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 MOPA28: Semantic Regression for Disentangling Beam Losses in the Fermilab Main Injector and Recycler

@inproceedings{thieme:napac2022-mopa28,
  author       = {M. Thieme and J.M.S. Arnold and M.R. Austin and P.M. Hanlet and K.J. Hazelwood and M.A. Ibrahim and H. Liu and S. Memik and V.P. Nagaslaev and A. Narayanan and D.J. Nicklaus and G. Pradhan and A.L. Saewert and B.A. Schupbach and K. Seiya and R. Shi and R.M. Thurman-Keup and N.V. Tran},
% author       = {M. Thieme and J.M.S. Arnold and M.R. Austin and P.M. Hanlet and K.J. Hazelwood and M.A. Ibrahim and others},
% author       = {M. Thieme and others},
  title        = {{Semantic Regression for Disentangling Beam Losses in the Fermilab Main Injector and Recycler}},
& booktitle    = {Proc. NAPAC'22},
  booktitle    = {Proc. 5th Int. Particle Accel. Conf. (NAPAC'22)},
  pages        = {112--115},
  eid          = {MOPA28},
  language     = {english},
  keywords     = {operation, real-time, distributed, proton, beam-losses},
  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-MOPA28},
  url          = {https://jacow.org/napac2022/papers/mopa28.pdf},
  abstract     = {{Fermilab’s Main Injector enclosure houses two accelerators: the Main Injector (MI) and the Recycler (RR). In periods of joint operation, when both machines contain high intensity beam, radiative beam losses from MI and RR overlap on the enclosure’s beam loss monitoring (BLM) system, making it difficult to attribute those losses to a single machine. Incorrect diagnoses result in unnecessary downtime that incurs both financial and experimental cost. In this work, we introduce a novel neural approach for automatically disentangling each machine’s contributions to those measured losses. Using a continuous adaptation of the popular UNet architecture in conjunction with a novel data augmentation scheme, our model accurately infers the machine of origin on a per-BLM basis in periods of joint and independent operation. Crucially, by extracting beam loss information at varying receptive fields, the method is capable of learning both local and global machine signatures and producing high quality inferences using only raw BLM loss measurements.}},
}