EUVIMEDEUVIMED entdecken
Crossref

Hybrid Neural Network-Driven Inverse Design of Metasurface for Ultrabroadband RCS Reduction

Rong Niu, Liming Si, Weiren Zhu, Xiue Bao, Kaiqiang Zhu, Houjun Sun, Fan Yang

IEEE Transactions on Antennas and Propagation · 2026-01 · 74 (1) · 837-847

DOI: 10.1109/tap.2025.3621515 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Antennas and Propagation, 2026-01. Verfasst von Rong Niu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Technology Innovation Center of Infrared Remote Sensing Metrology Technology of State Administration for Market Regulation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

An inverse design approach based on a hybrid artificial intelligence (AI) network is proposed for designing a metasurface with ultra broadband radar cross section (RCS) reduction. The metasurface comprises 1-bit coded unit cells designed by a tandem neural network (TNN), which enables efficient inverse prediction of unit cell parameters with absorption and polarization conversion as input. A deep $Q$ -network (DQN) optimizes the array arrangement to maximize RCS reduction bandwidth. This hybrid artificial network enables an efficient end-to-end inverse design from target RCS performance to unit cells and array arrangement, significantly improving the design efficiency and scalability. As an example, we design and fabricate an optically transparent metasurface with polyethylene terephthalate and indium tin oxide (ITO), achieving over 10 dB RCS reduction in an ultra wide frequency band from 3.7 to 18.7 GHz (133.9% relative bandwidth) and maintains angular stability up to 45° under dual polarizations. The proposed metasurface demonstrates strong potential for electromagnetic stealth applications that require optical transparency. Moreover, the hybrid AI network provides a scalable approach for developing advanced multifunctional metasurfaces.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Technology Innovation Center of Infrared Remote Sensing Metrology Technology of State Administration for Market Regulation
  • Beijing Natural Science Foundation of China-Haidian Original Innovation Joint Fund
  • Natural Science Foundation of Hebei Province
  • Open Research Fund of State Key Laboratory of Millimeter Waves
  • Open Research Fund of State Key Laboratory of Space-Ground Integrated Information Technology
  • Basic Research Foundation of Beijing Institute of Technology, China

Zitieren

APA

Niu, R., Si, L., Zhu, W., Bao, X., Zhu, K., Sun, H., & Yang, F. (2026). Hybrid Neural Network-Driven Inverse Design of Metasurface for Ultrabroadband RCS Reduction. IEEE Transactions on Antennas and Propagation, 74(1), 837-847. https://doi.org/10.1109/tap.2025.3621515

Vancouver

Niu R, Si L, Zhu W, Bao X, Zhu K, Sun H, et al. Hybrid Neural Network-Driven Inverse Design of Metasurface for Ultrabroadband RCS Reduction. IEEE Transactions on Antennas and Propagation. 2026;74(1):837-847. doi:10.1109/tap.2025.3621515

BibTeX
@article{Niu2026,
  author = {Niu, Rong and Si, Liming and Zhu, Weiren and Bao, Xiue and Zhu, Kaiqiang and Sun, Houjun and Yang, Fan},
  title = {Hybrid Neural Network-Driven Inverse Design of Metasurface for Ultrabroadband RCS Reduction},
  journal = {IEEE Transactions on Antennas and Propagation},
  year = {2026},
  volume = {74},
  number = {1},
  pages = {837--847},
  doi = {10.1109/tap.2025.3621515}
}
Kostenlos starten →