Final published version
Licence: CC BY: Creative Commons Attribution 4.0 International License
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Explainable machine learning for breakdown prediction in high gradient rf cavities
AU - Obermair, Christoph
AU - Cartier-Michaud, Thomas
AU - Apollonio, Andrea
AU - Millar, William
AU - Felsberger, Lukas
AU - Fischl, Lorenz
AU - Bovbjerg, Holger Severin
AU - Wollmann, Daniel
AU - Wuensch, Walter
AU - Catalan-Lasheras, Nuria
AU - Boronat, Marçà
AU - Pernkopf, Franz
AU - Burt, Graeme
PY - 2022/10/4
Y1 - 2022/10/4
N2 - The occurrence of vacuum arcs or radio frequency (rf) breakdowns is one of the most prevalent factors limiting the high-gradient performance of normal conducting rf cavities in particle accelerators. In this paper, we search for the existence of previously unrecognized features related to the incidence of rf breakdowns by applying a machine learning strategy to high-gradient cavity data from CERN’s test stand for the Compact Linear Collider (CLIC). By interpreting the parameters of the learned models with explainable artificial intelligence (AI), we reverse-engineer physical properties for deriving fast, reliable, and simple rule–based models. Based on 6 months of historical data and dedicated experiments, our models show fractions of data with a high influence on the occurrence of breakdowns. Specifically, it is shown that the field emitted current following an initial breakdown is closely related to the probability of another breakdown occurring shortly thereafter. Results also indicate that the cavity pressure should be monitored with increased temporal resolution in future experiments, to further explore the vacuum activity associated with breakdowns.
AB - The occurrence of vacuum arcs or radio frequency (rf) breakdowns is one of the most prevalent factors limiting the high-gradient performance of normal conducting rf cavities in particle accelerators. In this paper, we search for the existence of previously unrecognized features related to the incidence of rf breakdowns by applying a machine learning strategy to high-gradient cavity data from CERN’s test stand for the Compact Linear Collider (CLIC). By interpreting the parameters of the learned models with explainable artificial intelligence (AI), we reverse-engineer physical properties for deriving fast, reliable, and simple rule–based models. Based on 6 months of historical data and dedicated experiments, our models show fractions of data with a high influence on the occurrence of breakdowns. Specifically, it is shown that the field emitted current following an initial breakdown is closely related to the probability of another breakdown occurring shortly thereafter. Results also indicate that the cavity pressure should be monitored with increased temporal resolution in future experiments, to further explore the vacuum activity associated with breakdowns.
KW - Surfaces and Interfaces
KW - Physics and Astronomy (miscellaneous)
KW - Nuclear and High Energy Physics
U2 - 10.1103/physrevaccelbeams.25.104601
DO - 10.1103/physrevaccelbeams.25.104601
M3 - Journal article
VL - 25
JO - Physical Review Accelerators and Beams
JF - Physical Review Accelerators and Beams
SN - 2469-9888
IS - 10
M1 - 104601
ER -