| アイテムタイプ |
会議発表論文 / Conference Paper(1) |
| 公開日 |
2024-12-25 |
| タイトル |
|
|
タイトル |
MULTI-OBJECTIVE BAYESIAN OPTIMIZATION OF ELECTRON CYCLOTRON RESONANCE ION SOURCE |
|
言語 |
en |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_5794 |
|
資源タイプ |
conference paper |
| アクセス権 |
|
|
アクセス権 |
metadata only access |
|
アクセス権URI |
http://purl.org/coar/access_right/c_14cb |
| 著者 |
Andrea De Franco
Akagi Tomoya
Itagaki Tomonobu
Kondo Keitaro
Masuda Kai
Benoit Bolzon
Nicolas Chauvin
Fabio Cismondi
Herve Dzitko
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Electron Cyclotron Resonance (ECR) ion sources typically require tuning by experts to achieve best performance. We developed a Multi-Objective Bayesian optimization for the ECR of the Linear IFMIF Prototype Accelerator (LIPAc). The free parameters are: the RF power fed, the gas flow, the position of 2 RF tuners and the current of 2 solenoid coils. The machine learning approach demonstrated a fast convergence to a working point where not only the extracted beam current is >125 mA, but also the emittance is successfully constrained to be <0.25 π mm mrad, and the rms intra-pulse and inter-pulse current fluctuations are <3 mA. We present the detailed algorithm, testing methodology, results achieved and encountered challenges posed by the dimensionality of the problem and evolving state of the system. |
| 書誌情報 |
Proceedings of the 21st Annual Meeting of Particle Accelerator Society of Japan
発行日 2024-12
|
| 関連サイト |
|
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://ibic12.kek.jp/mirror/www.pasj.jp/web_publish/pasj2024/proceedings/PDF/WEOT/WEOT02.pdf |
