| Paper | Title | Page |
|---|---|---|
| FRXC01 | Superconducting Radio-Frequency Cavity Fault Classification Using Machine Learning at Jefferson Laboratory | 4535 |
|
||
|
Funding: This work supported by the U.S. Department of Energy, Office of Science, Office of Nuclear Physics under Contract No. DE-AC05-06OR23177. We report on the development of machine learning models for classifying C100 superconducting radiofrequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. Of the 418 SRF cavities in CEBAF, 96 are designed with a digital low-level RF system configured such that a cavity fault triggers recordings of RF signals for each of eight cavities in the cryomodule. Subject matter experts analyze the collected time-series data and identify which of the eight cavities faulted first and classify the type of fault. This information is used to find trends and strategically deploy mitigations to problematic cryomodules. However, manually labeling the data is laborious and time-consuming. By leveraging machine learning, near real-time - rather than postmortem - identification of the offending cavity and classification of the fault type has been implemented. We discuss the performance of the machine learning models during a recent physics run. We also discuss efforts for further insights into fault types through unsupervised learning techniques and present preliminary work on cavity and fault prediction using data collected prior to a failure event. |
||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-FRXC01 | |
| About • | paper received ※ 16 May 2021 paper accepted ※ 01 July 2021 issue date ※ 13 August 2021 | |
| Export • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
FRXC02 |
Non Invasive Bunch Length Measurements Exploiting Cherenkov Diffraction Radiation | |
|
||
| Cherenkov Diffraction Radiation (ChDR) refers to the emission of broadband electromagnetic radiation which occurs when a charged particle propagates at relativistic speed in the vicinity of a dielectric material. At variance with the better-known Cherenkov radiation, ChDR is a non-invasive technique, that is the particle beam does not impinge on the dielectric radiator. ChDR also possesses other interesting features like a relatively high light yield, a broadband spectrum of emission and the emission at a relatively large angle with respect to the beam trajectory. Due to its potential, CERN initiated over the last few years several studies on ChDR-based diagnostics techniques. In this contribution I will focus on the exploitation of ChDR for non-invasive bunch length measurement, from proof of principle tests performed at the CLEAR facility at CERN and CLARA at Daresbury laboratory to current developments for experiments and facilities such as AWAKE and FCC | ||
| Export • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| FRXC03 | Modern Ultra-Fast Detectors for Online Beam Diagnostics | 4540 |
|
||
|
Funding: This work is supported by the BMBF project 05K19VKD STARTRAC and DFG-funded Doctoral School ’Karlsruhe School of Elementary and Astroparticle Physics: Science and Technology’ Synchrotron light sources operate with bunch repetition rates in the MHz regime. The longitudinal and transverse beam dynamics of these electron bunches can be investigated and characterized by experiments employing linear array detectors. To improve the performance of modern beam diagnostics and overcome the limitations of commercially available detectors, we have at KIT developed KALYPSO, a detector system operating with an unprecedented frame rate of up to 12 MHz. To facilitate the integration in different experiments, a modular architecture has been utilized. Different semiconductor microstrip sensors based on Si, InGaAs, PbS, and PbSe can be connected to the custom-designed low noise front-end ASIC to optimize the quantum efficiency at different photon energies, ranging from near-UV, visible, and up to near-IR. The front-end electronics are integrated within a heterogeneous DAQ consisting of FPGAs and GPUs, which allows the implementation of real-time data processing. This detector is currently installed at KARA, European XFEL, FLASH, Soleil, DELTA. In this contribution, we present the detector architecture, the performance results, and the ongoing technical developments. |
||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-FRXC03 | |
| About • | paper received ※ 19 May 2021 paper accepted ※ 22 July 2021 issue date ※ 01 September 2021 | |
| Export • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| FRXC04 | Time-Resolved H⁻ Beam Emittance Measurement at the SNS Linac Using a Laser Comb | 4545 |
|
||
|
Funding: This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). We proposed and demonstrated a novel technique to measure time-resolved transverse emittances of the hydrogen ion (H−) beam in a 1-GeV high-power accelerator. The measurement is performed in a non-intrusive manner by using laser comb - laser pulses with controllable multi-layer temporal structure generated from a fiber-based master laser oscillator and diode-pumped solid-state laser amplifiers. The technique has been applied to the transverse emittance measurement of 1-GeV H− beam at the Spallation Neutron Source (SNS) high energy beam transport (HEBT). More than 20 time-resolved emittances have been simultaneously measured within a macro-pulse, a single mini-pulse, or a single bunch of the 1.4-MW neutron production H− beam from one measurement. |
||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-FRXC04 | |
| About • | paper received ※ 18 May 2021 paper accepted ※ 08 July 2021 issue date ※ 20 August 2021 | |
| Export • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| FRXC05 | Gas Jet In-Vivo Dosimetry for Particle Beam Therapy | 4548 |
|
||
|
Funding: This work is supported by the HL-LHC-UK project funded by STFC and CERN and the STFC Cockcroft core grant No. ST/G008248/1. Medical applications of charged particle beams require a full online characterisation of the beam to ensure patient safety, treatment efficacy, and facility efficiency. In-vivo dosimetry, measurement of delivered dose during treatment, is a significant part of this characterisation. Current methods offer limited information or are invasive to the beam, meaning measurements must be done offline. This contribution presents the development of a non-invasive gas jet in-vivo dosimeter for treatment facilities. The technique is based on the interaction between a particle beam and a supersonic gas jet curtain, which was originally developed for the high luminosity upgrade of the large hadron collider (HL-LHC). To demonstrate the medical application of this technique, an existing HL-LHC test system with minor modifications will be installed at the University of Birmingham’s 35 MeV proton cyclotron, which has properties comparable to that of a treatment beam. This contribution presents the design and development of this test setup, plans for initial benchmarking measurements, and plans for a future optimised medical accelerator gas jet in-vivo dosimeter. |
||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-FRXC05 | |
| About • | paper received ※ 18 May 2021 paper accepted ※ 23 July 2021 issue date ※ 11 August 2021 | |
| Export • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| FRXC06 | Development of the Prototype of the Cavity BPM System for SHINE | 4552 |
|
||
| The Shanghai high repetition rate XFEL and extreme light facility (SHINE) under construction is designed as one of the most advanced FEL facilities in the world, which will produce coherent x-rays with wavelengths from 0.05 to 3 nm and maximum repetition rate of 1MHz. In order to achieve precise, stable alignment of the electron and photo beams in the undulator, the prototype of the cavity beam position monitors (CBPM) including C-band and X-band have been designed and fabricated for the SHINE. And the requirement of the transverse position resolution is better than 200 nm for a single bunch of 100 pC at the dynamic range of ±100 µm. In this paper, we present the design of the cavity with high loaded Q and the RF front-end with low noise-figure, adjustable gain, single-stage down-conversion and phase-locked with reference clock, and also described the structure and specifications of the home-made data acquisition (DAQ) system. The construction of the experiment platform and preliminary measurement result with beam at Shanghai Soft X-ray FEL facility (SXFEL) will be addressed as well. | ||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-FRXC06 | |
| About • | paper received ※ 20 May 2021 paper accepted ※ 06 July 2021 issue date ※ 17 August 2021 | |
| Export • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
FRXC07 |
Uncertainty Quantification for Virtual Diagnostic of Particle Accelerators | |
|
||
| Current diagnostic tools for characterizing a system are often costly, limited and invasive, i.e. interrupt the system’s normal operation. A Virtual Diagnostic (VD) is a computational tool based on deep learning that can be used to predict the diagnostic output. For practical usage of VDs, it is necessary to quantify the prediction’s reliability, namely the uncertainty in that prediction. In this paper, we applied an ensemble of neural networks to create uncertainty and explore various ways of analyzing prediction’s uncertainty using experimental data from the Linac Coherent Light Source particle accelerator at SLAC National Laboratory. We aim to accurately and confidently predict the longitudinal properties of the electron beam as given by their phase-space images. The ability to make informed decisions under uncertainty is crucial for reliable deployment of deep learning tools on safety-critical systems as particle accelerators. | ||
| Export • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |