JACoW logo

Journals of Accelerator Conferences Website (JACoW)

JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.


BiBTeX citation export for THPOPA26: Machine Learning Assisted Cavity Quench Identification at the European XFEL

@inproceedings{branlard:linac2022-thpopa26,
  author       = {J. Branlard and A. Eichler and J.H.K. Timm and N. Walker},
  title        = {{Machine Learning Assisted Cavity Quench Identification at the European XFEL}},
  booktitle    = {Proc. LINAC'22},
% booktitle    = {Proc. 31st International Linear Accelerator Conference (LINAC'22)},
  pages        = {798--801},
  eid          = {THPOPA26},
  language     = {english},
  keywords     = {cavity, FEL, operation, software, hardware},
  venue        = {Liverpool, UK},
  series       = {International Linear Accelerator Conference},
  number       = {31},
  publisher    = {JACoW Publishing, Geneva, Switzerland},
  month        = {09},
  year         = {2022},
  issn         = {2226-0366},
  isbn         = {978-3-95450-215-8},
  doi          = {10.18429/JACoW-LINAC2022-THPOPA26},
  url          = {https://jacow.org/linac2022/papers/thpopa26.pdf},
  abstract     = {{A server-based quench detection system is used since the beginning of operation at the European XFEL (2017) to stop driving superconducting cavities if they experience a quench. While this approach effectively detects quenches, it also generates false positives, tripping the accelerating stations when failures other than quenches occur. Using the post-mortem data snapshots generated for every trip, an additional signal (referred to as residual) is systematically computed based on the standard cavity model. Following an initial training on a set of such residuals derived from quench as well as non-quench events, two independent machine learning engines analyze routinely the trip snapshots and their residuals to identify if a trip was indeed triggered by a quench or has another root cause. The outcome of the analysis is automatically appended to the data snapshots and distributed to a team of experts. This constitutes a fully deployed example of machine-learning-assisted failure classification to identify quenches, supporting experts in their daily routine of monitoring and documenting the accelerator uptime and availability.}},
}