IPAC2021 - List of Authors (Millar, W.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)

TUPAB076	High-Gradient Breakdown Studies of an X-Band Accelerating Structure Operated in the Reversed Taper Direction	1543
	X.W. Wu, N. Catalán Lasheras, A. Grudiev, G. McMonagle, I. Syratchev, W. Wuensch CERN, Meyrin, Switzerland M. Boronat IFIC, Valencia, Spain A. Castilla, A.V. Edwards, W.L. Millar Lancaster University, Lancaster, United Kingdom
	The results of high-gradient tests of a tapered X-band traveling-wave accelerator structure powered in reversed direction are presented. Powering the tapered structure from the small aperture, normally output, at the end of the structure provides unique conditions for the study of gradient limits. This allows high fields in the first cell for a comparatively low input power and a field distribution that rapidly falls off along the length of the structure. A maximum gradient of 130 MV/m in the first cell at a pulse length of 100 ns was reached for an input power of 31.9 MW. Details of the conditioning and operation at high-gradient are presented. Various breakdown rate measurements were conducted at different power levels and rf pulse widths. The structure was standard T24 CLIC test structure and was tested in Xbox-3 at CERN.
	Poster TUPAB076 [1.077 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB076
About •	paper received ※ 19 May 2021 paper accepted ※ 12 July 2021 issue date ※ 12 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)

TUPAB076

High-Gradient Breakdown Studies of an X-Band Accelerating Structure Operated in the Reversed Taper Direction

1543

X.W. Wu, N. Catalán Lasheras, A. Grudiev, G. McMonagle, I. Syratchev, W. Wuensch
CERN, Meyrin, Switzerland
M. Boronat
IFIC, Valencia, Spain
A. Castilla, A.V. Edwards, W.L. Millar
Lancaster University, Lancaster, United Kingdom

The results of high-gradient tests of a tapered X-band traveling-wave accelerator structure powered in reversed direction are presented. Powering the tapered structure from the small aperture, normally output, at the end of the structure provides unique conditions for the study of gradient limits. This allows high fields in the first cell for a comparatively low input power and a field distribution that rapidly falls off along the length of the structure. A maximum gradient of 130 MV/m in the first cell at a pulse length of 100 ns was reached for an input power of 31.9 MW. Details of the conditioning and operation at high-gradient are presented. Various breakdown rate measurements were conducted at different power levels and rf pulse widths. The structure was standard T24 CLIC test structure and was tested in Xbox-3 at CERN.

Poster TUPAB076 [1.077 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB076

About •

paper received ※ 19 May 2021 paper accepted ※ 12 July 2021 issue date ※ 12 August 2021

Export •

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