EUVIMEDEUVIMED entdecken
Crossref

Inverse Design Method for Electromagnetic Periodic Structures Based on Physics-Informed Neural Network With Embedded Analytical Models

Yu-Hang Liu, Jing-Cheng Liang, Bing-Zhong Wang, Ren Wang

IEEE Transactions on Microwave Theory and Techniques · 2025-02 · 73 (2) · 844-853

DOI: 10.1109/tmtt.2024.3435970 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Microwave Theory and Techniques, 2025-02. Verfasst von Yu-Hang Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Sichuan Province, Aeronautical Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To achieve an efficient inverse design method for electromagnetic devices, this article introduces the physics-informed neural network with embedded analytical models (EAM-PINN). This approach combines embedded physical knowledge and external physical constraints and is applied to the inverse design of electromagnetic periodic structures. In EAM-PINN, we embed the physical knowledge of periodic structures into neural networks, specifically by replacing ordinary neurons with periodic neurons containing Floquet mode solutions to form neural networks and output electromagnetic fields. Then, we use the mode matching method to link the electromagnetic field with the structures, integrating them into the loss function as external physical constraints. Through EAM-PINN, we successfully perform inverse design of artificial magnetic conductors (AMCs) and frequency-selective surfaces (FSSs), demonstrating its effectiveness in designing electromagnetic periodic structures. Compared with traditional neural networks, EAM-PINN inherits the benefits of traditional PINN, requiring fewer training data or even no data at all, and achieves faster inverse design. Moreover, EAM-PINN exhibits stronger learning capabilities and easier convergence compared with the traditional PINN.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Sichuan Province
  • Aeronautical Science Foundation of China

Zitieren

APA

Liu, Y., Liang, J., Wang, B., & Wang, R. (2025). Inverse Design Method for Electromagnetic Periodic Structures Based on Physics-Informed Neural Network With Embedded Analytical Models. IEEE Transactions on Microwave Theory and Techniques, 73(2), 844-853. https://doi.org/10.1109/tmtt.2024.3435970

Vancouver

Liu Y, Liang J, Wang B, Wang R. Inverse Design Method for Electromagnetic Periodic Structures Based on Physics-Informed Neural Network With Embedded Analytical Models. IEEE Transactions on Microwave Theory and Techniques. 2025;73(2):844-853. doi:10.1109/tmtt.2024.3435970

BibTeX
@article{Liu2025,
  author = {Liu, Yu-Hang and Liang, Jing-Cheng and Wang, Bing-Zhong and Wang, Ren},
  title = {Inverse Design Method for Electromagnetic Periodic Structures Based on Physics-Informed Neural Network With Embedded Analytical Models},
  journal = {IEEE Transactions on Microwave Theory and Techniques},
  year = {2025},
  volume = {73},
  number = {2},
  pages = {844--853},
  doi = {10.1109/tmtt.2024.3435970}
}
Kostenlos starten →