In literature, heuristic algorithms have been successfully applied to a number of electromagnetic problems. The associated cost functions are commonly linked to full-wave analysis, leading to complexity and high computational expense. Arti-cial Neural Network is one of the most e®ective biological inspired techniques. In this article, an e±cient surrogate model is trained to replace the full-wave analysis in optimizing the bandwidth of microstrip antenna. The numerical comparison between ANN substitution model and full-wave characterization shows signi-cant improvements in time convergence and computational cost. To verify the robustness of this approach, all these concepts are integrated into a case study represented by a rectangular ring antenna with proximity-coupled feed antenna.

Optimization of a dual ring antenna by means of artifcial neural network

GRIMACCIA, FRANCESCO;MUSSETTA, MARCO;ZICH, RICCARDO
2014

Abstract

In literature, heuristic algorithms have been successfully applied to a number of electromagnetic problems. The associated cost functions are commonly linked to full-wave analysis, leading to complexity and high computational expense. Arti-cial Neural Network is one of the most e®ective biological inspired techniques. In this article, an e±cient surrogate model is trained to replace the full-wave analysis in optimizing the bandwidth of microstrip antenna. The numerical comparison between ANN substitution model and full-wave characterization shows signi-cant improvements in time convergence and computational cost. To verify the robustness of this approach, all these concepts are integrated into a case study represented by a rectangular ring antenna with proximity-coupled feed antenna.
PROGRESS IN ELECTROMAGNETICS RESEARCH B
Condensed Matter Physics; Electrical and Electronic Engineering; Electronic, Optical and Magnetic Materials
File in questo prodotto:
File Dimensione Formato  
05.13112806_PIERB.pdf

accesso aperto

Descrizione: Principal
: Publisher’s version
Dimensione 1.3 MB
Formato Adobe PDF
1.3 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11311/968485
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? ND
social impact