A Generative Meta‐Atom Model for Metasurface‐Based Absorber Designs
- 3 November 2022
- journal article
- research article
- Published by Wiley in Advanced Optical Materials
- Vol. 11 (2)
Abstract
Metasurfaces (MS) are widely accepted in the devices, such as absorbers, to improve their performances. MS provide new design freedoms, however, they also result in complexity in designs because of the high‐dimensional topological space of meta‐atoms, and high computational costs in the optimization procedure. To alleviate this challenge, a generative meta‐atom model that generates the pattern and corresponding electromagnetic (EM) responses of meta‐atoms, specialized for absorbing applications is developed. The model is established by the convolutional variational autoencoder (CVAE), and a deep neural network (DNN). The model is verified by designing different types of absorbers with the evolutionary algorithm, and an ultrabroadband lower profile absorber at low microwave frequencies is achieved. The realized metasurface‐based absorber (MSA) covers the frequency range from 1.4 to 18 GHz at the criteria of return loss (RL) −10 dB with a thickness of 8 mm, which is validated by experiments. This work provides an effective and highly efficient way to design high‐performance MSA, which can be easily extended to other metasurface‐based functional devices.Keywords
Funding Information
- National Natural Science Foundation of China (61771237)
- Fundamental Research Funds for the Central Universities
This publication has 47 references indexed in Scilit:
- An Ultra-wideband and Polarization-independent Metasurface for RCS ReductionScientific Reports, 2016
- Single-Layer Wideband Microwave Absorber Using Array of Crossed DipolesIEEE Antennas and Wireless Propagation Letters, 2016
- Electrically Tunable Epsilon-Near-Zero (ENZ) Metafilm AbsorbersScientific Reports, 2015
- Ultrawideband and High-Efficiency Linear Polarization Converter Based on Double V-Shaped MetasurfaceIEEE Transactions on Antennas and Propagation, 2015
- Thin Perfect Absorbers for Electromagnetic Waves: Theory, Design, and RealizationsPhysical Review Applied, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Ultra-thin perfect absorber employing a tunable phase change materialApplied Physics Letters, 2012
- Metamaterial Electromagnetic Wave AbsorbersAdvanced Materials, 2012
- Tunable broadband metamaterial absorber consisting of ferrite slabs and a copper wireChinese Physics B, 2012
- Light Propagation with Phase Discontinuities: Generalized Laws of Reflection and RefractionScience, 2011