Fast Adaptive Neural Control of Resonant Extraction at Fermilab

TL;DR

This paper reports on developing and comparing machine learning controllers for resonant beam extraction at Fermilab, focusing on performance, training efficiency, and edge-based implementation for adaptive control.

Contribution

It introduces ML-based controllers optimized via simulations for resonant extraction, highlighting their performance and training efficiency improvements.

Findings

ML controllers outperform classical methods in simulation.

Training efficiency varies among models, impacting adaptive control.

Edge-optimized ML models enable real-time inference.

Abstract

We present progress on the development of a machine learning (ML) regulation system for third-order resonant extraction of the beam delivered to the Mu2e experiment at Fermilab. We consider classical and ML-based controllers optimized on semi-analytic simulations and provide performance comparisons for several models. Additionally, we discuss the efficiency of each model in training, which has implications for future work on adaptive control. We also discuss progress on developing optimized implementations of ML models for edge-based inference.