Automated RF Phase Adjustment for Beam Stabilization in the Fermilab Linac

TL;DR

This paper presents a machine learning-based system for automating RF phase adjustments in the Fermilab Linac to stabilize the beam, reducing manual effort and improving reliability.

Contribution

It introduces a prototype-based classification model utilizing synthetic data and custom loss functions for autonomous RF phase correction in particle accelerators.

Findings

Successful synthetic data generation improves model training

Custom loss functions ensure physically plausible predictions

System achieves stable beam acceleration with reduced manual intervention

Abstract

The Fermilab Linac experiences longitudinal beam phase drift, leading to increased particle loss, conventionally corrected through labor-intensive manual RF adjustments. This project explores machine learning-based automation for drift correction, employing a prototype-based classification approach. Our model utilizes a 34-dimensional feature set (RF settings and BPM readings) and leverages a 7x27 response matrix for system modeling. To overcome limited real-world data, we generate synthetic data, enhancing model training and generalizability. Custom loss functions, including a surrogate energy-consistent loss and a temporal smoothness constraint, ensure physically plausible drift predictions. The goal is a robust system for autonomous phase adjustments, ensuring stable beam acceleration and reduced manual intervention.