A Novel Metasurface Inverse Design Based on Back Propagation Neural Network

Tao Qin, Su Wen, Xianqi Lin, Yuyan Cao, Yang Cai, Peng Mei

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

Abstract

This paper proposes a novel reflective meta-surface inverse design by utilizing a back propagation neural network. A reflective meta-surface, measuring 0.92 m in width, 0.92 m in height, and 0.508 cm in thickness, is synthesized. This metasurface is composed of twelve distinct unit types, each possessing unique phase-shifting characteristics. When illuminated by a multi-mode waveguide horn employing the offset design, the meta-surface demonstrates a gain of 31.65 dB at a frequency of 5.8 GHz. Furthermore, the simulated design achieves a side lobe level of 23 dB in the far-field region, accompanied by a system efficiency of 36% and a relative 3-dB bandwidth of 7%. By incorporating more training data and enhancing the machine learning algorithms, this design methodology could be applied to generate complex meta-surface structures with multi-frequencies and multi-polarization responses, demonstrating significant potential in multi-functional meta-surface integration.

OriginalsprogEngelsk
Titel18th European Conference on Antennas and Propagation, EuCAP 2024
Antal sider5
ForlagIEEE (Institute of Electrical and Electronics Engineers)
Publikationsdato26 apr. 2024
Artikelnummer10501758
ISBN (Trykt)979-8-3503-9443-6
ISBN (Elektronisk)978-88-31299-09-1
DOI
StatusUdgivet - 26 apr. 2024
Begivenhed18th European Conference on Antennas and Propagation, EuCAP 2024 - Glasgow, Storbritannien
Varighed: 17 mar. 202422 mar. 2024

Konference

Konference18th European Conference on Antennas and Propagation, EuCAP 2024
Land/OmrådeStorbritannien
ByGlasgow
Periode17/03/202422/03/2024
SponsorANSYS, CADFEM, Dassault Systemes, et al., Huawei Technologies Co., Ltd., Microwave Vision Group

Fingeraftryk

Dyk ned i forskningsemnerne om 'A Novel Metasurface Inverse Design Based on Back Propagation Neural Network'. Sammen danner de et unikt fingeraftryk.

Citationsformater