- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Accelerators and Beams

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Coincident learning for beam-based rf station fault identification using phase information at the SLAC linac coherent light source

Jia Liang1,*, William Colocho2, Franz-Josef Decker2, Ryan Humble3, Ben Morris2, Finn H. O’Shea2, David A. Steele2, Zhe Zhang2, Eric Darve1,‡ et al.

Daniel Ratner2,†

  • *Contact author: jialiang@slac.stanford.edu
  • †Contact author: dratner@slac.stanford.edu
  • ‡Also at Mechanical Engineering, Stanford University, Stanford, California 94305, USA.
PDF

Phys. Rev. Accel. Beams 28, 124601 – Published 3 December, 2025

DOI: https://doi.org/10.1103/zmmr-ry9h

Abstract

Anomalies in radio-frequency (rf) stations can result in unplanned downtime and performance degradation in linear accelerators such as SLAC’s Linac Coherent Light Source (LCLS). Detecting these anomalies is challenging due to the complexity of accelerator systems, high data volume, and scarcity of labeled fault data. Prior work identified faults using beam-based detection, combining rf amplitude and beam position monitor data. Due to the simplicity of the rf amplitude data, classical methods are sufficient to identify faults, but the recall is constrained by the low-frequency and asynchronous characteristics of the data. In this work, we leverage high-frequency, time-synchronous rf phase data to enhance anomaly detection in the LCLS accelerator. Due to the complexity of phase data, classical methods fail, and we instead train deep neural networks within the Coincident Anomaly Detection (CoAD) framework. We find that applying CoAD to phase data detects nearly 3 times as many anomalies as when applied to amplitude data, while achieving broader coverage across rf stations. Furthermore, the rich structure of phase data enables us to cluster anomalies into distinct physical categories. Through the integration of auxiliary system status bits, we link clusters to specific fault signatures, providing additional granularity for uncovering the root cause of faults. We also investigate interpretability via Shapley values, confirming that the learned models focus on the most informative regions of the data and providing insight for cases where the model makes mistakes. This work demonstrates that phase-based anomaly detection for rf stations improves both diagnostic coverage and root cause analysis in accelerator systems and that deep neural networks are essential for effective analysis.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (32)

  1. Ryan Humble, Finn H. O’Shea, William Colocho, Matt Gibbs, Helen Chaffee, Eric Darve, and Daniel Ratner, Beam-based rf station fault identification at the SLAC Linac Coherent Light Source, Phys. Rev. Accel. Beams 25, 122804 (2022).
  2. Ryan Humble, Zhe Zhang, Finn O’Shea, Eric Darve, and Daniel Ratner, Coincident learning for unsupervised anomaly detection of scientific instruments, Mach. Learn. 5, 035036 (2024).
  3. Zhiyuan Chen, Wei Lu, Radhika Bhong, Yimin Hu, Brian Freeman, and Adam Carpenter, Anomaly detection of particle orbit in accelerator using LSTM deep learning technology, arXiv:2401.15543.
  4. Chris Tennant, Brian Freeman, Reza Kazimi, Daniel Moser, Dan Abell, Jonathan Edelen, and Joshua Einstein-Curtis, A smart alarm for particle accelerator beamline operations, Mach. Learn. 4, 015021 (2023).
  5. Davide Marcato, Damiano Bortolato, Valentina Martinelli, Giovanni Savarese, and Gian Antonio Susto, Time-series deep learning anomaly detection for particle accelerators, IFAC-PapersOnLine 56, 1566 (2023).
  6. Willem Blokland, Kishansingh Rajput, Malachi Schram, Torri Jeske, Pradeep Ramuhalli, Charles Peters, Yigit Yucesan, and Alexander Zhukov, Uncertainty aware anomaly detection to predict errant beam pulses in the Oak Ridge Spallation Neutron Source accelerator, Phys. Rev. Accel. Beams 25, 122802 (2022).
  7. Ihar Lobach and Michael Borland, Long short-term memory networks for anomaly detection in magnet power supplies of particle accelerators, arXiv:2405.18321.
  8. Yusuke Suetsugu, Machine-learning-based pressure-anomaly detection system for SuperKEKB accelerator, Phys. Rev. Accel. Beams 27, 063201 (2024).
  9. Kishansingh Rajput, Malachi Schram, Willem Blokland, Yasir Alanazi, Pradeep Ramuhalli, Alexander Zhukov, Charles Peters, and Ricardo Vilalta, Robust errant beam prognostics with conditional modeling for particle accelerators, Mach. Learn. 5, 015044 (2024).
  10. Majdi I. Radaideh, Chris Pappas, Mark Wezensky, Pradeep Ramuhalli, and Sarah Cousineau, Early fault detection in particle accelerator power electronics using ensemble learning, Int. J. Prognostics Health Manage. 14 (2023).
  11. Md M. Rahman, Adam Carpenter, Khan Iftekharuddin, and Chris Tennant, Accelerating cavity fault prediction using deep learning at Jefferson Laboratory, Mach. Learn. 5, 035078 (2024).
  12. Zhou Jiqing, Li Deming, and Su Haijun, Particle accelerator power system early fault diagnosis based on deep learning and multi-sensor feature fusion, Eng. Res. Express 6, 025225 (2024).
  13. Zhe Yang, Rongbing Ye, Lingli Jiang, Jianyu Long, Yunwei Huang, and Chuan Li, Few-shot fault diagnosis of particle accelerator power system using a bidirectional discriminative prototype network, Appl. Soft Comput. 170, 112726 (2025).
  14. Yigit A. Yucesan, Willem Blokland, Pradeep Ramuhalli, Alexander Zhukov, Charles Peters, David Brown, and Cary Long, A machine learning approach for particle accelerator errant beam prediction using spatial phase deviation, Nucl. Instrum. Methods Phys. Res., Sect. A 1063, 169232 (2024).
  15. Jonathan P. Edelen and Nathan M. Cook, Anomaly detection in particle accelerators using autoencoders, arXiv:2112.07793.
  16. T. Straumann, R. Akre, R. G. Johnson, D. Kotturi, P. Krejcik, E. Medvedko, J. Olsen, and S. Smith, LCLS beam-position monitor data acquisition system, in Proceedings of the ICALEPCS07, Knoxville, TN (Joint Accelerator Conference Website, CERN, Geneva, Switzerland, 2007).
  17. Ryan Prescott Adams and David J. C. MacKay, Bayesian online changepoint detection, arXiv:0710.3742.
  18. Natalia Y. Bilenko and Jack L. Gallant, pyrcca: Regularized kernel canonical correlation analysis in python and its applications to neuroimaging, Front. Neuroinf. 10, 49 (2016).
  19. Eun Jeong Min, Eric C. Chi, and Hua Zhou, Tensor canonical correlation analysis, Stat 8, e253 (2019).
  20. Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou, Isolation forest, in Proceedings of the 2008 Eighth IEEE International Conference on Data Mining (IEEE, New York, NY, 2008), pp. 413–422.
  21. Larry M. Manevitz and Malik Yousef, One-class SVMS for document classification, J. Mach. Learn. Res. 2, 139 (2001), https://www.jmlr.org/papers/v2/manevitz01a.html.
  22. Cristian I. Challu, Peihong Jiang, Ying Nian Wu, and Laurent Callot, Deep generative model with hierarchical latent factors for time series anomaly detection, in Proceedings of the International Conference on Artificial Intelligence and Statistics (PMLR, Cambridge, MA, 2022), pp. 1643–1654.
  23. Ya Su, Youjian Zhao, Chenhao Niu, Rong Liu, Wei Sun, and Dan Pei, Robust anomaly detection for multivariate time series through stochastic recurrent neural network, in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Association for Computing Machinery, New York, NY, 2019), pp. 2828–2837.
  24. J. Liang et al., LCLS RF Station Phase Anomaly Candidate Dataset. SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States), 2025, 10.71929/2584368.
  25. Navid Hashemi, Eduardo Verdugo German, Jonatan Pena Ramirez, and Justin Ruths, Filtering approaches for dealing with noise in anomaly detection, in Proceedings of the 2019 IEEE 58th Conference on Decision and Control (CDC) (IEEE, New York, NY, 2019), pp. 5356–5361.
  26. Yue Zhao, Ryan A. Rossi, and Leman Akoglu, Automating outlier detection via meta-learning, arXiv:2009.10606.
  27. Willem van Veluw, Application of mixture models to threshold anomaly scores, Master’s thesis, Utrecht University, 2023.
  28. Leland McInnes, John Healy, and James Melville, UMAP: Uniform manifold approximation and projection for dimension reduction, arXiv:1802.03426.
  29. Leland McInnes, John Healy, and Steve Astels, hdbscan: Hierarchical density based clustering, J. Open Source Software 2, 205 (2017).
  30. D. Rogind, W. Allen, W. Colocho, G. DeContreras, J. Gordon, P. Pandey, and H. Shoaee, Integrated management tool for controls software problems, requests and project tasking at SLAC, in Proceedings of the ICALEPCS (Joint Accelerator Conference Website, CERN, Geneva, Switzerland, 2018).
  31. Scott M. Lundberg and Su-In Lee, A unified approach to interpreting model predictions, in Advances in Neural Information Processing Systems (Curran Associates Inc., Red Hook, NY, 2017), Vol. 30.
  32. Kishansingh Rajput, Sen Lin, Auralee Edelen, Willem Blokland, and Malachi Schram, Outlook towards deployable continual learning for particle accelerators, Mach. Learn. 6, 031001 (2025).

Outline

Information

Phys. Rev. Accel. Beams 28, 124601– Published 3 December, 2025
  • Received 19 May 2025
  • Accepted 30 October 2025
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation