| Issue |
EPJ Web Conf.
Volume 315, 2024
International Workshop on Future Linear Colliders (LCWS2024)
|
|
|---|---|---|
| Article Number | 02004 | |
| Number of page(s) | 7 | |
| Section | Accelerator | |
| DOI | https://doi.org/10.1051/epjconf/202431502004 | |
| Published online | 18 December 2024 | |
https://doi.org/10.1051/epjconf/202431502004
SuperKEKB positron beam tuning using machine learning
KEK
* e-mail: takuya.natsui@kek.jp
Published online: 18 December 2024
In the KEK injector linac, four-ring simultaneous top-up injection has been achieved, and beam tuning is always performed in various beam modes. As there are four beam modes, the optimum magnet current and RF phase must be selected for each. There are numerous tuning knobs for each mode; thus, it takes significant time and manpower to find the optimum state for all modes. In particular, tuning the positron primary electron beam requires delicate parameter adjustment due to its large charge. Significant time has been spent on this tuning. Therefore, an automatic tuning tool has been developed. Automatic tuning is realized using Bayesian optimization and the downhill simplex method. This tool can be used for any beam tuning on our system and has been particularly useful for positron beam tuning.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.