LINAC2022 - List of Keywords (network)

Paper	Title	Other Keywords	Page
MOPOGE07	High Power RF Transmission Lines of the Light Proton Therapy Linac	cavity, linac, proton, controls	158
	J.L. Navarro Quirante, D. Aguilera Murciano, S. Benedetti, G. Castorina, C. Cochrane, G. De Michele, J. Douthwaite, A. Eager, S. Fanella, M. Giles, D. Kaye, V.F. Khan, J. Mannion, J. Morris, J.F. Orrett, N. Pattalwar, E. Rose, D. Soriano Guillén AVO-ADAM, Meyrin, Switzerland
	The LIGHT (Linac for Image-Guided Hadron Therapy) machine is designed to accelerate a proton beam up to 230 MeV to treat deep seated tumours. The machine consists of three different kinds of accelerators: RFQ (Radio-Frequency Quadrupole), SCDTL (Side Coupled Drift Tube Linac) and CCL (Coupled Cavity Linac). These accelerating structures are fed with RF power at 750 MHz (RFQ) and 3 GHz (SCDTLs and CCLs). This power is delivered to the accelerating structure via the high power RF transmission network (RF network). In addition, the RF network needs to offer other functionalities, like protection of the high RF power feeding stations, power splitting, phase and amplitude control and monitoring. The maximum power handling of the RF network corresponds to a peak RF power of 8 MW and an average RF power of 9 kW. It functions either in Ultra-High Vacuum (UHV) conditions at an ultimate operating pressure of 10^-7 mbar, or under pressurized gas. The above listed requirements involve different challenges. In this contribution we exhibit the main aspects to be considered based on AVO experience during the commissioning of the RF network units.
	Poster MOPOGE07 [1.075 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-LINAC2022-MOPOGE07
About •	Received ※ 22 August 2022 — Revised ※ 28 August 2022 — Accepted ※ 29 August 2022 — Issue date ※ 02 September 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPOJO17	High Efficiency High Power Resonant Cavity Amplifier For PIP-II	cavity, coupling, impedance, electron	384
	R.E. Simpson, N. Butler, D.B. Cope, M.P.J. Gaudreau, M.K. Kempkes Diversified Technologies, Inc., Bedford, Massachusetts, USA
	An advanced high-power, high power density, solid state power amplifier (SSPA) was developed to replace Vacuum Electron Devices (VEDs). Diversified Technologies, Inc. (DTI) developed and integrated a resonant-cavity combiner with solid state amplifiers for the Proton Improvement Plan-II (PIP-II) at Fermilab. The architecture combines the power of N-many RF power transistors into a single resonant cavity that are surface-mounted and -cooled. The system is designed so that failure of individual transistors has negligible performance impact. Due to the electrical and mechanical simplicity, maintenance and logistics are simplified. DTI demonstrated the basic feasibility of a 50-100 kW class amplifier resonant cavity combiner system at 650 MHz. A single-cavity system reached 15 kW at 66% power-added efficiency with ten of 12 slots filled on only 1 of 2 cavities faces. The system further demonstrated the expected graceful degradation; an intermittent fault occurred on 1 of the 10 modules and the only observable effect was a reduction in output power to 13.3 kW with a slight reduction in efficiency. Combining of multiple cavities was also demonstrated at low power.
	Poster TUPOJO17 [0.790 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-LINAC2022-TUPOJO17
About •	Received ※ 16 August 2022 — Revised ※ 25 August 2022 — Accepted ※ 28 August 2022 — Issue date ※ 15 September 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

WE2AA04	Data Analysis and Control of an MeV Ultrafast Electron Diffraction System using Machine Learning	electron, real-time, FEM, experiment	650
	T.B. Bolin, S. Biedron, M.A. Fazio, M. Martínez-Ramón, S.I. Sosa Guitron UNM-ECE, Albuquerque, USA M. Babzien, M.G. Fedurin, J.J. Li, M.A. Palmer BNL, Upton, New York, USA S. Biedron Element Aero, Chicago, USA S. Biedron UNM-ME, Albuquerque, New Mexico, USA
	MeV ultrafast electron diffraction (MUED) is a pump-probe material characterization technique to study ultrafast lattice dynamics with high temporal and spatial resolution. It is a relatively young technology that has the potential to shed light onto some of the most puzzling problems in physics. This complex instrument can be advanced into a turn-key high-throughput tool with the aid of machine learning (ML) mechanisms together with high-performance computing. The MUED instrument located in the Accelerator Test Facility of Brookhaven National Laboratory was employed in this work to test different ML approaches for both data analysis and control. We characterized three materials using MUED: graphite, black phosphorous and gold thin films. Diffraction patterns were acquired in single shot mode and different ML methodologies were applied to reduce image noise. Convolutional neural network autoenconder and variational autoenconder models were utilized to extract the noise features and increase the signal-to-noise ratio. The energy jitter of the electron beam was analyzed after noise reduction of the single shot diffraction patterns.

	please see instructions how to view/control embeded videos
	Slides WE2AA04 [12.865 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-LINAC2022-WE2AA04
About •	Received ※ 30 August 2022 — Revised ※ 02 September 2022 — Accepted ※ 15 September 2022 — Issue date ※ 20 September 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPORI02	Machine Learning for Beam Orbit Correction at KOMAC Accelerator	proton, controls, linac, diagnostics	848
	D.-H. Kim, J.J. Dang, H.S. Kim, H.-J. Kwon, S. Lee, S.P. Yun KOMAC, KAERI, Gyeongju, Republic of Korea
	Funding: This work has been supported through KOMAC op-eration fund of KAERI by Ministry of Science and ICT, the Korean government (KAERI ID no. : 524320-22) There are approaches to apply machine learning (ML) techniques to efficiently operate and optimize particle accelerators. Deep neural networks-based model is applied to experiments, correcting beam orbit through the low energy beam transport at the proton injector test stand. For more complex applications, time-series analysis model is studied to predict beam orbit in the 100-MeV beamline at KOMAC. This paper describes experimental data to train neural networks model, and presents the performance of the machine learning models.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-LINAC2022-THPORI02
About •	Received ※ 25 August 2022 — Revised ※ 01 September 2022 — Accepted ※ 08 September 2022 — Issue date ※ 15 September 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPORI16	Machine Learning for RF Breakdown Detection at CLARA	cavity, detector, gun, operation	858
	A.E. Pollard, D.J. Dunning, A.J. Gilfellon STFC/DL/ASTeC, Daresbury, Warrington, Cheshire, United Kingdom
	Maximising the accelerating gradient of RF structures is fundamental to improving accelerator facility performance and cost-effectiveness. Structures must be subjected to a conditioning process before operational use, in which the gradient is gradually increased up to the operating value. A limiting effect during this process is breakdown or vacuum arcing, which can cause damage that limits the ultimate operating gradient. Techniques to efficiently condition the cavities while minimising the number of breakdowns are therefore important. In this paper, machine learning techniques are applied to detect breakdown events in RF pulse traces by approaching the problem as anomaly detection, using a variational autoencoder. This process detects deviations from normal operation and classifies them with near perfect accuracy. Offline data from various sources has been used to develop the techniques, which we aim to test at the CLARA facility at Daresbury Laboratory. Deployment of the machine learning system on the high repetition rate gun upgrade at CLARA has begun.
	Poster THPORI16 [2.099 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-LINAC2022-THPORI16
About •	Received ※ 22 August 2022 — Revised ※ 30 August 2022 — Accepted ※ 01 September 2022 — Issue date ※ 15 October 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Other Keywords

Page

MOPOGE07

High Power RF Transmission Lines of the Light Proton Therapy Linac

cavity, linac, proton, controls

158

J.L. Navarro Quirante, D. Aguilera Murciano, S. Benedetti, G. Castorina, C. Cochrane, G. De Michele, J. Douthwaite, A. Eager, S. Fanella, M. Giles, D. Kaye, V.F. Khan, J. Mannion, J. Morris, J.F. Orrett, N. Pattalwar, E. Rose, D. Soriano Guillén
AVO-ADAM, Meyrin, Switzerland

The LIGHT (Linac for Image-Guided Hadron Therapy) machine is designed to accelerate a proton beam up to 230 MeV to treat deep seated tumours. The machine consists of three different kinds of accelerators: RFQ (Radio-Frequency Quadrupole), SCDTL (Side Coupled Drift Tube Linac) and CCL (Coupled Cavity Linac). These accelerating structures are fed with RF power at 750 MHz (RFQ) and 3 GHz (SCDTLs and CCLs). This power is delivered to the accelerating structure via the high power RF transmission network (RF network). In addition, the RF network needs to offer other functionalities, like protection of the high RF power feeding stations, power splitting, phase and amplitude control and monitoring. The maximum power handling of the RF network corresponds to a peak RF power of 8 MW and an average RF power of 9 kW. It functions either in Ultra-High Vacuum (UHV) conditions at an ultimate operating pressure of 10^-7 mbar, or under pressurized gas. The above listed requirements involve different challenges. In this contribution we exhibit the main aspects to be considered based on AVO experience during the commissioning of the RF network units.

Poster MOPOGE07 [1.075 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-LINAC2022-MOPOGE07

About •

Received ※ 22 August 2022 — Revised ※ 28 August 2022 — Accepted ※ 29 August 2022 — Issue date ※ 02 September 2022

Cite •

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

TUPOJO17

High Efficiency High Power Resonant Cavity Amplifier For PIP-II

cavity, coupling, impedance, electron

384

R.E. Simpson, N. Butler, D.B. Cope, M.P.J. Gaudreau, M.K. Kempkes
Diversified Technologies, Inc., Bedford, Massachusetts, USA

An advanced high-power, high power density, solid state power amplifier (SSPA) was developed to replace Vacuum Electron Devices (VEDs). Diversified Technologies, Inc. (DTI) developed and integrated a resonant-cavity combiner with solid state amplifiers for the Proton Improvement Plan-II (PIP-II) at Fermilab. The architecture combines the power of N-many RF power transistors into a single resonant cavity that are surface-mounted and -cooled. The system is designed so that failure of individual transistors has negligible performance impact. Due to the electrical and mechanical simplicity, maintenance and logistics are simplified. DTI demonstrated the basic feasibility of a 50-100 kW class amplifier resonant cavity combiner system at 650 MHz. A single-cavity system reached 15 kW at 66% power-added efficiency with ten of 12 slots filled on only 1 of 2 cavities faces. The system further demonstrated the expected graceful degradation; an intermittent fault occurred on 1 of the 10 modules and the only observable effect was a reduction in output power to 13.3 kW with a slight reduction in efficiency. Combining of multiple cavities was also demonstrated at low power.

Poster TUPOJO17 [0.790 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-LINAC2022-TUPOJO17

About •

Received ※ 16 August 2022 — Revised ※ 25 August 2022 — Accepted ※ 28 August 2022 — Issue date ※ 15 September 2022

Cite •

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

WE2AA04

Data Analysis and Control of an MeV Ultrafast Electron Diffraction System using Machine Learning

electron, real-time, FEM, experiment

650

T.B. Bolin, S. Biedron, M.A. Fazio, M. Martínez-Ramón, S.I. Sosa Guitron
UNM-ECE, Albuquerque, USA
M. Babzien, M.G. Fedurin, J.J. Li, M.A. Palmer
BNL, Upton, New York, USA
S. Biedron
Element Aero, Chicago, USA
S. Biedron
UNM-ME, Albuquerque, New Mexico, USA

MeV ultrafast electron diffraction (MUED) is a pump-probe material characterization technique to study ultrafast lattice dynamics with high temporal and spatial resolution. It is a relatively young technology that has the potential to shed light onto some of the most puzzling problems in physics. This complex instrument can be advanced into a turn-key high-throughput tool with the aid of machine learning (ML) mechanisms together with high-performance computing. The MUED instrument located in the Accelerator Test Facility of Brookhaven National Laboratory was employed in this work to test different ML approaches for both data analysis and control. We characterized three materials using MUED: graphite, black phosphorous and gold thin films. Diffraction patterns were acquired in single shot mode and different ML methodologies were applied to reduce image noise. Convolutional neural network autoenconder and variational autoenconder models were utilized to extract the noise features and increase the signal-to-noise ratio. The energy jitter of the electron beam was analyzed after noise reduction of the single shot diffraction patterns.

please see instructions how to view/control embeded videos

Slides WE2AA04 [12.865 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-LINAC2022-WE2AA04

About •

Received ※ 30 August 2022 — Revised ※ 02 September 2022 — Accepted ※ 15 September 2022 — Issue date ※ 20 September 2022

Cite •

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

THPORI02

Machine Learning for Beam Orbit Correction at KOMAC Accelerator

proton, controls, linac, diagnostics

848

D.-H. Kim, J.J. Dang, H.S. Kim, H.-J. Kwon, S. Lee, S.P. Yun
KOMAC, KAERI, Gyeongju, Republic of Korea

Funding: This work has been supported through KOMAC op-eration fund of KAERI by Ministry of Science and ICT, the Korean government (KAERI ID no. : 524320-22)
There are approaches to apply machine learning (ML) techniques to efficiently operate and optimize particle accelerators. Deep neural networks-based model is applied to experiments, correcting beam orbit through the low energy beam transport at the proton injector test stand. For more complex applications, time-series analysis model is studied to predict beam orbit in the 100-MeV beamline at KOMAC. This paper describes experimental data to train neural networks model, and presents the performance of the machine learning models.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-LINAC2022-THPORI02

About •

Received ※ 25 August 2022 — Revised ※ 01 September 2022 — Accepted ※ 08 September 2022 — Issue date ※ 15 September 2022

Cite •

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

THPORI16

Machine Learning for RF Breakdown Detection at CLARA

cavity, detector, gun, operation

858

A.E. Pollard, D.J. Dunning, A.J. Gilfellon
STFC/DL/ASTeC, Daresbury, Warrington, Cheshire, United Kingdom

Maximising the accelerating gradient of RF structures is fundamental to improving accelerator facility performance and cost-effectiveness. Structures must be subjected to a conditioning process before operational use, in which the gradient is gradually increased up to the operating value. A limiting effect during this process is breakdown or vacuum arcing, which can cause damage that limits the ultimate operating gradient. Techniques to efficiently condition the cavities while minimising the number of breakdowns are therefore important. In this paper, machine learning techniques are applied to detect breakdown events in RF pulse traces by approaching the problem as anomaly detection, using a variational autoencoder. This process detects deviations from normal operation and classifies them with near perfect accuracy. Offline data from various sources has been used to develop the techniques, which we aim to test at the CLARA facility at Daresbury Laboratory. Deployment of the machine learning system on the high repetition rate gun upgrade at CLARA has begun.

Poster THPORI16 [2.099 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-LINAC2022-THPORI16

About •

Received ※ 22 August 2022 — Revised ※ 30 August 2022 — Accepted ※ 01 September 2022 — Issue date ※ 15 October 2022

Cite •

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