Skip to main navigation Skip to search Skip to main content

Elliptical Gaussian Beam Decomposition Using Multi-Layer Perceptron Network

  • Chuan Shi
  • , Lei Zhao
  • , Junpeng Shi
  • , Jiahui Zhao
  • , Shiyuan Zhang
  • , Ming Bai

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

Abstract

This paper investigates Elliptical Gaussian beam decomposition through the use of multi-layer perceptron (MLP) network. The advantage of employing the MLP network for elliptical Gaussian beam decomposition lies in its capability to maintain exceptional decomposition efficiency even when faced with intricate fields and sudden phase changes. Compared to the analytical method of elliptical Gaussian beam decomposition, the MLP network demonstrates lower residual energy in the decomposed residual field when decomposing the same number of sub-Gaussian beams. The results indicate that this technique has significant potential for the beam propagation in systems with large electrical size.

Original languageEnglish
Title of host publicationIEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications, IMWS-AMP 2023 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350308761
DOIs
StatePublished - 2023
Event2023 IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications, IMWS-AMP 2023 - Chengdu, China
Duration: 12 Nov 202315 Nov 2023

Publication series

NameIEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications, IMWS-AMP 2023 - Proceedings

Conference

Conference2023 IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications, IMWS-AMP 2023
Country/TerritoryChina
CityChengdu
Period12/11/2315/11/23

Fingerprint

Dive into the research topics of 'Elliptical Gaussian Beam Decomposition Using Multi-Layer Perceptron Network'. Together they form a unique fingerprint.

Cite this