AI-Driven Inverse Antenna Design in UWB Band: Embedding Forward Consistency Into Deep Learning Architectures
IEEE Transactions on Antennas and Propagation · 2026-02 · 74 (2) · 1356-1370
DOI: 10.1109/tap.2025.3641248 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Antennas and Propagation, 2026-02. Verfasst von Olaoluwa A. Adegboye und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: U.S. Army Research Office, U.S. National Science Foundation.
Abstract (Originalsprache)
This work presents a deep learning-based inverse design framework for rapid prototyping of fork antennas operating within the ultrawideband (UWB) frequency. By integrating a pretrained frozen forward model into the inverse training process, the proposed method with forward-consistency loss ensures that predicted antenna geometries yield physically valid performance metrics. Three models were trained: deep neural network (DNN), long short-term memory (LSTM), and echo state network (ESN), to map performance targets to antenna dimensions. The results show that the models trained with forward-consistency loss achieve a lower error in return loss, bandwidth, and frequency metrics. The proposed framework considering both forward loss and reverse loss outperforms inverse-only models, especially in complex high-frequency wideband scenarios. DNN and LSTM models demonstrated the best generalization at 3.5 and 8 GHz, while all models significantly reduced the computational cost of antenna design compared to conventional simulation sweeps.
Förderung
- U.S. Army Research Office
- U.S. National Science Foundation
Zitieren
APA
Adegboye, O. A., Akinola, T. A., Li, X., & Qian, L. (2026). AI-Driven Inverse Antenna Design in UWB Band: Embedding Forward Consistency Into Deep Learning Architectures. IEEE Transactions on Antennas and Propagation, 74(2), 1356-1370. https://doi.org/10.1109/tap.2025.3641248
Vancouver
Adegboye OA, Akinola TA, Li X, Qian L. AI-Driven Inverse Antenna Design in UWB Band: Embedding Forward Consistency Into Deep Learning Architectures. IEEE Transactions on Antennas and Propagation. 2026;74(2):1356-1370. doi:10.1109/tap.2025.3641248
BibTeX
@article{Adegboye2026,
author = {Adegboye, Olaoluwa A. and Akinola, Taoreed A. and Li, Xiangfang and Qian, Lijun},
title = {AI-Driven Inverse Antenna Design in UWB Band: Embedding Forward Consistency Into Deep Learning Architectures},
journal = {IEEE Transactions on Antennas and Propagation},
year = {2026},
volume = {74},
number = {2},
pages = {1356--1370},
doi = {10.1109/tap.2025.3641248}
}
EUVIMED