Optimization of Loads for Antenna-Based Scattering Systems Using Feedforward Neural Networks

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

Major/Subject

Mcode

Degree programme

Language

en

Pages

Series

18th European Conference on Antennas and Propagation, EuCAP 2024

Abstract

In this paper, we optimize the passive loads of a scattering system consisting of multiple coupled antennas using multi-layer feedforward neural networks. The developed in this study architectures, trained to solve a classification task, predict the load impedance values connected to unit antenna scatterers based on the bistatic radar cross-section of a structure. Trained networks exhibit potential in optimizing load values for scattering redirection among predefined directions. To demonstrate the applicability of the proposed method, two multi-layer feedforward neural networks are trained and used to predict proper load impedances for different scattering objectives. Additionally, existing limitations of the method usage are discussed with the potential ways to mitigate them.

Description

Publisher Copyright: © 2024 18th European Conference on Antennas and Propagation, EuCAP 2024. All Rights Reserved.

Other note

Citation

Kuznetsov, A D, Holopainen, J & Viikari, V 2024, Optimization of Loads for Antenna-Based Scattering Systems Using Feedforward Neural Networks. in 18th European Conference on Antennas and Propagation, EuCAP 2024. IEEE, European Conference on Antennas and Propagation, Glasgow, United Kingdom, 17/03/2024. https://doi.org/10.23919/EuCAP60739.2024.10501204