IPAC2022 - List of Authors (Diaz Cruz, J.A.)

Paper	Title	Page
MOPOPT058	Machine Learning Training for HOM Reduction in a TESLA-Type Cryomodule at FAST	400
SUSPMF099	use link to see paper's listing under its alternate paper code
	J.A. Diaz Cruz UNM-ECE, Albuquerque, USA J.A. Diaz Cruz, A.L. Edelen, B.T. Jacobson, J.P. Sikora SLAC, Menlo Park, California, USA D.R. Edstrom, A.H. Lumpkin, R.M. Thurman-Keup Fermilab, Batavia, Illinois, USA
	Low emittance electron beams are of high importance at facilities like the Linac Coherent Light Source II (LCLS-II) at SLAC. Emittance dilution effects due to off-axis beam transport for a TESLA-type cryomodule (CM) have been shown at the Fermilab Accelerator Science and Technology (FAST) facility. The results showed the correlation between the electron beam-induced cavity high-order modes (HOMs) and the Beam Position Monitor (BPM) measurements downstream the CM. Mitigation of emittance dilution can be achieved by reducing the HOM signals. Here, we present a couple of Neural Networks (NN) for bunch-by-bunch mean prediction and standard deviation prediction for BPMs located downstream the CM.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-MOPOPT058
About •	Received ※ 15 June 2022 — Revised ※ 18 June 2022 — Accepted ※ 24 June 2022 — Issue date ※ 26 June 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPOST027	Machine Learning-Based Tuning of Control Parameters for LLRF System of Superconducting Cavities	915
	J.A. Diaz Cruz, S. Biedron UNM-ECE, Albuquerque, USA J.A. Diaz Cruz SLAC, Menlo Park, California, USA R. Pirayesh UNM-ME, Albuquerque, New Mexico, USA S. Sosa ODU, Norfolk, Virginia, USA
	The multiple systems involved in the operation of particle accelerators use diverse control systems to reach the desired operating point for the machine. Each system needs to tune several control parameters to achieve the required performance. Traditional Low-Level RF (LLRF) systems are implemented as proportional-integral feedback loops, whose gains need to be optimized. In this paper, we explore Machine Learning (ML) as a tool to improve a traditional LLRF controller by tuning its gains using a Neural Network (NN). We present the data production scheme and a control parameter optimization using a NN. The NN training is performed using the THETA supercomputer.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOST027
About •	Received ※ 14 June 2022 — Revised ※ 15 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 20 June 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

MOPOPT058

Machine Learning Training for HOM Reduction in a TESLA-Type Cryomodule at FAST

400

SUSPMF099

use link to see paper's listing under its alternate paper code

J.A. Diaz Cruz
UNM-ECE, Albuquerque, USA
J.A. Diaz Cruz, A.L. Edelen, B.T. Jacobson, J.P. Sikora
SLAC, Menlo Park, California, USA
D.R. Edstrom, A.H. Lumpkin, R.M. Thurman-Keup
Fermilab, Batavia, Illinois, USA

Low emittance electron beams are of high importance at facilities like the Linac Coherent Light Source II (LCLS-II) at SLAC. Emittance dilution effects due to off-axis beam transport for a TESLA-type cryomodule (CM) have been shown at the Fermilab Accelerator Science and Technology (FAST) facility. The results showed the correlation between the electron beam-induced cavity high-order modes (HOMs) and the Beam Position Monitor (BPM) measurements downstream the CM. Mitigation of emittance dilution can be achieved by reducing the HOM signals. Here, we present a couple of Neural Networks (NN) for bunch-by-bunch mean prediction and standard deviation prediction for BPMs located downstream the CM.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-MOPOPT058

About •

Received ※ 15 June 2022 — Revised ※ 18 June 2022 — Accepted ※ 24 June 2022 — Issue date ※ 26 June 2022

Cite •

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

TUPOST027

Machine Learning-Based Tuning of Control Parameters for LLRF System of Superconducting Cavities

915

J.A. Diaz Cruz, S. Biedron
UNM-ECE, Albuquerque, USA
J.A. Diaz Cruz
SLAC, Menlo Park, California, USA
R. Pirayesh
UNM-ME, Albuquerque, New Mexico, USA
S. Sosa
ODU, Norfolk, Virginia, USA

The multiple systems involved in the operation of particle accelerators use diverse control systems to reach the desired operating point for the machine. Each system needs to tune several control parameters to achieve the required performance. Traditional Low-Level RF (LLRF) systems are implemented as proportional-integral feedback loops, whose gains need to be optimized. In this paper, we explore Machine Learning (ML) as a tool to improve a traditional LLRF controller by tuning its gains using a Neural Network (NN). We present the data production scheme and a control parameter optimization using a NN. The NN training is performed using the THETA supercomputer.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOST027

About •

Received ※ 14 June 2022 — Revised ※ 15 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 20 June 2022

Cite •

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