journal article·2023-09-01Open access

Research on a demand design method of a cross polarization converter metasurface based on a depth generation model

Junwei Li, Qinhua A, Qiusong Lan, Jintao Yang, Lijun Yun, Yuelong Xia, Chengfu Yang

Optical Materials Express· Volume 13· Issue 9

Abstract

As a two-dimensional electromagnetic metamaterial, the cross-polarization conversion (CPC) metasurface is thin, easy to develop, and has attracted wide attention. However, existing CPC cell surface designs still rely on inefficient full-wave numerical simulation. Although some researchers have explored deep learning CPC metasurface structure design methods, the generated metasurface patterns are of poor quality. In this paper, an on-demand design method for cross-polarization conversion metasurface based on depth-generation model is proposed. Firstly, Wasserstein generative adversarial network (WGAN) is used to reverse design CPC metasurface, and Wasserstein distance is introduced to replace JS divergence and KL divergence to optimize the target. The problem of training difficulty caused by gradient elimination of original generative adversarial network (GAN) is fundamentally solved. Secondly, in the WGAN model, U-Net architecture generator is used to generate images, which greatly improves the surface image quality of CPC. In addition, a simulator composed of convolutional neural network (CNN) is also added in this paper to carry out forward prediction of S-parameter spectrum diagram. By inputting the patterns generated by WGAN into the simulator, the corresponding S-parameter spectrum diagram is generated and compared with the real S-parameter spectrum diagram, so as to verify whether the surface patterns of generated elements meet the requirements. The depth generation model proposed in this paper organically combines the forward spectrum prediction model and the reverse CPC metasurface structure design model, so that the CPC metasurface structure satisfying the expected electromagnetic response can be designed quickly on demand. This on-demand design method is expected to promote the rapid design, fabrication and application of electromagnetic devices.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Metamaterials and Metasurfaces Applications · Advanced Antenna and Metasurface Technologies · Antenna Design and Analysis

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Yunnan Normal University

Engineering Research Center of Computer Vision and Intelligent Control Technology

Funding

the doctoral research foundation of Yunnan normal university · Yunnan Provincial Department of Education · Natural Science Foundation of Yunnan Province

References (33)

Show source-provided references
1. Zhang · Nat. Mater. · 2008 · 7 · 43510.1038/nmat2141 ↗
2. Ni · Science · 2015 · 349 · 131010.1126/science.aac9411 ↗
3. Arbabi · Optica · 2016 · 3 · 62810.1364/OPTICA.3.000628 ↗
4. Krasnok · Mater. Today · 2018 · 21 · 810.1016/j.mattod.2017.06.007 ↗
5. Lin · Nat. Commun. · 2020 · 11 · 138910.1038/s41467-020-15116-z ↗
6. Schurig · Science · 2006 · 314 · 97710.1126/science.1133628 ↗
7. Yang · Opt. Express · 2018 · 26 · 2428010.1364/OE.26.024280 ↗
8. Yang · J. Acoust. Soc. Amer. · 2019 · 146 · 50510.1121/1.5118244 ↗
9. Yang · Sci. Rep. · 2018 · 8 · 1733910.1038/s41598-018-35327-1 ↗
10. Yang · AIP Adv. · 2019 · 9 · 02502810.1063/1.5087047 ↗
11. Yang · J. Appl. Phys. · 2020 · 128 · 01450310.1063/5.0010713 ↗
12. Yang · Opt. Commun. · 2019 · 435 · 15010.1016/j.optcom.2018.11.028 ↗
13. Ismail · Appl. Phys. · 2017 · 121 · 04510310.1063/1.4974849 ↗
14. Li · Nat. Rev. Mater. · 2021 · 6 · 82910.1038/s41578-021-00304-0 ↗
15. Saman · Nat. Nanotechnol. · 2016 · 11 · 2310.1038/nnano.2015.304 ↗
16. Khorasaninejad · Nano Lett. · 2017 · 17 · 181910.1021/acs.nanolett.6b05137 ↗
17. Yu · Nat. Mater. · 2014 · 13 · 13910.1038/nmat3839 ↗
18. Shi · Opt. Express · 2020 · 28 · 3157210.1364/OE.402137 ↗
19. Goni · J.Vib.Control. · 2017 · 23 · 261910.1177/1077546315619076 ↗
20. Cai · J. Quant. Spectrosc. Radiat. Transfer · 2021 · 271 · 10771210.1016/j.jqsrt.2021.107712 ↗
21. Song · Computing · 2020 · 102 · 66310.1007/s00607-019-00753-0 ↗
22. Vasily · Appl. Sci. · 2021 · 11 · 1053210.3390/app112210532 ↗
23. Manwar · Optics · 2020 · 2 · 110.3390/opt2010001 ↗
24. LeCun · Nature · 2015 · 521 · 43610.1038/nature14539 ↗
25. Pun · Nat. Commun. · 2019 · 10 · 233910.1038/s41467-019-10343-5 ↗
26. Cang · J. Mech. Des. · 2017 · 139 · 07140410.1115/1.4036649 ↗
27. Baldi · Nat. Commun. · 2014 · 5 · 430810.1038/ncomms5308 ↗
28. Han · Briefings Bioinf. · 2023 · 24 · 53210.1093/bib/bbac532 ↗
29. Malkiel · Light: Sci. Appl. · 2018 · 7 · 6010.1038/s41377-018-0060-7 ↗
30. Liu · Nano Lett. · 2018 · 18 · 657010.1021/acs.nanolett.8b03171 ↗
31. Ma · Adv. Mater. · 2019 · 31 · 190111110.1002/adma.201901111 ↗
32. Wang · Comput. Methods Appl. Mech. and Eng. · 2020 · 372 · 11337710.1016/j.cma.2020.113377 ↗
33. Hou · Nanoscale Res. Lett. · 2020 · 15 · 8310.1186/s11671-020-03319-8 ↗