CERN Accelerating science

Article
Title	Machine Learning Models for Breakdown Prediction in RF Cavities for Accelerators
Related title	MACHINE LEARNING MODELS FOR BREAKDOWN PREDICTION IN RF CAVITIES FOR ACCELERATORS
Author(s)	Obermair, Christoph (CERN ; Graz, Tech. U.) ; Apollonio, Andrea (CERN) ; Cartier-Michaud, Thomas (CERN) ; Catalán Lasheras, Nuria (CERN) ; Felsberger, Lukas (CERN) ; Millar, William L (CERN) ; Pernkopf, Franz (CERN ; Graz, Tech. U.) ; Wuensch, Walter (CERN)
Publication	Geneva : JACoW, 2021
Number of pages	4
In:	JACoW IPAC 2021 (2021) 1068-1071
In:	12th International Particle Accelerator Conference (IPAC 2021), Online, 24 - 28 May 2021, pp.1068-1071
DOI	10.18429/JACoW-IPAC2021-MOPAB344
Subject category	Accelerators and Storage Rings
Abstract	Radio Frequency (RF) breakdowns are one of the most prevalent limits in RF cavities for particle accelerators. During a breakdown, field enhancement associated with small deformations on the cavity surface results in electrical arcs. Such arcs degrade a passing beam and if they occur frequently, they can cause irreparable damage to the RF cavity surface. In this paper, we propose a machine learning approach to predict the occurrence of breakdowns in CERN’s Compact LInear Collider (CLIC) accelerating structures. We discuss state-of-the-art algorithms for data exploration with unsupervised machine learning, breakdown prediction with supervised machine learning, and result validation with Explainable-Artificial Intelligence (Explainable AI). By interpreting the model parameters of various approaches, we go further in addressing opportunities to elucidate the physics of a breakdown and improve accelerator reliability and operation.
Copyright/License	publication: © 2021 (License: CC-BY-3.0)

Corresponding record in: Inspire