Machine learning-based approach for bandwidth and frequency prediction of circular SIW antenna

Abstract Machine Learning (ML) has significantly transformed antenna design by enabling efficient optimization of geometrical parameters, modeling complex electromagnetic behavior, and accelerating performance prediction with reduced computational cost. This study presents an ML-based approach to ac...

Full description

Saved in:
Bibliographic Details
Main Authors: Md Mahabub Alam, Nurhafizah Abu Talip Yusof, Ahmad Afif Mohd Faudzi, Md Raihanul Islam Tomal, Md Ershadul Haque, Md. Suaibur Rahman
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Journal of King Saud University: Engineering Sciences
Subjects:
Online Access:https://doi.org/10.1007/s44444-025-00010-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238320229384192
author Md Mahabub Alam
Nurhafizah Abu Talip Yusof
Ahmad Afif Mohd Faudzi
Md Raihanul Islam Tomal
Md Ershadul Haque
Md. Suaibur Rahman
author_facet Md Mahabub Alam
Nurhafizah Abu Talip Yusof
Ahmad Afif Mohd Faudzi
Md Raihanul Islam Tomal
Md Ershadul Haque
Md. Suaibur Rahman
author_sort Md Mahabub Alam
collection DOAJ
description Abstract Machine Learning (ML) has significantly transformed antenna design by enabling efficient optimization of geometrical parameters, modeling complex electromagnetic behavior, and accelerating performance prediction with reduced computational cost. This study presents an ML-based approach to accurately predict the resonance frequencies and bandwidth of a novel triple-band circular Substrate Integrated Waveguide (SIW) antenna intended for K- and Ka-band satellite communication. The antenna features four symmetrically etched ring slots on the radiating patch and circularly arranged vias within a Rogers RT/Duroid 5880 substrate (20 × 15 × 1.6 mm3). The interaction between the TE₁₁ cavity mode and the ring slots facilitates controlled electromagnetic field leakage, enhancing radiation performance. A predictive ML framework was developed using six regression algorithms trained on significant geometrical parameters, such as ring slot radius, via diameter, and feedline width. Among them, the Extra Trees Regression model achieved over 98% accuracy, with errors below 0.1% for both resonance frequency and bandwidth predictions. The approach was validated through Computer Simulation Technology (CST) simulations and ML-based predictions, both demonstrating strong agreement. Although experimental fabrication was not included in this phase, the model offers a reliable foundation for future physical validation and prototyping. The results confirm that the proposed antenna structure, combined with the predictive power of ML, presents a promising solution for compact, high-performance antennas in satellite communication systems.
format Article
id doaj-art-a3440cd371d84fb784d88c060a684dcf
institution Kabale University
issn 1018-3639
2213-1558
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Journal of King Saud University: Engineering Sciences
spelling doaj-art-a3440cd371d84fb784d88c060a684dcf2025-08-20T04:01:40ZengSpringerJournal of King Saud University: Engineering Sciences1018-36392213-15582025-07-0137411910.1007/s44444-025-00010-0Machine learning-based approach for bandwidth and frequency prediction of circular SIW antennaMd Mahabub Alam0Nurhafizah Abu Talip Yusof1Ahmad Afif Mohd Faudzi2Md Raihanul Islam Tomal3Md Ershadul Haque4Md. Suaibur Rahman5Faculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang Al-Sultan AbdullahFaculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang Al-Sultan AbdullahFaculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang Al-Sultan AbdullahFaculty of Computing, Universiti Malaysia Pahang Al-Sultan AbdullahSchool of Computing Mathematics and Engineering, Charles Sturt UniversityDepartment of Electrical and Electronics Engineering, Islamic University of TechnologyAbstract Machine Learning (ML) has significantly transformed antenna design by enabling efficient optimization of geometrical parameters, modeling complex electromagnetic behavior, and accelerating performance prediction with reduced computational cost. This study presents an ML-based approach to accurately predict the resonance frequencies and bandwidth of a novel triple-band circular Substrate Integrated Waveguide (SIW) antenna intended for K- and Ka-band satellite communication. The antenna features four symmetrically etched ring slots on the radiating patch and circularly arranged vias within a Rogers RT/Duroid 5880 substrate (20 × 15 × 1.6 mm3). The interaction between the TE₁₁ cavity mode and the ring slots facilitates controlled electromagnetic field leakage, enhancing radiation performance. A predictive ML framework was developed using six regression algorithms trained on significant geometrical parameters, such as ring slot radius, via diameter, and feedline width. Among them, the Extra Trees Regression model achieved over 98% accuracy, with errors below 0.1% for both resonance frequency and bandwidth predictions. The approach was validated through Computer Simulation Technology (CST) simulations and ML-based predictions, both demonstrating strong agreement. Although experimental fabrication was not included in this phase, the model offers a reliable foundation for future physical validation and prototyping. The results confirm that the proposed antenna structure, combined with the predictive power of ML, presents a promising solution for compact, high-performance antennas in satellite communication systems.https://doi.org/10.1007/s44444-025-00010-0SIWResonance frequencyBandwidthMachine learningK and Ka-bandSatellite communication
spellingShingle Md Mahabub Alam
Nurhafizah Abu Talip Yusof
Ahmad Afif Mohd Faudzi
Md Raihanul Islam Tomal
Md Ershadul Haque
Md. Suaibur Rahman
Machine learning-based approach for bandwidth and frequency prediction of circular SIW antenna
Journal of King Saud University: Engineering Sciences
SIW
Resonance frequency
Bandwidth
Machine learning
K and Ka-band
Satellite communication
title Machine learning-based approach for bandwidth and frequency prediction of circular SIW antenna
title_full Machine learning-based approach for bandwidth and frequency prediction of circular SIW antenna
title_fullStr Machine learning-based approach for bandwidth and frequency prediction of circular SIW antenna
title_full_unstemmed Machine learning-based approach for bandwidth and frequency prediction of circular SIW antenna
title_short Machine learning-based approach for bandwidth and frequency prediction of circular SIW antenna
title_sort machine learning based approach for bandwidth and frequency prediction of circular siw antenna
topic SIW
Resonance frequency
Bandwidth
Machine learning
K and Ka-band
Satellite communication
url https://doi.org/10.1007/s44444-025-00010-0
work_keys_str_mv AT mdmahabubalam machinelearningbasedapproachforbandwidthandfrequencypredictionofcircularsiwantenna
AT nurhafizahabutalipyusof machinelearningbasedapproachforbandwidthandfrequencypredictionofcircularsiwantenna
AT ahmadafifmohdfaudzi machinelearningbasedapproachforbandwidthandfrequencypredictionofcircularsiwantenna
AT mdraihanulislamtomal machinelearningbasedapproachforbandwidthandfrequencypredictionofcircularsiwantenna
AT mdershadulhaque machinelearningbasedapproachforbandwidthandfrequencypredictionofcircularsiwantenna
AT mdsuaiburrahman machinelearningbasedapproachforbandwidthandfrequencypredictionofcircularsiwantenna