Developments of control system for ion source using machine learning. Issue 1 (1st April 2022)

• Record Type: Journal Article
• Authors: Morita, Y; Fukuda, M; Yorita, T; Kanda, H; Hatanaka, K; Saitou, T; Tamura, H; Yasuda, Y; Washio, T; Nakashima, Y; Iwasaki, M; Koay, H W; Takeda, K; Hara, T; Chong, T H; Zhao, H
• Is Part Of: Journal of physics. Volume 2244:Issue 1(2022)
• Publication Date: 2022-04-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2244/1/012105
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Various factors influence each other in an ion source. Therefore, when operating an ion source, it is necessary to optimize and adjust various parameters. This time, we performed an experiment to automize adjustment that maximizes the brightness of the beam using machine learning. By automatically adjusting 4 parameters, we succeeded in finding a point with a beam brightness of 4.32 × 10 -6 mA/(imm mrad) 2 in 25 steps. This shows that automatic adjustment using Bayesian optimization is feasible.