TY - JOUR
T1 - Improvements of pre-emptive identification of particle accelerator failures using binary classifiers and dimensionality reduction
AU - Rescic, Miha
AU - Seviour, Rebecca
AU - Blokland, W.
N1 - Funding Information:
This research has been partially funded under contract DE-AC05-00OR22725 with the US Department of Energy (DOE) and used resources at the Spallation Neutron Source, a DOE Office of Science User Facility operated by the Oak Ridge National Laboratory.
Publisher Copyright:
© 2021 Elsevier B.V.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2022/2/11
Y1 - 2022/2/11
N2 - In this paper we look at the properties of the Spallation Neutron Source (SNS) Differential Beam Current Monitor (DCM) data and various methods of data transformation to improve pre-emptive detection of machine trips. Foundation of the approach is the analysis of new underlying data and understanding various properties with the goal of faster classification, higher precision and higher recall with the aim to reduce false positives as low as required. The result of the research presented in this paper are a binary classifier capable of predicting accelerator failures with millisecond classification time, 96% precision, 58% true positive and 0% false positive rate and optimization techniques enabling real-time implementations.
AB - In this paper we look at the properties of the Spallation Neutron Source (SNS) Differential Beam Current Monitor (DCM) data and various methods of data transformation to improve pre-emptive detection of machine trips. Foundation of the approach is the analysis of new underlying data and understanding various properties with the goal of faster classification, higher precision and higher recall with the aim to reduce false positives as low as required. The result of the research presented in this paper are a binary classifier capable of predicting accelerator failures with millisecond classification time, 96% precision, 58% true positive and 0% false positive rate and optimization techniques enabling real-time implementations.
KW - Machine learning
KW - Particle accelerator
KW - Failure prediction
KW - Reliability
UR - http://www.scopus.com/inward/record.url?scp=85121573772&partnerID=8YFLogxK
U2 - 10.1016/j.nima.2021.166064
DO - 10.1016/j.nima.2021.166064
M3 - Article
VL - 1025
JO - Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
JF - Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
SN - 0168-9002
M1 - 166064
ER -
