Machine Learning for Time Series Prediction of an Accelerator Beam to Recognize Equipment Malfunction

Peters, Charles; Blokland, Willem; Brown, David; Liu, Frank; Long, Cary; Lu, Dan; Ramuhalli, Pradeep; Womble, David; Zhang, Jiaxin; Zhukov, Alexander

doi:10.18429/JACoW-IPAC2021-TUPAB328

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 TUPAB328: Machine Learning for Time Series Prediction of an Accelerator Beam to Recognize Equipment Malfunction

@inproceedings{peters:ipac2021-tupab328,
  author       = {C.C. Peters and W. Blokland and D.L. Brown and F. Liu and C.D. Long and D. Lu and P. Ramuhalli and D.E. Womble and J. Zhang and A.P. Zhukov},
% author       = {C.C. Peters and W. Blokland and D.L. Brown and F. Liu and C.D. Long and D. Lu and others},
% author       = {C.C. Peters and others},
  title        = {{Machine Learning for Time Series Prediction of an Accelerator Beam to Recognize Equipment Malfunction}},
  booktitle    = {Proc. IPAC'21},
  pages        = {2272--2275},
  eid          = {TUPAB328},
  language     = {english},
  keywords     = {cavity, SRF, linac, ion-source, neutron},
  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-TUPAB328},
  url          = {https://jacow.org/ipac2021/papers/tupab328.pdf},
  note         = {https://doi.org/10.18429/JACoW-IPAC2021-TUPAB328},
  abstract     = {{The Spallation Neutron Source (SNS) is an accelerator based pulsed neutron source based on a 1 GeV pulsed proton Superconducting Radio Frequency (SRF) linear accelerator (linac). Since beginning high power beam operation in 2006 correlations have been found linking abrupt beam loss events to SRF cavity instabilities. With the planned upgrades to double the beam power we expect increased rates of degradation and the importance of minimizing these beam loss events will become ever more important. To further limit degradation, we are developing machine learning approaches to monitor the beam and to detect, predict and prevent beam loss events. Initial research has shown that precursors to beam loss events are detectable. The initial steps are to use ML-based classification to recognize anomalies and to use Long Short-Term Memory (LSTM) autoencoders to predict beam loss. In this paper, we describe recent progress in applying machine learning for recognizing anomalies and predicting beam loss and present initial results of our research using acquired data from different diagnostics and the Machine Protection System (MPS).}},
}