin. Phys. B 27 084101
[2] . Liu K T, Wang G M, Cai T, Dai B J, Xiao Y, Li H P, Guo W L 2019J. Phys. D: Appl. Phys. 52 255002
[3] . Bai H, Wang G M, Zou X J, Xie P, Shi Y P 2022Chin. Phys. B 31 54102
[4] . Liu K Y, Wang G M, Cai T, Li H P, Li T Y 2021IEEE Trans. Antennas Propag. 69 3349
[5] . Germain D, Seetharamdoo D, Burokur S N, de Lustrac A 2013Appl. Phys. Lett. 103 124102
[6] . Wang Y C, Feng Q, Kong X D, Liu H X, Han J Q, Li L 2024IEEE Antennas Wirel. Propag. Lett. 23 970
[7] . Fu B, Yu S X, Kou N, Ding Z, Zhang Z P 2022Chin. Phys. B 31 40703
[8] . Gupta E, Bonner C, Lazarus N, Mirotznik M S, Nicholson K J. 2023IEEE Antennas Wirel. Propag. Lett. 22 2629
[9] . Fu C F, Han L F, Liu C, Lu X L, Sun Z J 2022IEEE Trans. Antennas Propag. 70 2352
[10] . Wang Y J, Su J X, Li Z R, Guo Q X, Song J M 2020IEEE Antennas Wirel. Propag. Lett. 19 631
[11] . Luo X Y, Chen K, Guo W L, Feng Y J, 2019International Conference on Microwave and Millimeter Wave Technology (ICMMT), Guangzhou China, May 19-22, 2019 pp 1
[12] . Xu H X, Hu G W, Wang Y Z, Wang C H, Wang M Z, Wang S J, Huang Y J, Genevet P, Huang W, Qiu C W 2021Light Sci. Appl. 10 75
[13] . Wang C H, Xu H X, Pang Z C, Wang M Z, Wang S J 2022J. Infrared Millimeter Waves 41 210
[14] . Srilatha K., Madhav B. T. P., babu B. Anil, Das Sudipta, Rao M. C. 2022Appl. Phys. A 128 1091
[15] . Liu M J, Li T Y, Ge Q, Wang S M, Wang Z L, Zhu S N 2022 Acta Optica Sinica 42 21260049(刘梦蛟,李添悦,戈钦,王漱明,王振林,祝世宁2022光学学报42 2126004)
[16] . Wang Z H, Xu H X, Pang Z C, Wang M Z, Wang S J 2022J Infrared Millim W 41 8(王朝辉,许河秀,逄智超,王明照,王少杰2022红外与毫米波学报41 8)
[17] . Yang S W, Huang L L, Wang Y T 2023Optical Technique 49 6(杨斯雯,黄玲玲,王涌天2023光学技术49 6)
[18] . Ma Y C, Chen S, Ermon S, Lobell David B. 2024Remote Sens. Environ. 301 113924
[19] . Fu S Y, Tao S Y, Fan H T, He K, Liu X T, Tao Y L, Zuo J X, Zhang X, Wang Y, Sun Y J 2024Appl. Energy 353 121991
[20] . Chen L C, Zhu Y, Papandreou G, Schroff F, Adam H, 2018European Conference on Computer Vision, Berlin Germany, September 8-14, 2018 p833
[21] . Treviso M Lee J U, Ji T 2023Trans. Assoc. Comput. Linguist. 11 826
[22] . Zhu R C, Qiu T S, Wang J F, Sui S, Hao C L, Liu T, Li Y F, Feng M D, Zhang A X, Qiu C W, Qu S B 2021Nat. Commun. 12 2974
[23] . Xu Y, Li F, Gu J Q, Bi Z W, Cao B, Yang Q L, Han J G, Hu Q H, Zhang W L 2024Adv. Photonics Nexus 3 026002
[24] . Qu Y R, Jing L Shen Y C, Qiu M, Soljačić M 2019ACS Photonics 6 1168
[25] . Xu D, Luo Y, Luo J, Pu M B, Zhang Y X, Ha Y L, Luo X G 2021Opt. Mater. Express 11 1852
[26] . Zhang J, Qian C, Fan Z X, Chen J T, Li E P, Jin J M, Chen H S 2022Adv. Opt. Mater. 10 2200748
[27] . Zhang S, Xi D K, Li H X 2019J. Eng. Thermophys. 407(张森,席德科,李华星2019工程热物理学报40 7)
[28] . Jia Y T, Qian C, Fan Z X, Ding Y Z, Wang Z D, Wang D P, Li E P, Zheng B, Cai T, Chen H S 2022Adv. Funct. Mater. 32 2109331
计量
- 文章访问数: 60
- PDF下载量: 2
- 被引次数: 0