Uncertainty aware anomaly detection to predict errant beam pulses in the Oak Ridge Spallation Neutron Source accelerator

Willem Blokland; Kishansingh Rajput; Malachi Schram; Torri Jeske; Pradeep Ramuhalli; Charles Peters; Yigit Yucesan; Alexander Zhukov

doi:10.1103/PhysRevAccelBeams.25.122802

Uncertainty aware anomaly detection to predict errant beam pulses in the Oak Ridge Spallation Neutron Source accelerator

Willem Blokland, Kishansingh Rajput, Malachi Schram, Torri Jeske, Pradeep Ramuhalli, Charles Peters, Yigit Yucesan, Alexander Zhukov

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

10 Scopus citations

Abstract

High-power particle accelerators are complex machines with thousands of pieces of equipment that are frequently running at the cutting edge of technology. In order to improve the day-to-day operations and maximize the delivery of the science, new analytical techniques are being explored for anomaly detection, classification, and prognostications. As such, we describe the application of an uncertainty aware Machine Learning method using the Siamese neural network model to predict upcoming errant beam pulses using the data from a single monitoring device. By predicting the upcoming failure, we can stop the accelerator before damage occurs. We describe the accelerator operation, related Machine Learning research, the prediction performance required to abort the beam while maintaining operations, the monitoring device and its data, and the uncertainty aware Siamese method and its results. These results show that the researched method can be applied to improve accelerator operations.

Original language	English
Article number	122802
Journal	Physical Review Accelerators and Beams
Volume	25
Issue number	12
DOIs	https://doi.org/10.1103/PhysRevAccelBeams.25.122802
State	Published - Dec 2022

Funding

The authors acknowledge the help from David Brown in evaluating Operations requirements, Frank Liu, for his assistance on the ML techniques, and Sarah Cousineau for making this grant work possible. The authors are grateful for support from the Neutron Sciences Directorate at ORNL in the investigation of this work. This work was supported by the DOE Office of Science, United States under Grant No. DE-SC0009915 (Office of Basic Energy Sciences, Scientific User Facilities program). This research used resources at the Spallation Neutron Source, a DOE Office of Science User Facility operated by the Oak Ridge National Laboratory. This manuscript has been authored by UT-Battelle, LLC, under Contract No. DE-AC05-00OR22725 and the Jefferson Science Associates (JSA) under Contract No. DE-AC05-06OR2317 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan .

Funders	Funder number
Jefferson Science Associates	DE-AC05-06OR2317
U.S. Department of Energy
Office of Science	DE-SC0009915
Basic Energy Sciences	DE-AC05-00OR22725
Oak Ridge National Laboratory

Access to Document

10.1103/PhysRevAccelBeams.25.122802

Cite this

@article{467a9a42f334408787d635a08210b8a2,

title = "Uncertainty aware anomaly detection to predict errant beam pulses in the Oak Ridge Spallation Neutron Source accelerator",

abstract = "High-power particle accelerators are complex machines with thousands of pieces of equipment that are frequently running at the cutting edge of technology. In order to improve the day-to-day operations and maximize the delivery of the science, new analytical techniques are being explored for anomaly detection, classification, and prognostications. As such, we describe the application of an uncertainty aware Machine Learning method using the Siamese neural network model to predict upcoming errant beam pulses using the data from a single monitoring device. By predicting the upcoming failure, we can stop the accelerator before damage occurs. We describe the accelerator operation, related Machine Learning research, the prediction performance required to abort the beam while maintaining operations, the monitoring device and its data, and the uncertainty aware Siamese method and its results. These results show that the researched method can be applied to improve accelerator operations.",

author = "Willem Blokland and Kishansingh Rajput and Malachi Schram and Torri Jeske and Pradeep Ramuhalli and Charles Peters and Yigit Yucesan and Alexander Zhukov",

note = "Publisher Copyright: {\textcopyright} 2022 authors. Published by the American Physical Society. Published by the American Physical Society under the terms of the {"}https://creativecommons.org/licenses/by/4.0/{"}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.",

year = "2022",

month = dec,

doi = "10.1103/PhysRevAccelBeams.25.122802",

language = "English",

volume = "25",

journal = "Physical Review Accelerators and Beams",

issn = "2469-9888",

publisher = "American Physical Society",

number = "12",

}

TY - JOUR

T1 - Uncertainty aware anomaly detection to predict errant beam pulses in the Oak Ridge Spallation Neutron Source accelerator

AU - Blokland, Willem

AU - Rajput, Kishansingh

AU - Schram, Malachi

AU - Jeske, Torri

AU - Ramuhalli, Pradeep

AU - Peters, Charles

AU - Yucesan, Yigit

AU - Zhukov, Alexander

N1 - Publisher Copyright: © 2022 authors. Published by the American Physical Society. Published by the American Physical Society under the terms of the "https://creativecommons.org/licenses/by/4.0/"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.

PY - 2022/12

Y1 - 2022/12

N2 - High-power particle accelerators are complex machines with thousands of pieces of equipment that are frequently running at the cutting edge of technology. In order to improve the day-to-day operations and maximize the delivery of the science, new analytical techniques are being explored for anomaly detection, classification, and prognostications. As such, we describe the application of an uncertainty aware Machine Learning method using the Siamese neural network model to predict upcoming errant beam pulses using the data from a single monitoring device. By predicting the upcoming failure, we can stop the accelerator before damage occurs. We describe the accelerator operation, related Machine Learning research, the prediction performance required to abort the beam while maintaining operations, the monitoring device and its data, and the uncertainty aware Siamese method and its results. These results show that the researched method can be applied to improve accelerator operations.

AB - High-power particle accelerators are complex machines with thousands of pieces of equipment that are frequently running at the cutting edge of technology. In order to improve the day-to-day operations and maximize the delivery of the science, new analytical techniques are being explored for anomaly detection, classification, and prognostications. As such, we describe the application of an uncertainty aware Machine Learning method using the Siamese neural network model to predict upcoming errant beam pulses using the data from a single monitoring device. By predicting the upcoming failure, we can stop the accelerator before damage occurs. We describe the accelerator operation, related Machine Learning research, the prediction performance required to abort the beam while maintaining operations, the monitoring device and its data, and the uncertainty aware Siamese method and its results. These results show that the researched method can be applied to improve accelerator operations.

UR - http://www.scopus.com/inward/record.url?scp=85145456681&partnerID=8YFLogxK

U2 - 10.1103/PhysRevAccelBeams.25.122802

DO - 10.1103/PhysRevAccelBeams.25.122802

M3 - Article

AN - SCOPUS:85145456681

SN - 2469-9888

VL - 25

JO - Physical Review Accelerators and Beams

JF - Physical Review Accelerators and Beams

IS - 12

M1 - 122802

ER -

Uncertainty aware anomaly detection to predict errant beam pulses in the Oak Ridge Spallation Neutron Source accelerator

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this