ICALEPCS2023 - List of Authors (Austin, M.R.)

Paper	Title	Page
TU1BCO06	Disentangling Beam Losses in The Fermilab Main Injector Enclosure Using Real-Time Edge AI	273
	K.J. Hazelwood, J.M.S. Arnold, M.R. Austin, J.R. Berlioz, P.M. Hanlet, M.A. Ibrahim, A.T. Livaudais-Lewis, J. Mitrevski, V.P. Nagaslaev, A. Narayanan, D.J. Nicklaus, G. Pradhan, A.L. Saewert, B.A. Schupbach, K. Seiya, R.M. Thurman-Keup, N.V. Tran Fermilab, Batavia, Illinois, USA J.YC. Hu, J. Jiang, H. Liu, S. Memik, R. Shi, A.M. Shuping, M. Thieme, C. Xu Northwestern University, Evanston, Illinois, USA A. Narayanan Northern Illinois University, DeKalb, Illinois, USA
	The Fermilab Main Injector enclosure houses two accelerators, the Main Injector and Recycler Ring. During normal operation, high intensity proton beams exist simultaneously in both. The two accelerators share the same beam loss monitors (BLM) and monitoring system. Deciphering the origin of any of the 260 BLM readings is often difficult. The (Accelerator) Real-time Edge AI for Distributed Systems project, or READS, has developed an AI/ML model, and implemented it on fast FPGA hardware, that disentangles mixed beam losses and attributes probabilities to each BLM as to which machine(s) the loss originated from in real-time. The model inferences are then streamed to the Fermilab accelerator controls network (ACNET) where they are available for operators and experts alike to aid in tuning the machines.
DOI •	reference for this paper ※ doi:10.18429/JACoW-ICALEPCS2023-TU1BCO06
About •	Received ※ 06 October 2023 — Revised ※ 11 October 2023 — Accepted ※ 15 November 2023 — Issued ※ 06 December 2023
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPDP111	Software and Firmware-Logic Design for the PIP-II Machine Protection System Mode and Configuration Control at Fermilab	832
	L.R. Carmichael, M.R. Austin, E.R. Harms, R. Neswold, A. Prosser, A. Warner, J.Y. Wu Fermilab, Batavia, Illinois, USA
	Funding: This manuscript has been authored by Fermi Research Alliance, LLC under Contract No. DE-AC02-07CH11359 with the U.S. Department of Energy, Office of Science, Office of High Energy Physics The PIP-II Machine Protection System (MPS) requires a dedicated set of tools for configuration control and management of the machine modes and beam modes of the accelerator. The protection system reacts to signals from various elements of the machine according to rules established in a setup database filtered by the program Mode Controller. This is achieved in accordance with commands from the operator and governed by the firmware logic of the MPS. This paper describes the firmware logic, architecture, and implementation of the program mode controller in an EPICs based environment.
	Poster TUPDP111 [2.313 MB]
DOI •	reference for this paper ※ doi:10.18429/JACoW-ICALEPCS2023-TUPDP111
About •	Received ※ 03 October 2023 — Revised ※ 09 October 2023 — Accepted ※ 04 December 2023 — Issued ※ 12 December 2023
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Disentangling Beam Losses in The Fermilab Main Injector Enclosure Using Real-Time Edge AI

273

K.J. Hazelwood, J.M.S. Arnold, M.R. Austin, J.R. Berlioz, P.M. Hanlet, M.A. Ibrahim, A.T. Livaudais-Lewis, J. Mitrevski, V.P. Nagaslaev, A. Narayanan, D.J. Nicklaus, G. Pradhan, A.L. Saewert, B.A. Schupbach, K. Seiya, R.M. Thurman-Keup, N.V. Tran
Fermilab, Batavia, Illinois, USA
J.YC. Hu, J. Jiang, H. Liu, S. Memik, R. Shi, A.M. Shuping, M. Thieme, C. Xu
Northwestern University, Evanston, Illinois, USA
A. Narayanan
Northern Illinois University, DeKalb, Illinois, USA

The Fermilab Main Injector enclosure houses two accelerators, the Main Injector and Recycler Ring. During normal operation, high intensity proton beams exist simultaneously in both. The two accelerators share the same beam loss monitors (BLM) and monitoring system. Deciphering the origin of any of the 260 BLM readings is often difficult. The (Accelerator) Real-time Edge AI for Distributed Systems project, or READS, has developed an AI/ML model, and implemented it on fast FPGA hardware, that disentangles mixed beam losses and attributes probabilities to each BLM as to which machine(s) the loss originated from in real-time. The model inferences are then streamed to the Fermilab accelerator controls network (ACNET) where they are available for operators and experts alike to aid in tuning the machines.

DOI •

reference for this paper ※ doi:10.18429/JACoW-ICALEPCS2023-TU1BCO06

About •

Received ※ 06 October 2023 — Revised ※ 11 October 2023 — Accepted ※ 15 November 2023 — Issued ※ 06 December 2023

Cite •

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

TUPDP111

Software and Firmware-Logic Design for the PIP-II Machine Protection System Mode and Configuration Control at Fermilab

832

L.R. Carmichael, M.R. Austin, E.R. Harms, R. Neswold, A. Prosser, A. Warner, J.Y. Wu
Fermilab, Batavia, Illinois, USA

Funding: This manuscript has been authored by Fermi Research Alliance, LLC under Contract No. DE-AC02-07CH11359 with the U.S. Department of Energy, Office of Science, Office of High Energy Physics
The PIP-II Machine Protection System (MPS) requires a dedicated set of tools for configuration control and management of the machine modes and beam modes of the accelerator. The protection system reacts to signals from various elements of the machine according to rules established in a setup database filtered by the program Mode Controller. This is achieved in accordance with commands from the operator and governed by the firmware logic of the MPS. This paper describes the firmware logic, architecture, and implementation of the program mode controller in an EPICs based environment.

Poster TUPDP111 [2.313 MB]

DOI •

reference for this paper ※ doi:10.18429/JACoW-ICALEPCS2023-TUPDP111

About •

Received ※ 03 October 2023 — Revised ※ 09 October 2023 — Accepted ※ 04 December 2023 — Issued ※ 12 December 2023

Cite •

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