IPAC2022 - List of Authors (Shen, M.)

Paper	Title	Page
TUPOMS054	Data Augmentation for Breakdown Prediction in CLIC RF Cavities	1553
	H.S. Bovbjerg, M. Shen, Z.H. Tan Aalborg University, Aalborg, Denmark A. Apollonio, H.S. Bovbjerg, T. Cartier-Michaud, W.L. Millar, C. Obermair, D. Wollmann CERN, Meyrin, Switzerland C. Obermair TUG, Graz, Austria
	One of the primary limitations on the achievable accelerating gradient in normal-conducting accelerator cavities is the occurrence of vacuum arcs, also known as RF breakdowns. A recent study on experimental data from the CLIC XBOX2 test stand at CERN proposes the use of supervised machine learning methods for predicting RF breakdowns. As RF breakdowns occur relatively infrequently during operation, the majority of the data was instead comprised of non-breakdown pulses. This phenomenon is known in the field of machine learning as class imbalance and is problematic for the training of the models. This paper proposes the use of data augmentation methods to generate synthetic data to counteract this problem. Different data augmentation methods like random transformations and pattern mixing are applied to the experimental data from the XBOX2 test stand, and their efficiency is compared.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOMS054
About •	Received ※ 08 June 2022 — Revised ※ 12 June 2022 — Accepted ※ 13 June 2022 — Issue date ※ 15 June 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Data Augmentation for Breakdown Prediction in CLIC RF Cavities

1553

H.S. Bovbjerg, M. Shen, Z.H. Tan
Aalborg University, Aalborg, Denmark
A. Apollonio, H.S. Bovbjerg, T. Cartier-Michaud, W.L. Millar, C. Obermair, D. Wollmann
CERN, Meyrin, Switzerland
C. Obermair
TUG, Graz, Austria

One of the primary limitations on the achievable accelerating gradient in normal-conducting accelerator cavities is the occurrence of vacuum arcs, also known as RF breakdowns. A recent study on experimental data from the CLIC XBOX2 test stand at CERN proposes the use of supervised machine learning methods for predicting RF breakdowns. As RF breakdowns occur relatively infrequently during operation, the majority of the data was instead comprised of non-breakdown pulses. This phenomenon is known in the field of machine learning as class imbalance and is problematic for the training of the models. This paper proposes the use of data augmentation methods to generate synthetic data to counteract this problem. Different data augmentation methods like random transformations and pattern mixing are applied to the experimental data from the XBOX2 test stand, and their efficiency is compared.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOMS054

About •

Received ※ 08 June 2022 — Revised ※ 12 June 2022 — Accepted ※ 13 June 2022 — Issue date ※ 15 June 2022

Cite •

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