On demand design of multi-freedom metamaterial absorbers based on recurrent prediction networks
Source abstract
Abstract
Metamaterial absorbers (MMAs) have received a lot of attention due to their wide range of promising applications. In general, metamaterials involve a large number of geometric parameters, so the traditional simulation requires researchers to have rich experience and sufficient computational resources. In this paper, we demonstrate the forward and on demand design of multi-freedom MMAs based on the recurrent prediction network (RPN). We used the variable contribution analysis (VCA) algorithm to eliminate 55 absorption points whose contribution score was less than 1.0, the maximum fitting coefficient (R 2 ) was increased by 7.0%, and the average calculation time was reduced by 20.326s. multi-freedom design is achieved by quantifying the design material into binary features as geometric parameter inputs into the RPN model. We solve the prediction peak error problem by many-to-one RPN, compared with the many-to-many prediction of classical deep neural network (DNN) model, the RPN error range is 0-0.12 compared to the 0-0.25 error range of the DNN. The ultra-wideband MMA design with the absorption of 0.2-4.2µm broadband is more than 90%, and the highest absorption rate is 99.2%. This method can be used in zoom imaging, metamaterials filters and other fields.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Metamaterials and Metasurfaces Applications · Antenna Design and Analysis · Microwave Imaging and Scattering Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (25)
Show source-provided references
1. Dolan · Adv. Opt. Mater. · 2015 · 3 · 1210.1002/adom.201400333 ↗
2. Kumar · IEEE Access · 2021 · 9 · 1872210.1109/ACCESS.2021.3053100 ↗
3. Chen · Opt. Express · 2012 · 20 · 716510.1364/OE.20.007165 ↗
4. Gao · Adv. Mater. Technol. · 2022 · 7 · 210069810.1002/admt.202100698 ↗
5. Wang · Photonics Res. · 2022 · 10 · 271810.1364/PRJ.473332 ↗
6. Caglayan · Opt. Express · 2008 · 16 · 1113210.1364/OE.16.011132 ↗
7. Rybin · Nat. Commun. · 2015 · 6 · 1010210.1038/ncomms10102 ↗
8. Cai · Small Sci. · 2022 · 2 · 220003910.1002/smsc.202200039 ↗
9. Monticone · Chinese Phys. B · 2014 · 23 · 04780910.1088/1674-1056/23/4/047809 ↗
10. Popov · Opt. Express · 2009 · 17 · 677010.1364/OE.17.006770 ↗
11. Esteva · Nat. Med. · 2019 · 25 · 2410.1038/s41591-018-0316-z ↗
12. Yuan · Remote Sensing of Environment · 2020 · 241 · 11171610.1016/j.rse.2020.111716 ↗
13. Otter · IEEE Trans. Neural Netw. Learning Syst. · 2021 · 32 · 60410.1109/TNNLS.2020.2979670 ↗
14. Di Cesare · Advances in Engineering Software · 2016 · 101 · 14910.1016/j.advengsoft.2015.10.011 ↗
15. Chen · Opt. Express · 2008 · 16 · 1280610.1364/OE.16.012806 ↗
16. Gu · Opt. Mater. · 2023 · 136 · 11347110.1016/j.optmat.2023.113471 ↗
17. Yuan · Opt. Commun. · 2024 · 557 · 13029610.1016/j.optcom.2024.130296 ↗
18. Han · Opt. Express · 2021 · 29 · 1995510.1364/OE.427593 ↗
19. Patel · Opt. Mater. · 2022 · 124 · 11204910.1016/j.optmat.2022.112049 ↗
20. Wang · IEEE Microw. Wireless Tech. Lett. · 2024 · 34 · 46310.1109/LMWT.2024.3385982 ↗
21. Wang · Phys. Scr. · 2024 · 99 · 05553110.1088/1402-4896/ad398e ↗
22. Yu · Adv. Opt. Mater. · 2019 · 7 · 180099510.1002/adom.201800995 ↗
23. Palik · 1998
24. Noor · 2010
25. Zhang · Concurr. Comput.-Pract. Exp. · 2020 · 32 · e592110.1002/cpe.5921 ↗