A Machine Learning Approach for the Tune Estimation in the LHC

Leander Grech,Diogo Alves,Gianluca Valentino

doi:10.3390/info12050197

Leander Grech, Diogo Alves + Show 1 more

Open Access

https://doi.org/10.3390/info12050197

Copy DOI

Abstract

The betatron tune in the Large Hadron Collider (LHC) is measured using a Base-Band Tune (BBQ) system. The processing of these BBQ signals is often perturbed by 50 Hz noise harmonics present in the beam. This causes the tune measurement algorithm, currently based on peak detection, to provide incorrect tune estimates during the acceleration cycle with values that oscillate between neighbouring harmonics. The LHC tune feedback (QFB) cannot be used to its full extent in these conditions as it relies on stable and reliable tune estimates. In this work, we propose new tune estimation algorithms, designed to mitigate this problem through different techniques. As ground-truth of the real tune measurement does not exist, we developed a surrogate model, which allowed us to perform a comparative analysis of a simple weighted moving average, Gaussian Processes and different deep learning techniques. The simulated dataset used to train the deep models was also improved using a variant of Generative Adversarial Networks (GANs) called SimGAN. In addition, we demonstrate how these methods perform with respect to the present tune estimation algorithm.

Highlights

Introduction the Large Hadron Collider (LHC)Information 2021, 12, 197.The tune (Q) of a circular accelerator is defined as the number of betatron oscillations per turn [1]
The tune estimates obtained from each respective model and algorithm were subtracted from the ground-truth resonances used to generate the spectra to obtain a set of errors per tune estimation system
From real Base-Band Q (BBQ) spectra it is difficult to show any objective difference between the performance of the new Machine Learning (ML) tune estimation models and the various algorithmic approaches (BQ, Weighted Moving Average (WMA) and GP)

Summary

Introduction

The tune (Q) of a circular accelerator is defined as the number of betatron oscillations per turn [1] This is a critical parameter in the Large Hadron Collider (LHC), which has to be monitored and corrected in order to ensure stable operations [2] and adequate beam lifetime. The BBQ system in the LHC is sensitive enough to not require that the beam be externally excited in order to measure the tune. This normally results in a frequency spectrum, such as the one shown, where the value of the betatron tune frequency should, in principle, be the frequency position of the dominant peak [3,4]. FLATTOP is a beam mode which occurs after the LHC energy ramp and before collision optics are set [5]

Objectives

Results

Discussion

Conclusion