Improvements of pre-emptive identification of particle accelerator failures using binary classifiers and dimensionality reduction

Miha Reščič, Rebecca Seviour, Willem Blokland

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

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.

Original languageEnglish
Article number166064
JournalNuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
Volume1025
DOIs
StatePublished - Feb 11 2022
Externally publishedYes

Funding

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.

FundersFunder number
U.S. Department of Energy
Office of Science
Oak Ridge National Laboratory

    Keywords

    • Failure prediction
    • Machine learning
    • Particle accelerator
    • Reliability

    Fingerprint

    Dive into the research topics of 'Improvements of pre-emptive identification of particle accelerator failures using binary classifiers and dimensionality reduction'. Together they form a unique fingerprint.

    Cite this