Machine Learning Models for Breakdown Prediction in RF Cavities for Accelerators

Obermair, Christoph; Apollonio, Andrea; Cartier-Michaud, Thomas; Catalán Lasheras, Nuria; Felsberger, Lukas; Millar, William; Pernkopf, Franz; Wuensch, Walter

doi:10.18429/JACoW-IPAC2021-MOPAB344

Joint Accelerator Conferences Website

The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.

BiBTeX citation export for MOPAB344: Machine Learning Models for Breakdown Prediction in RF Cavities for Accelerators

@inproceedings{obermair:ipac2021-mopab344,
  author       = {C. Obermair and A. Apollonio and T. Cartier-Michaud and N. Catalán Lasheras and L. Felsberger and W.L. Millar and F. Pernkopf and W. Wuensch},
% author       = {C. Obermair and A. Apollonio and T. Cartier-Michaud and N. Catalán Lasheras and L. Felsberger and W.L. Millar and others},
% author       = {C. Obermair and others},
  title        = {{Machine Learning Models for Breakdown Prediction in RF Cavities for Accelerators}},
  booktitle    = {Proc. IPAC'21},
  pages        = {1068--1071},
  eid          = {MOPAB344},
  language     = {english},
  keywords     = {cavity, operation, network, vacuum, linac},
  venue        = {Campinas, SP, Brazil},
  series       = {International Particle Accelerator Conference},
  number       = {12},
  publisher    = {JACoW Publishing, Geneva, Switzerland},
  month        = {08},
  year         = {2021},
  issn         = {2673-5490},
  isbn         = {978-3-95450-214-1},
  doi          = {10.18429/JACoW-IPAC2021-MOPAB344},
  url          = {https://jacow.org/ipac2021/papers/mopab344.pdf},
  note         = {https://doi.org/10.18429/JACoW-IPAC2021-MOPAB344},
  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.}},
}