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 WEPA29: Real-Time Cavity Fault Prediction in CEBAF Using Deep Learning

  author       = {M. Rahman and A. Carpenter and K.M. Iftekharuddin and T.S. McGuckin and C. Tennant and L.S. Vidyaratne},
  title        = {{Real-Time Cavity Fault Prediction in CEBAF Using Deep Learning}},
& booktitle    = {Proc. NAPAC'22},
  booktitle    = {Proc. 5th Int. Particle Accel. Conf. (NAPAC'22)},
  pages        = {687--690},
  eid          = {WEPA29},
  language     = {english},
  keywords     = {cavity, network, cryomodule, SRF, experiment},
  venue        = {Albuquerque, NM, USA},
  series       = {International Particle Accelerator Conference},
  number       = {5},
  publisher    = {JACoW Publishing, Geneva, Switzerland},
  month        = {10},
  year         = {2022},
  issn         = {2673-7000},
  isbn         = {978-3-95450-232-5},
  doi          = {10.18429/JACoW-NAPAC2022-WEPA29},
  url          = {https://jacow.org/napac2022/papers/wepa29.pdf},
  abstract     = {{Data-driven prediction of future faults is a major research area for many industrial applications. In this work, we present a new procedure of real-time fault prediction for superconducting radio-frequency (SRF) cavities at the Continuous Electron Beam Accelerator Facility (CEBAF) using deep learning. CEBAF has been afflicted by frequent downtime caused by SRF cavity faults. We perform fault prediction using pre-fault RF signals from C100-type cryomodules. Using the pre-fault signal information, the new algorithm predicts the type of cavity fault before the actual onset. The early prediction may enable potential mitigation strategies to prevent the fault. In our work, we apply a two-stage fault prediction pipeline. In the first stage, a model distinguishes between faulty and normal signals using a U-Net deep learning architecture. In the second stage of the network, signals flagged as faulty by the first model are classified into one of seven fault types based on learned signatures in the data. Initial results show that our model can successfully predict most fault types 200 ms before onset. We will discuss reasons for poor model performance on specific fault types.}},