Operational Accelerator Tuning via Model-Coupled Optics and Bayesian Steering

TL;DR

This paper introduces an online tuning method for particle accelerators that uses a digital twin and Bayesian optimization to improve efficiency, reliability, and safety during operation.

Contribution

The paper presents a novel approach that decouples optics tuning from steering, reducing parameter space complexity and enhancing convergence speed and reliability.

Findings

Iterations to high transmission tunes reduced by 4-6 times

Final transmission rates in the mid- to high-90% range

Decoupling optics from steering improves convergence and safety

Abstract

We present an on-line tuning strategy for the ISAC post-accelerator that pre-sets machine optics with a digital twin and then performs Bayesian optimization for steering under online operation with beam. The model computes end-to-end tunes in seconds and interfaces with the control system under device bounds, slew-rate limits, and loss interlocks. We report three experimental case studies demonstrating that decoupling optics from steering yields faster and more reliable convergence than a fully Bayesian optics-plus-steering baseline under identical conditions. Across these cases, iterations to high transmission tunes are reduced by a factor of 4-6, with final average transmissions in the mid- to high-90% range. By factorizing optics from steering, the dimensionality of the parameter space is reduced, convergence becomes more predictable, and operational safeguards are easier to enforce.