EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Microstrip Antenna Design Supported by Generative Adversarial Networks

Silvania T. Goncalves, Gilliard N. Malheiros-Silveira

AI · 02.12.2024 · 5 (4) · 2693-2706

DOI: 10.3390/ai5040129 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI, online erschienen am 02.12.2024. Verfasst von Silvania T. Goncalves und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Council for Scientific and Technological Development—CNPq, FAEPEX, Coordenação de Aperfeiçoamento de Pessoal de Nivel Superior—Brasil (CAPES).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We report on the effectiveness of using generative neural networks in an antenna design. We considered the modeling of microstrip antennas as they have significant advantages, such as a low profile, lightness, and ease of manufacture, which make them versatile for various applications. We designed, trained, and analyzed generative models applied to the modeling of these antennas without losing the generalizability of the application of these models to any antenna. We started with a Generative Adversarial Network (GAN), which was trained with data related to the antenna models for operation within the frequency range of 1 to 30 GHz. Using the synthetic data produced by the GAN resulted in antenna designs with dimensions and electromagnetic properties that were very close to the expected values. Next, a model was developed using a Conditional GAN (CGAN), which was trained to generate antenna characteristic data conditioned on an arbitrary central frequency, i.e., 2.4 GHz (generally used for Bluetooth, Wi-Fi, and ZigBee technologies), to enable better control over the process of generating these synthetic data. The CGAN model could satisfactorily generate synthetic data for this frequency range, simultaneously considering substrates with different dielectric permittivities. This study reveals that both generative models could produce synthetic data that were very close to the expected data, as evidenced by the low error values. Additionally, in terms of application, the models could provide both geometries and more than one antenna characteristic (resonance, bandwidth, and quality factor), which is very useful for direct application to practical designs.

Förderung

  • National Council for Scientific and Technological Development—CNPq
  • FAEPEX
  • Coordenação de Aperfeiçoamento de Pessoal de Nivel Superior—Brasil (CAPES)

Zitieren

APA

Goncalves, S. T., & Malheiros-Silveira, G. N. (2024). Microstrip Antenna Design Supported by Generative Adversarial Networks. AI, 5(4), 2693-2706. https://doi.org/10.3390/ai5040129

Vancouver

Goncalves ST, Malheiros-Silveira GN. Microstrip Antenna Design Supported by Generative Adversarial Networks. AI. 2024;5(4):2693-2706. doi:10.3390/ai5040129

BibTeX
@article{Goncalves2024,
  author = {Goncalves, Silvania T. and Malheiros-Silveira, Gilliard N.},
  title = {Microstrip Antenna Design Supported by Generative Adversarial Networks},
  journal = {AI},
  year = {2024},
  volume = {5},
  number = {4},
  pages = {2693--2706},
  doi = {10.3390/ai5040129}
}
Kostenlos starten →