NAPAC2022 - List of Authors (Diaw, A.)

Paper	Title	Page
MOPA55	Facilitating Machine Learning Collaborations Between Labs, Universities, and Industry	164
	J.P. Edelen, D.T. Abell, D.L. Bruhwiler, S.J. Coleman, N.M. Cook, A. Diaw, J.A. Einstein-Curtis, C.C. Hall, M.C. Kilpatrick, B. Nash, I.V. Pogorelov RadiaSoft LLC, Boulder, Colorado, USA K.A. Brown BNL, Upton, New York, USA S. Calder ORNL RAD, Oak Ridge, Tennessee, USA A.L. Edelen, B.D. O’Shea, R.J. Roussel SLAC, Menlo Park, California, USA C.M. Hoffmann ORNL, Oak Ridge, Tennessee, USA E.-C. Huang LANL, Los Alamos, New Mexico, USA P. Piot Northern Illinois University, DeKalb, Illinois, USA C. Tennant JLab, Newport News, Virginia, USA
	It is clear from numerous recent community reports, papers, and proposals that machine learning is of tremendous interest for particle accelerator applications. The quickly evolving landscape continues to grow in both the breadth and depth of applications including physics modeling, anomaly detection, controls, diagnostics, and analysis. Consequently, laboratories, universities, and companies across the globe have established dedicated machine learning (ML) and data-science efforts aiming to make use of these new state-of-the-art tools. The current funding environment in the U.S. is structured in a way that supports specific application spaces rather than larger collaboration on community software. Here, we discuss the existing collaboration bottlenecks and how a shift in the funding environment, and how we develop collaborative tools, can help fuel the next wave of ML advancements for particle accelerators.
DOI •	reference for this paper ※ doi:10.18429/JACoW-NAPAC2022-MOPA55
About •	Received ※ 10 August 2022 — Revised ※ 11 August 2022 — Accepted ※ 22 August 2022 — Issue date ※ 01 September 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPA29	Machine Learning for Predicting Power Supply Trips in Storage Rings	413
	I. Lobach, M. Borland, G.I. Fystro, A. Sannibale, Y. Sun ANL, Lemont, Illinois, USA A. Diaw, J.P. Edelen RadiaSoft LLC, Boulder, Colorado, USA
	Funding: The work is supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357. In the Advanced Photon Source (APS) storage ring at Argonne National Lab, trips in the magnet power supplies (PSs) lead to a complete electron beam loss a few times a year. This results in unexpected interruptions of the users’ experiments. In this contribution, we investigate the historical data for the last two decades to find precursors for the PS trips that could provide an advance notice for future trips and allow some preventive action by the ring operator or by the PS maintenance team. Various unsupervised anomaly detection models can be trained on the vast amounts of available reference data from the beamtime periods that ended with an intentional beam dump. We find that such models can sometimes detect trip precursors in PS currents, voltages, and in the temperatures of magnets, capacitors and transistors (components of PSs).
	Poster TUPA29 [2.116 MB]
DOI •	reference for this paper ※ doi:10.18429/JACoW-NAPAC2022-TUPA29
About •	Received ※ 03 August 2022 — Revised ※ 07 August 2022 — Accepted ※ 10 August 2022 — Issue date ※ 18 August 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THZE4	Experimental Characterization of Gas Sheet Transverse Profile Diagnostic	907
	N. Burger, G. Andonian, D.I. Gavryushkin, T.J. Hodgetts, A.-L.M.S. Lamure, M. Ruelas RadiaBeam, Santa Monica, California, USA N.M. Cook, A. Diaw RadiaSoft LLC, Boulder, Colorado, USA P.E. Denham, P. Musumeci, A. Ody UCLA, Los Angeles, USA N.P. Norvell UCSC, Santa Cruz, California, USA C.P. Welsch, M. Yadav The University of Liverpool, Liverpool, United Kingdom C.P. Welsch Cockcroft Institute, Warrington, Cheshire, United Kingdom
	Transverse profile diagnostics for high-intensity beams require solutions that are non-intercepting and single-shot. In this paper, we describe a gas-sheet ionization diagnostic that employs a precision-shaped, neutral gas jet. As the high-intensity beam passes through the gas sheet, neutral particles are ionized. The ionization products are transported and imaged on a detector. A neural-network based reconstruction algorithm, trained on simulation data, then outputs the initial transverse conditions of the beam prior to ionization. The diagnostic is also adaptable to image the photons from recombination. Preliminary tests at low energy are presented to characterize the working principle of the instrument, including comparisons to existing diagnostics. The results are parametrized as a function of beam charge, spot size, and bunch length.
	Slides THZE4 [2.051 MB]
DOI •	reference for this paper ※ doi:10.18429/JACoW-NAPAC2022-THZE4
About •	Received ※ 02 August 2022 — Revised ※ 09 August 2022 — Accepted ※ 10 August 2022 — Issue date ※ 09 October 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Facilitating Machine Learning Collaborations Between Labs, Universities, and Industry

164

J.P. Edelen, D.T. Abell, D.L. Bruhwiler, S.J. Coleman, N.M. Cook, A. Diaw, J.A. Einstein-Curtis, C.C. Hall, M.C. Kilpatrick, B. Nash, I.V. Pogorelov
RadiaSoft LLC, Boulder, Colorado, USA
K.A. Brown
BNL, Upton, New York, USA
S. Calder
ORNL RAD, Oak Ridge, Tennessee, USA
A.L. Edelen, B.D. O’Shea, R.J. Roussel
SLAC, Menlo Park, California, USA
C.M. Hoffmann
ORNL, Oak Ridge, Tennessee, USA
E.-C. Huang
LANL, Los Alamos, New Mexico, USA
P. Piot
Northern Illinois University, DeKalb, Illinois, USA
C. Tennant
JLab, Newport News, Virginia, USA

It is clear from numerous recent community reports, papers, and proposals that machine learning is of tremendous interest for particle accelerator applications. The quickly evolving landscape continues to grow in both the breadth and depth of applications including physics modeling, anomaly detection, controls, diagnostics, and analysis. Consequently, laboratories, universities, and companies across the globe have established dedicated machine learning (ML) and data-science efforts aiming to make use of these new state-of-the-art tools. The current funding environment in the U.S. is structured in a way that supports specific application spaces rather than larger collaboration on community software. Here, we discuss the existing collaboration bottlenecks and how a shift in the funding environment, and how we develop collaborative tools, can help fuel the next wave of ML advancements for particle accelerators.

DOI •

reference for this paper ※ doi:10.18429/JACoW-NAPAC2022-MOPA55

About •

Received ※ 10 August 2022 — Revised ※ 11 August 2022 — Accepted ※ 22 August 2022 — Issue date ※ 01 September 2022

Cite •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPA29

Machine Learning for Predicting Power Supply Trips in Storage Rings

413

I. Lobach, M. Borland, G.I. Fystro, A. Sannibale, Y. Sun
ANL, Lemont, Illinois, USA
A. Diaw, J.P. Edelen
RadiaSoft LLC, Boulder, Colorado, USA

Funding: The work is supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357.
In the Advanced Photon Source (APS) storage ring at Argonne National Lab, trips in the magnet power supplies (PSs) lead to a complete electron beam loss a few times a year. This results in unexpected interruptions of the users’ experiments. In this contribution, we investigate the historical data for the last two decades to find precursors for the PS trips that could provide an advance notice for future trips and allow some preventive action by the ring operator or by the PS maintenance team. Various unsupervised anomaly detection models can be trained on the vast amounts of available reference data from the beamtime periods that ended with an intentional beam dump. We find that such models can sometimes detect trip precursors in PS currents, voltages, and in the temperatures of magnets, capacitors and transistors (components of PSs).

Poster TUPA29 [2.116 MB]

DOI •

reference for this paper ※ doi:10.18429/JACoW-NAPAC2022-TUPA29

About •

Received ※ 03 August 2022 — Revised ※ 07 August 2022 — Accepted ※ 10 August 2022 — Issue date ※ 18 August 2022

Cite •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THZE4

Experimental Characterization of Gas Sheet Transverse Profile Diagnostic

907

N. Burger, G. Andonian, D.I. Gavryushkin, T.J. Hodgetts, A.-L.M.S. Lamure, M. Ruelas
RadiaBeam, Santa Monica, California, USA
N.M. Cook, A. Diaw
RadiaSoft LLC, Boulder, Colorado, USA
P.E. Denham, P. Musumeci, A. Ody
UCLA, Los Angeles, USA
N.P. Norvell
UCSC, Santa Cruz, California, USA
C.P. Welsch, M. Yadav
The University of Liverpool, Liverpool, United Kingdom
C.P. Welsch
Cockcroft Institute, Warrington, Cheshire, United Kingdom

Transverse profile diagnostics for high-intensity beams require solutions that are non-intercepting and single-shot. In this paper, we describe a gas-sheet ionization diagnostic that employs a precision-shaped, neutral gas jet. As the high-intensity beam passes through the gas sheet, neutral particles are ionized. The ionization products are transported and imaged on a detector. A neural-network based reconstruction algorithm, trained on simulation data, then outputs the initial transverse conditions of the beam prior to ionization. The diagnostic is also adaptable to image the photons from recombination. Preliminary tests at low energy are presented to characterize the working principle of the instrument, including comparisons to existing diagnostics. The results are parametrized as a function of beam charge, spot size, and bunch length.

Slides THZE4 [2.051 MB]

DOI •

reference for this paper ※ doi:10.18429/JACoW-NAPAC2022-THZE4

About •

Received ※ 02 August 2022 — Revised ※ 09 August 2022 — Accepted ※ 10 August 2022 — Issue date ※ 09 October 2022

Cite •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)