Highly Localized Cylindrical Wave Synthesis for Linear Array Based on Convolutional Neural Network

Chengcheng Guan; Rui Cai; Da Huang; Ming Bai

doi:10.1109/NEMO62710.2025.11215522

Highly Localized Cylindrical Wave Synthesis for Linear Array Based on Convolutional Neural Network

Chengcheng Guan
, Rui Cai
, Da Huang
, Ming Bai^*

^*Corresponding author for this work

School of Electronic and Information Engineering

Beihang University
CNC Processing Plant of AVIC Xi'an Aircraft Industry Company LTD

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, a generalized method based on convolutional neural network is proposed for the synthesis of highly localized quasi-cylindrical wave in the near field from a linear array. The convolutional neural network (CNN) is exploited to optimize the excitation amplitudes and phases. Simulation and measurement results for an 8 elements X-band uniform linear array are presented, demonstrating that the trained network produces cylindrical wavefront in a specific zone in the near field with flat amplitude and phase, which can help consequently enhance the accuracy of measurement and the efficiency of directional energy transmission.

Original language	English
Title of host publication	IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798331597993
DOIs	https://doi.org/10.1109/NEMO62710.2025.11215522
State	Published - 2025
Event	2025 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Tianjin, China Duration: 29 Jul 2025 → 1 Aug 2025

Publication series

Name	IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings

Conference

Conference	2025 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025
Country/Territory	China
City	Tianjin
Period	29/07/25 → 1/08/25

Keywords

convolutional neural network
Highly localized cylindrical wave synthesis
near field
uniform linear array

Access to Document

10.1109/NEMO62710.2025.11215522

Cite this

Guan, C., Cai, R., Huang, D., & Bai, M. (2025). Highly Localized Cylindrical Wave Synthesis for Linear Array Based on Convolutional Neural Network. In IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings (IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NEMO62710.2025.11215522

Guan, Chengcheng ; Cai, Rui ; Huang, Da et al. / Highly Localized Cylindrical Wave Synthesis for Linear Array Based on Convolutional Neural Network. IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2025. (IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings).

@inproceedings{ef7692928be04fccbdb8c3da0d9ed3d7,

title = "Highly Localized Cylindrical Wave Synthesis for Linear Array Based on Convolutional Neural Network",

abstract = "In this paper, a generalized method based on convolutional neural network is proposed for the synthesis of highly localized quasi-cylindrical wave in the near field from a linear array. The convolutional neural network (CNN) is exploited to optimize the excitation amplitudes and phases. Simulation and measurement results for an 8 elements X-band uniform linear array are presented, demonstrating that the trained network produces cylindrical wavefront in a specific zone in the near field with flat amplitude and phase, which can help consequently enhance the accuracy of measurement and the efficiency of directional energy transmission.",

keywords = "convolutional neural network, Highly localized cylindrical wave synthesis, near field, uniform linear array",

author = "Chengcheng Guan and Rui Cai and Da Huang and Ming Bai",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 ; Conference date: 29-07-2025 Through 01-08-2025",

year = "2025",

doi = "10.1109/NEMO62710.2025.11215522",

language = "英语",

series = "IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings",

address = "美国",

}

Guan, C, Cai, R, Huang, D & Bai, M 2025, Highly Localized Cylindrical Wave Synthesis for Linear Array Based on Convolutional Neural Network. in IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings. IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2025 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025, Tianjin, China, 29/07/25. https://doi.org/10.1109/NEMO62710.2025.11215522

Highly Localized Cylindrical Wave Synthesis for Linear Array Based on Convolutional Neural Network. / Guan, Chengcheng; Cai, Rui; Huang, Da et al.
IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2025. (IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Highly Localized Cylindrical Wave Synthesis for Linear Array Based on Convolutional Neural Network

AU - Guan, Chengcheng

AU - Cai, Rui

AU - Huang, Da

AU - Bai, Ming

PY - 2025

Y1 - 2025

N2 - In this paper, a generalized method based on convolutional neural network is proposed for the synthesis of highly localized quasi-cylindrical wave in the near field from a linear array. The convolutional neural network (CNN) is exploited to optimize the excitation amplitudes and phases. Simulation and measurement results for an 8 elements X-band uniform linear array are presented, demonstrating that the trained network produces cylindrical wavefront in a specific zone in the near field with flat amplitude and phase, which can help consequently enhance the accuracy of measurement and the efficiency of directional energy transmission.

AB - In this paper, a generalized method based on convolutional neural network is proposed for the synthesis of highly localized quasi-cylindrical wave in the near field from a linear array. The convolutional neural network (CNN) is exploited to optimize the excitation amplitudes and phases. Simulation and measurement results for an 8 elements X-band uniform linear array are presented, demonstrating that the trained network produces cylindrical wavefront in a specific zone in the near field with flat amplitude and phase, which can help consequently enhance the accuracy of measurement and the efficiency of directional energy transmission.

KW - convolutional neural network

KW - Highly localized cylindrical wave synthesis

KW - near field

KW - uniform linear array

UR - https://www.scopus.com/pages/publications/105022616828

U2 - 10.1109/NEMO62710.2025.11215522

DO - 10.1109/NEMO62710.2025.11215522

M3 - 会议稿件

AN - SCOPUS:105022616828

T3 - IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings

BT - IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2025 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025

Y2 - 29 July 2025 through 1 August 2025

ER -

Guan C, Cai R, Huang D, Bai M. Highly Localized Cylindrical Wave Synthesis for Linear Array Based on Convolutional Neural Network. In IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2025. (IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization for RF, Microwave, and Terahertz Applications, NEMO 2025 - Proceedings). doi: 10.1109/NEMO62710.2025.11215522

Highly Localized Cylindrical Wave Synthesis for Linear Array Based on Convolutional Neural Network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this