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

Miha Reščič; Rebecca Seviour; Willem Blokland

doi:10.1016/j.nima.2021.166064

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 journal › Article › peer-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 language	English
Article number	166064
Journal	Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
Volume	1025
DOIs	https://doi.org/10.1016/j.nima.2021.166064
State	Published - Feb 11 2022
Externally published	Yes

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.

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

Keywords

Failure prediction
Machine learning
Particle accelerator
Reliability

Access to Document

10.1016/j.nima.2021.166064

Cite this

Reščič, M., Seviour, R., & Blokland, W. (2022). Improvements of pre-emptive identification of particle accelerator failures using binary classifiers and dimensionality reduction. Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 1025, Article 166064. https://doi.org/10.1016/j.nima.2021.166064

@article{ed7caf6f20474e918daefcf779d1390a,

title = "Improvements of pre-emptive identification of particle accelerator failures using binary classifiers and dimensionality reduction",

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.",

keywords = "Failure prediction, Machine learning, Particle accelerator, Reliability",

author = "Miha Re{\v s}{\v c}i{\v c} and Rebecca Seviour and Willem Blokland",

note = "Publisher Copyright: {\textcopyright} 2021 Elsevier B.V.",

year = "2022",

month = feb,

day = "11",

doi = "10.1016/j.nima.2021.166064",

language = "English",

volume = "1025",

journal = "Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment",

issn = "0168-9002",

publisher = "Elsevier",

}

Improvements of pre-emptive identification of particle accelerator failures using binary classifiers and dimensionality reduction. / Reščič, Miha; Seviour, Rebecca; Blokland, Willem.
In: Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 1025, 166064, 11.02.2022.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - Improvements of pre-emptive identification of particle accelerator failures using binary classifiers and dimensionality reduction

AU - Reščič, Miha

AU - Seviour, Rebecca

AU - Blokland, Willem

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 - Failure prediction

KW - Machine learning

KW - Particle accelerator

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

AN - SCOPUS:85121573772

SN - 0168-9002

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

M1 - 166064

ER -

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

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this