Optimization of the injection beam line at the Cooler Synchrotron COSY using Bayesian Optimization

TL;DR

This paper demonstrates how Bayesian optimization can effectively enhance the injection beam line of the COSY synchrotron, leading to improved beam intensity with fewer manual adjustments.

Contribution

It applies Bayesian optimization to a complex accelerator system, showcasing its advantages over manual tuning methods for beam line optimization.

Findings

Bayesian optimization outperforms manual tuning in speed and quality.

Significant increase in beam intensity achieved.

Efficient optimization with limited observations.

Abstract

The complex non-linear processes in multi-dimensional parameter spaces, that are typical for an accelerator, are a natural application for machine learning algorithms. This paper reports on the use of Bayesian optimization for the optimization of the Injection Beam Line (IBL) of the Cooler Synchrotron storage ring COSY at the Forschungszentrum J\"ulich, Germany. Bayesian optimization is a machine learning method that optimizes a continuous objective function using limited observations. The IBL is composed of 15 quadrupoles and 28 steerers. The goal is to increase the beam intensity inside the storage ring. The results showed the effectiveness of the Bayesian optimization in achieving better/faster results compared to manual optimization.