An Antenna Array Design Method Based on Residual Graph Neural Network

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A learning method based on residual graph neural network was proposed to improve the efficiency of antenna array design. Firstly, the geometric parameters of the antenna array are processed into graph representation, which is used as the input features of the graph neural network. After the graph encoding process, the complex-valued fully connected network with residual connections is used to predict the radiation pattern of the antenna array. Based on the residual graph neural network, a seven-element linear array structure is designed to prove its effectiveness.

Original languageEnglish
Title of host publication2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781733509657
DOIs
StatePublished - 2023
Event2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023 - Hangzhou, China
Duration: 15 Aug 202318 Aug 2023

Publication series

Name2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

Conference

Conference2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023
Country/TerritoryChina
CityHangzhou
Period15/08/2318/08/23

Keywords

  • antenna array
  • graph neural network
  • optimization
  • residual

Fingerprint

Dive into the research topics of 'An Antenna Array Design Method Based on Residual Graph Neural Network'. Together they form a unique fingerprint.

Cite this