Robust Forward Surrogates for Free-Form Frequency Selective Surfaces With Uncertainty Quantification by Bayesian Deep Learning
IEEE Transactions on Antennas and Propagation · 2026-04 · 74 (4) · 3189-3202
DOI: 10.1109/tap.2026.3655177 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Antennas and Propagation, 2026-04. Verfasst von Erji Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: NSFC Ye Qisen Joint Fund, National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China.
Abstract (Originalsprache)
The free-form frequency selective surface (FF-FSS) is modeled with a binary matrix with a shape of (128, 128), approximating a continuous designable space. The free-form representation enables the realization of various functionalities across a wide frequency band, including bandpass, band-stop, and more diverse responses. To overcome the computational burden of full-wave simulations, an efficient forward surrogate based on Bayesian deep learning (DL) is introduced, capable of predicting electromagnetic (EM) responses (e.g., transmission coefficients) and simultaneously realizing uncertainty quantification (UQ). Specifically, the validation of these predictions is demonstrated using both statistical and individual results, and the model’s capability to capture uncertainty is verified through topological deformation and transmission coefficient noise. Furthermore, the proposed framework exhibits exceptional robustness across distinct FSS patterns, that is, artificial parametric structures and lower-dimensional binary matrices. Additionally, its expanded applications, such as those involving distinct periodicities, oblique incidence, and two-layer FF-FSSs, are also investigated. Finally, we present an efficient prescreening methodology for identifying candidate designs for specific targets, where the forward surrogate yields similar responses with distinguished uncertainty levels. The practical applicability of our approach is experimentally validated through the fabrication and measurement of two prototypes tailored to specific design targets, each exhibiting different prediction uncertainties.
Förderung
- NSFC Ye Qisen Joint Fund
- National Natural Science Foundation of China
- Zhejiang Provincial Natural Science Foundation of China
- co-supervised by Zhun Wei, Qian Wang, and Wen-Yan Yin.
Zitieren
APA
Li, E., Zhu, E., He, S., Wang, B., Wang, Q., Wei, Z., & Yin, W. (2026). Robust Forward Surrogates for Free-Form Frequency Selective Surfaces With Uncertainty Quantification by Bayesian Deep Learning. IEEE Transactions on Antennas and Propagation, 74(4), 3189-3202. https://doi.org/10.1109/tap.2026.3655177
Vancouver
Li E, Zhu E, He S, Wang B, Wang Q, Wei Z, et al. Robust Forward Surrogates for Free-Form Frequency Selective Surfaces With Uncertainty Quantification by Bayesian Deep Learning. IEEE Transactions on Antennas and Propagation. 2026;74(4):3189-3202. doi:10.1109/tap.2026.3655177
BibTeX
@article{Li2026,
author = {Li, Erji and Zhu, Enze and He, Siyuan and Wang, Bao and Wang, Qian and Wei, Zhun and Yin, Wen-Yan},
title = {Robust Forward Surrogates for Free-Form Frequency Selective Surfaces With Uncertainty Quantification by Bayesian Deep Learning},
journal = {IEEE Transactions on Antennas and Propagation},
year = {2026},
volume = {74},
number = {4},
pages = {3189--3202},
doi = {10.1109/tap.2026.3655177}
}
EUVIMED