Comparative analysis of machine learning and physics-based optimizations of a dual circularly polarized antenna for V2X applications

In this paper, a comparative analysis of Machine learning (ML) and physics-based (PB) optimizations of the monopole fence surrounding a dual circular polarized (CP) antenna, operating in the X-band, is presented and discussed. The aim is to enhance the antenna performances in terms of achieved co-po...

Full description

Saved in:
Bibliographic Details
Published in:International journal of electronics and communications 2021-12, Vol.142, p.153994, Article 153994
Main Authors: Pavone, Santi C., Ravichandran, Kesav, Senthilnathan, Palaniappan, K, Balaji Prasanna, Di Donato, Loreto, Crisafulli, Ottavio, S, Radha, Nagaradjane, Prabagarane, Sorbello, Gino
Format: Article
Language:English
Subjects:
Antenna optimization
Circular polarization
Cross-dipole antenna
Dual polarization
Machine learning
V2X standard
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:In this paper, a comparative analysis of Machine learning (ML) and physics-based (PB) optimizations of the monopole fence surrounding a dual circular polarized (CP) antenna, operating in the X-band, is presented and discussed. The aim is to enhance the antenna performances in terms of achieved co-polar gain and cross-polarization rejection at grazing angles, by preserving good impedance matching and input CP port isolation. The results are found to be satisfactory for the specific V2X application, since an acceptable co-polar (LHCP) gain is achieved on a broad angular range with a good cross-polarization (RHCP) rejection, without increasing dramatically the final antenna complexity.
ISSN:1434-8411
1618-0399
DOI:10.1016/j.aeue.2021.153994