ECRIS2024 - List of Authors (Morita, Y.)

Paper	Title	Page
WEB3	Beam intensity prediction using ECR plasma images and machine learning	156
	Y. Morita, T. Nishi RIKEN, Saitama, Japan A. Kasagi Rikkyo University, Tokyo, Japan K. Kamakura University of Tokyo, Tokyo, Japan N. Oka National Institute of Information and Communications Technology, Tokyo, Japan
	Long-term beam stability is one of the important issues in supplying multivalent heavy ion beams using an Electron Cyclotron Resonance Ion Source (ECRIS). When the beam intensity drops for long-term operation, the ECRIS parameters need to be tuned to restore the original beam intensity. Continuous measurement of the beam intensity using a Faraday cup (FC) is impractical while the beam is in use. We have had to rely on an unreliable method of monitoring the total drain current to estimate the beam intensity during beamtime. To resolve this issue, we propose a new method for predicting the beam intensity at FC using machine learning. Our approach incorporates plasma images, captured through a hole in the beam extraction electrode, and operating parameters as input data for the machine learning model. In short-term test datasets, our model has successfully produced rough predictions of the beam intensity. This presentation will detail the prediction model and its prediction results on the test data.
DOI •	reference for this paper ※ doi:10.18429/JACoW-ECRIS2024-WEB3
About •	Received ※ 14 September 2024 — Revised ※ 18 October 2024 — Accepted ※ 02 February 2025 — Issued ※ 04 March 2025
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Beam intensity prediction using ECR plasma images and machine learning

156

Y. Morita, T. Nishi
RIKEN, Saitama, Japan
A. Kasagi
Rikkyo University, Tokyo, Japan
K. Kamakura
University of Tokyo, Tokyo, Japan
N. Oka
National Institute of Information and Communications Technology, Tokyo, Japan

Long-term beam stability is one of the important issues in supplying multivalent heavy ion beams using an Electron Cyclotron Resonance Ion Source (ECRIS). When the beam intensity drops for long-term operation, the ECRIS parameters need to be tuned to restore the original beam intensity. Continuous measurement of the beam intensity using a Faraday cup (FC) is impractical while the beam is in use. We have had to rely on an unreliable method of monitoring the total drain current to estimate the beam intensity during beamtime. To resolve this issue, we propose a new method for predicting the beam intensity at FC using machine learning. Our approach incorporates plasma images, captured through a hole in the beam extraction electrode, and operating parameters as input data for the machine learning model. In short-term test datasets, our model has successfully produced rough predictions of the beam intensity. This presentation will detail the prediction model and its prediction results on the test data.

DOI •

reference for this paper ※ doi:10.18429/JACoW-ECRIS2024-WEB3

About •

Received ※ 14 September 2024 — Revised ※ 18 October 2024 — Accepted ※ 02 February 2025 — Issued ※ 04 March 2025

Cite •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)