Speaker
Description
The Advanced Photon Source (APS) facility has just completed an upgrade to become one of the world’s brightest storage-ring light sources. For the first time, machine learning (ML) methods have been developed and used as part of the baseline commissioning plan. One such method is Bayesian optimization (BO) – a versatile tool for efficient high-dimensional single and multi-objective tuning, as well as surrogate model construction and other purposes. In this paper we will present our development work on adapting BO to practical control room problems such as tuning linac and booster transmission efficiency, injection stabilization, enlarging storage ring dynamic and momentum apertures, and various other tasks. We will also show first experimental results of these efforts, including achieving initial beam capture in the APS-U storage ring. Given the success of BO methods at APS, we are working on tighter ML method integration into the standard control room procedures through a dedicated graphical interface.
Funding Agency
The work is supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357
| Region represented | North America |
|---|---|
| Paper preparation format | LaTeX |
