Machine Learning-Assisted Microstrip Antenna Design Featuring Extraordinary Polarization Purity
Rafidul, Sk, Akinsolu, Mobayode O., Liu, Bo, Kumar, Chandrakanta and Guha, Debatosh (2024) Machine Learning-Assisted Microstrip Antenna Design Featuring Extraordinary Polarization Purity. IEEE Antennas and Wireless Propagation Letters, 24 (4). pp. 1008-1012. ISSN 1536-1225
![[img]](https://wrexham.repository.guildhe.ac.uk/style/images/fileicons/text.png) |
Text
WURO_Machine_Learning-Assisted_Microstrip_Antenna.pdf - Accepted Version Available under License Creative Commons Attribution. Download (2MB) |
Abstract
A high degree of polarization purity for microstrip antennas has been successfully explored. This, to the best of our knowledge, is the first of its kind and claims a twofold novelty: a stepwise development of complex multiunit defected ground geometry (DGG) based on a thorough scientific analysis and use of a machine learning-assisted global antenna optimization method, particularly, the parallel surrogate model-assisted hybrid differential evolution for antenna synthesis (PSADEA) algorithm, which is often more than ten times faster than popular global optimization techniques, while obtaining superior results. They result in highly optimal solutions considering multiple performances, i.e., reduction in cross-polarization (XP) radiations simultaneously over orthogonal (H-) and diagonal (D-) planes maintaining the primary gain unaffected. The proposed DGG has been satisfactorily tested with different patches and arrays fabricated in C band. Typically, 7.5 dBi to 8.0 dBi peak gain has been ensured along with 13 dB to 18 dB improvement in XP level over entire radiation planes. A 4-element array on an identical DGG promises over 40 dB co-to-XP isolation over the entire azimuth planes.
| Item Type: | Article |
|---|---|
| Keywords: | Optimization , Gain , Antennas , Microstrip antennas , Microstrip , Substrates , Microstrip antenna arrays , Geometry , Electric fields , C-band |
| Divisions: | Applied Science, Computing and Engineering |
| Depositing User: | Hayley Dennis |
| Date Deposited: | 04 Jun 2025 14:08 |
| Last Modified: | 04 Jun 2025 14:08 |
| URI: | https://wrexham.repository.guildhe.ac.uk/id/eprint/18302 |
Actions (login required)
 |
Edit Item |