Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Robust errant beam prognostics with conditional modeling for particle accelerators

Journal Article · · Machine Learning: Science and Technology
ORCiD logo [1]; ORCiD logo [2];  [3];  [2];  [3];  [3];  [3];  [4]
  1. Thomas Jefferson National Accelerator Facility (TJNAF), Newport News, VA (United States); University of Houston, TX (United States)
  2. Thomas Jefferson National Accelerator Facility (TJNAF), Newport News, VA (United States)
  3. Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
  4. University of Houston, TX (United States)
+ Show Author Affiliations

Particle accelerators are complex and comprise thousands of components, with many pieces of equipment running at their peak power. Consequently, they can fault and abort operations for numerous reasons, lowering efficiency and science output. To avoid these faults, we apply anomaly detection techniques to predict unusual behavior and perform preemptive actions to improve the total availability. Supervised machine learning (ML) techniques such as siamese neural network models can outperform the often-used unsupervised or semi-supervised approaches for anomaly detection by leveraging the label information. One of the challenges specific to anomaly detection for particle accelerators is the data's variability due to accelerator configuration changes within a production run of several months. ML models fail at providing accurate predictions when data changes due to changes in the configuration. To address this challenge, we include the configuration settings into our models and training to improve the results. Beam configurations are used as a conditional input for the model to learn any cross-correlation between the data from different conditions and retain its performance. We employ conditional siamese neural network (CSNN) models and conditional variational auto encoder (CVAE) models to predict errant beam pulses at the spallation neutron source under different system configurations and compare their performance. We demonstrate that CSNNs outperform CVAEs in our application.

Research Organization:
Thomas Jefferson National Accelerator Facility (TJNAF), Newport News, VA (United States); Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE
Grant/Contract Number:
SC0009915; AC05-00OR22725; AC05-06OR23177
OSTI ID:
2320294
Alternate ID(s):
OSTI ID: 2315723; OSTI ID: 2370343
Report Number(s):
JLAB-CST-23-3999; DOE/OR/23177-7512; DE-SC0009915; DE-AC05-00OR22725; TRN: US2500218
Journal Information:
Machine Learning: Science and Technology, Vol. 5, Issue 1; ISSN 2632-2153
Publisher:
IOP PublishingCopyright Statement
Country of Publication:
United States
Language:
English

References (29)

Extremum Seeking-Based Control System for Particle Accelerator Beam Loss Minimization journal September 2022
Uncertainty aware anomaly detection to predict errant beam pulses in the Oak Ridge Spallation Neutron Source accelerator journal December 2022
Uncertainty aware machine-learning-based surrogate models for particle accelerators: Study at the Fermilab Booster Accelerator Complex journal April 2023
Using LSTM recurrent neural networks for monitoring the LHC superconducting magnets
  • Wielgosz, Maciej; Skoczeń, Andrzej; Mertik, Matej
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 867 https://doi.org/10.1016/j.nima.2017.06.020
journal September 2017
Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning journal June 2017
Time series anomaly detection in power electronics signals with recurrent and ConvLSTM autoencoders journal October 2022
Minimizing Errant Beam at the Spallation Neutron Source text January 2018
A Branch and Bound Algorithm for Computing k-Nearest Neighbors journal July 1975
Developing Robust Digital Twins and Reinforcement Learning for Accelerator Control Systems at the Fermilab Booster
  • Kafkes, Diana; Herwig, C.; Pellico, William
  • Developing Robust Digital Twins and Reinforcement Learning for Accelerator Control Systems at the Fermilab Booster https://doi.org/10.2172/1825276
conference January 2021
Overview of ten-year operation of the superconducting linear accelerator at the Spallation Neutron Source
  • Kim, S. -H.; Afanador, R.; Barnhart, D. L.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 852 https://doi.org/10.1016/j.nima.2017.02.009
journal April 2017
Developments in MLflow conference June 2020
A fuzzy K-nearest neighbor algorithm journal July 1985
The Spallation Neutron Source accelerator system design
  • Henderson, S.; Abraham, W.; Aleksandrov, A.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 763 https://doi.org/10.1016/j.nima.2014.03.067
journal November 2014
On Nonintrusive Uncertainty Quantification and Surrogate Model Construction in Particle Accelerator Modeling journal January 2019
Improvements of pre-emptive identification of particle accelerator failures using binary classifiers and dimensionality reduction
  • Reščič, Miha; Seviour, Rebecca; Blokland, Willem
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 1025 https://doi.org/10.1016/j.nima.2021.166064
journal February 2022
On Information and Sufficiency journal March 1951
Demonstration of Model-Independent Control of the Longitudinal Phase Space of Electron Beams in the Linac-Coherent Light Source with Femtosecond Resolution journal July 2018
Fast anomaly detection using Boxplot rule for multivariate data in cooperative wideband cognitive radio in the presence of jammer journal March 2014
Adaptive method for electron bunch profile prediction journal October 2015
Multi-module-based CVAE to predict HVCM faults in the SNS accelerator journal September 2023
Tuning particle accelerators with safety constraints using Bayesian optimization journal June 2022
Variational Inference: A Review for Statisticians journal July 2016
Neural Networks for Modeling and Control of Particle Accelerators journal April 2016
Superconducting radio-frequency cavity fault classification using machine learning at Jefferson Laboratory journal November 2020
Uncertainty quantification for deep learning in particle accelerator applications journal November 2021
Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives journal January 2024
A Novel Approach for Classification and Forecasting of Time Series in Particle Accelerators journal March 2021
Machine learning-based longitudinal phase space prediction of particle accelerators journal November 2018
Predicting particle accelerator failures using binary classifiers
  • Rescic, Miha; Seviour, Rebecca; Blokland, Willem
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 955 https://doi.org/10.1016/j.nima.2019.163240
journal March 2020

Similar Records

Related Subjects

43 PARTICLE ACCELERATORS
anomaly prediction
siamese model
variational autoencoder
conditional
SNS
spallational neutron source
particle accelerators