Simultaneous Inverse Design and Uncertainty Quantification for Frequency-Selective Rasorber With Tunable and Switchable Abilities by Bayesian Deep Learning
IEEE Transactions on Antennas and Propagation · 2024-05 · 72 (5) · 4349-4360
DOI: 10.1109/tap.2024.3384064 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Antennas and Propagation, 2024-05. Verfasst von Erji Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Science and Technology Major Project, Zhejiang Provincial Natural Science Foundation of China, Zhejiang Provincial Research and Development Project of China.
Abstract (Originalsprache)
A Bayesian deep learning (DL) scheme is proposed for simultaneous inverse design and uncertainty qualification (UQ) for frequency-selective rasorber (FSR) with switchable and tunable (S/T) abilities. The inversely designed FSR could work in single/two passband modes with bilateral absorption bands, where the tunable passband is controlled by varactor diodes, and the number of passbands is switched by elaborately designed bias lines. Further, the constraints of resonance are embedded into the inverse-design process based on the equivalent circuit model (ECM). In the uncertainty quantification process, both data uncertainty and model uncertainty of predicted S-parameters are modeled by the Bayesian neural network (BNN), whose effectiveness is verified by the correlation coefficient between true error and predicted uncertainty. At last, the inversely designed FSR sample is manufactured and measured, where the electromagnetic (EM) responses including S-parameters and absorption bands verify the accuracy and efficiency of the proposed method.
Förderung
- National Science and Technology Major Project
- Zhejiang Provincial Natural Science Foundation of China
- Zhejiang Provincial Research and Development Project of China
- key Basic Research of Basic Strengthening Program of the Science and Technology Commission
- Defense Industrial Technology Development Program
Zitieren
APA
Li, E., Zhu, E., Xiao, T., Wang, B., Wei, Z., Wang, Q., Qin, F., & Yin, W. (2024). Simultaneous Inverse Design and Uncertainty Quantification for Frequency-Selective Rasorber With Tunable and Switchable Abilities by Bayesian Deep Learning. IEEE Transactions on Antennas and Propagation, 72(5), 4349-4360. https://doi.org/10.1109/tap.2024.3384064
Vancouver
Li E, Zhu E, Xiao T, Wang B, Wei Z, Wang Q, et al. Simultaneous Inverse Design and Uncertainty Quantification for Frequency-Selective Rasorber With Tunable and Switchable Abilities by Bayesian Deep Learning. IEEE Transactions on Antennas and Propagation. 2024;72(5):4349-4360. doi:10.1109/tap.2024.3384064
BibTeX
@article{Li2024,
author = {Li, Erji and Zhu, Enze and Xiao, Tian and Wang, Bao and Wei, Zhun and Wang, Qian and Qin, Feng and Yin, Wen-Yan},
title = {Simultaneous Inverse Design and Uncertainty Quantification for Frequency-Selective Rasorber With Tunable and Switchable Abilities by Bayesian Deep Learning},
journal = {IEEE Transactions on Antennas and Propagation},
year = {2024},
volume = {72},
number = {5},
pages = {4349--4360},
doi = {10.1109/tap.2024.3384064}
}
EUVIMED