IPAC2021 - List of Authors (Felsberger, L.)

Paper	Title	Page
MOPAB344	Machine Learning Models for Breakdown Prediction in RF Cavities for Accelerators	1068
	C. Obermair, A. Apollonio, T. Cartier-Michaud, N. Catalán Lasheras, L. Felsberger, W.L. Millar, W. Wuensch CERN, Geneva, Switzerland C. Obermair, F. Pernkopf TUG, Graz, Austria
	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.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-MOPAB344
About •	paper received ※ 20 May 2021 paper accepted ※ 16 July 2021 issue date ※ 11 August 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPAB345	Availability Modeling of the Solid-State Power Amplifiers for the CERN SPS RF Upgrade	2308
	L. Felsberger, A. Apollonio, T. Cartier-Michaud, E. Montesinos, J.C. Oliveira, J.A. Uythoven CERN, Geneva, Switzerland
	Funding: This project has received funding from the Euratom research and training programme 2019-2020 under grant agreement No 945077. As part of the LHC Injector Upgrade program a complete overhaul of the Super Proton Synchrotron Radio-Frequency (RF) system took place. New cavities have been installed for which the solid-state technology was chosen to deliver a combined RF power of 2 MW from 2560 RF amplifiers. This strategy promises high availability as the system continues operation when some of the amplifiers fail. This study quantifies the operational availability that can be achieved with this new installation. The evaluation is based on a Monte Carlo simulation of the system using the novel AvailSim4 simulation software. A model based on lifetime estimations of the RF modules is compared against data from early operational experience. Sensitivity analyses have been made, that give insight to the chosen operational scenario. With the increasing use of solid-state RF power amplifiers, the findings of this study provide a useful reference for future application of this technology in particle accelerators.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB345
About •	paper received ※ 19 May 2021 paper accepted ※ 01 July 2021 issue date ※ 19 August 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Machine Learning Models for Breakdown Prediction in RF Cavities for Accelerators

1068

C. Obermair, A. Apollonio, T. Cartier-Michaud, N. Catalán Lasheras, L. Felsberger, W.L. Millar, W. Wuensch
CERN, Geneva, Switzerland
C. Obermair, F. Pernkopf
TUG, Graz, Austria

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.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-MOPAB344

About •

paper received ※ 20 May 2021 paper accepted ※ 16 July 2021 issue date ※ 11 August 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPAB345

Availability Modeling of the Solid-State Power Amplifiers for the CERN SPS RF Upgrade

2308

L. Felsberger, A. Apollonio, T. Cartier-Michaud, E. Montesinos, J.C. Oliveira, J.A. Uythoven
CERN, Geneva, Switzerland

Funding: This project has received funding from the Euratom research and training programme 2019-2020 under grant agreement No 945077.
As part of the LHC Injector Upgrade program a complete overhaul of the Super Proton Synchrotron Radio-Frequency (RF) system took place. New cavities have been installed for which the solid-state technology was chosen to deliver a combined RF power of 2 MW from 2560 RF amplifiers. This strategy promises high availability as the system continues operation when some of the amplifiers fail. This study quantifies the operational availability that can be achieved with this new installation. The evaluation is based on a Monte Carlo simulation of the system using the novel AvailSim4 simulation software. A model based on lifetime estimations of the RF modules is compared against data from early operational experience. Sensitivity analyses have been made, that give insight to the chosen operational scenario. With the increasing use of solid-state RF power amplifiers, the findings of this study provide a useful reference for future application of this technology in particle accelerators.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB345

About •

paper received ※ 19 May 2021 paper accepted ※ 01 July 2021 issue date ※ 19 August 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)