Potentials of machine learning in vacuum electronic devices demonstrated by the design of a magnetron injection gun

Liang Zhang; Adrian W. Cross

doi:10.1109/TED.2021.3075166

Potentials of machine learning in vacuum electronic devices demonstrated by the design of a magnetron injection gun

Liang Zhang, Adrian W. Cross

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

32 Downloads (Pure)

Abstract

Great progress has been made on machine learning and its applications are expanding rapidly nowadays. Through the case study of optimizing a magnetron injection gun for gyrotron devices, the functions of machine learning were investigated by using two supervised learning algorithms, regression trees and artificial neural networks. They showed excellent performance in predicting the outputs, exploring the importance of the input parameters and the relationship with the output parameters. Machine learning can be a useful tool in the development of microwave vacuum electron devices.

Original language	English
Pages (from-to)	3028 - 3033
Number of pages	6
Journal	IEEE Transactions on Electron Devices
Volume	68
Issue number	6
Early online date	5 May 2021
DOIs	https://doi.org/10.1109/TED.2021.3075166
Publication status	Published - 1 Jun 2021

Keywords

machine learning
microwave vacuum electron device
magnetron injection gun
regression tree
artificial neural networks
supervised learning

Access to Document

10.1109/TED.2021.3075166

Zhang-Cross-IEEE-TOED-2021-Potentials-of-machine-learning-in-vacuum-electronic-devices-demonstratedAccepted author manuscript, 772 KB

2 Finished

Sheet electron beam vacuum electronic devices for the generation of high power THz radiation
Cross, A. (Principal Investigator), He, W. (Co-investigator), Phelps, A. (Co-investigator) & Zhang, L. (Research Co-investigator)
EPSRC (Engineering and Physical Sciences Research Council)
5/03/19 → 4/03/21
Project: Research
Cockcroft Institute
McKenna, P. (Principal Investigator), Cross, A. (Co-investigator), Eliasson, B. (Co-investigator), Gray, R. (Co-investigator), Hidding, B. (Co-investigator), Jaroszynski, D. (Co-investigator), McNeil, B. (Co-investigator), Ronald, K. (Co-investigator), Sheng, Z.-M. (Co-investigator) & Zhang, L. (Research Co-investigator)
University of Liverpool, Lancaster University, University of Manchester, STFC Science and Technology Facilities Council
1/04/17 → 31/03/22
Project: Research

Data for: "Magnetron Injection Gun for high-power gyroklystron"
Zhang, L. (Creator), Cross, A. (Owner) & Nix, L. (Contributor), University of Strathclyde, 1 Jun 2021
DOI: 10.15129/48f5ca92-c244-4426-95d8-24a22fb60e08
Dataset

5 Citations
1 Article

Magnetron injection gun for high-power gyroklystron
Zhang, L., Nix, L. J. R. & Cross, A. W., Nov 2020, In: IEEE Transactions on Electron Devices. 67, 11, p. 5151-5157 7 p.
Research output: Contribution to journal › Article › peer-review

Open Access
File
9 Citations (Scopus)

77 Downloads (Pure)

Cite this

@article{165dfdc3b4e4404a8d4f17b58e075ea5,

title = "Potentials of machine learning in vacuum electronic devices demonstrated by the design of a magnetron injection gun",

abstract = "Great progress has been made on machine learning and its applications are expanding rapidly nowadays. Through the case study of optimizing a magnetron injection gun for gyrotron devices, the functions of machine learning were investigated by using two supervised learning algorithms, regression trees and artificial neural networks. They showed excellent performance in predicting the outputs, exploring the importance of the input parameters and the relationship with the output parameters. Machine learning can be a useful tool in the development of microwave vacuum electron devices.",

keywords = "machine learning, microwave vacuum electron device, magnetron injection gun, regression tree, artificial neural networks, supervised learning",

author = "Liang Zhang and Cross, {Adrian W.}",

note = "{\textcopyright} 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",

year = "2021",

month = jun,

day = "1",

doi = "10.1109/TED.2021.3075166",

language = "English",

volume = "68",

pages = "3028 -- 3033",

journal = "IEEE Transactions on Electron Devices",

issn = "0018-9383",

number = "6",

}

TY - JOUR

T1 - Potentials of machine learning in vacuum electronic devices demonstrated by the design of a magnetron injection gun

AU - Zhang, Liang

AU - Cross, Adrian W.

N1 - © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2021/6/1

Y1 - 2021/6/1

N2 - Great progress has been made on machine learning and its applications are expanding rapidly nowadays. Through the case study of optimizing a magnetron injection gun for gyrotron devices, the functions of machine learning were investigated by using two supervised learning algorithms, regression trees and artificial neural networks. They showed excellent performance in predicting the outputs, exploring the importance of the input parameters and the relationship with the output parameters. Machine learning can be a useful tool in the development of microwave vacuum electron devices.

AB - Great progress has been made on machine learning and its applications are expanding rapidly nowadays. Through the case study of optimizing a magnetron injection gun for gyrotron devices, the functions of machine learning were investigated by using two supervised learning algorithms, regression trees and artificial neural networks. They showed excellent performance in predicting the outputs, exploring the importance of the input parameters and the relationship with the output parameters. Machine learning can be a useful tool in the development of microwave vacuum electron devices.

KW - machine learning

KW - microwave vacuum electron device

KW - magnetron injection gun

KW - regression tree

KW - artificial neural networks

KW - supervised learning

U2 - 10.1109/TED.2021.3075166

DO - 10.1109/TED.2021.3075166

M3 - Article

SN - 0018-9383

VL - 68

SP - 3028

EP - 3033

JO - IEEE Transactions on Electron Devices

JF - IEEE Transactions on Electron Devices

IS - 6

ER -

Potentials of machine learning in vacuum electronic devices demonstrated by the design of a magnetron injection gun

Abstract

Keywords

Access to Document

Fingerprint

Projects

Sheet electron beam vacuum electronic devices for the generation of high power THz radiation

Cockcroft Institute

Datasets

Data for: "Magnetron Injection Gun for high-power gyroklystron"

Research output

Magnetron injection gun for high-power gyroklystron

Cite this