17–22 May 2026
C.I.D
Europe/Zurich timezone

Online tuning of the NSLS-II injector using Bayesian optimization with different packages

MOP6307
18 May 2026, 16:00
2h
C.I.D

C.I.D

Deauville, France
Poster Presentation MC6.D13: Instrumentation: Artificial Intelligence Poster session

Speaker

Guimei Wang (Brookhaven National Laboratory)

Description

The injector of the NSLS-II consists of a linear accelerator (LINAC) that accelerates the electron beam to 170 MeV, followed by a linac-to-booster (LTB) transport line and a booster synchrotron that further increases the beam energy to 3 GeV. The performance of the LINAC and LTB is critical for achieving efficient and stable beam injection. Automated online tuning is a useful method for improving injector performance. In this paper, we present an automated tuning approach based on Bayesian optimization, using different packages to optimize the LINAC and LTB subsystems. We evaluate and compare these packages based on how well they improve injection efficiency. Our results show that Bayesian optimization can significantly improve injector performance and reveal differences in performance across the packages.

In which format do you inted to submit your paper? LaTeX
Preprint marking on your proceeding paper I wish my paper to be marked as preprint.
I no longer wish to present this contribution, please withdraw it. Keep my contribution

Author

Minghao Song (Brookhaven National Laboratory)

Co-authors

Yoshiteru Hidaka (Brookhaven National Laboratory) Guimei Wang (Brookhaven National Laboratory) Xi Yang (Brookhaven National Laboratory)

Presentation materials

There are no materials yet.