A Deep-Learning Enabled Discrete Dielectric Lens Antenna for Terahertz Reconfigurable Holographic Imaging

A deep-learning enabled discrete dielectric lens (DDL) antenna with terahertz hologram reconfigurability is proposed. The antenna is constructed by two cascaded discrete dielectric lenses, which are designed based on a diffractive deep neural network (D 2 NN) with an improved loss function, fed by a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE antennas and wireless propagation letters 2022-04, Vol.21 (4), p.823-827
Main Authors: Liao, Dashuang, Wang, Manting, Chan, Ka Fai, Chan, Chi Hou, Wang, Haogang
Format: Article
Language:English
Subjects:
Antenna design
Antennas
Artificial neural networks
Conductors
Deep learning
Dielectrics
Diffractive deep neural network
discrete dielectric lens (DDL) antenna
Electric conductors
Holography
Lens antennas
Lenses
Machine learning
Optical imaging
Phase change materials
reconfigurable holograms
Reconfiguration
terahertz (THz)
Terahertz frequencies
Training
Wave fronts
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A deep-learning enabled discrete dielectric lens (DDL) antenna with terahertz hologram reconfigurability is proposed. The antenna is constructed by two cascaded discrete dielectric lenses, which are designed based on a diffractive deep neural network (D 2 NN) with an improved loss function, fed by a static horn. The DDL antenna can achieve dynamic holographic imaging by a simple mechanical translation of the perfect electric conductor (PEC) mask attached to the first lens instead of locally controlling individual meta-atoms through incorporating active elements or phase change materials with complicated feeding networks. The phase profiles for the DDL antenna design are obtained by training four customized input field patterns and corresponding anticipated output target images with the modified D 2 NN. Dynamic switching of four number images "1, 2, 3, 4" is demonstrated by both full-wave simulated and experimental results. The proposed DDL antenna and design strategy present a new approach to achieve wavefront reconfiguration, especially in the absence of tunable components at high frequencies.
ISSN:1536-1225
1548-5757
DOI:10.1109/LAWP.2022.3149861