Paper | Title | Other Keywords | Page |
---|---|---|---|
TU3C02 | FPGA Architectures for Distributed ML Systems for Real-Time Beam Loss De-Blending | network, real-time, operation, FPGA | 160 |
|
|||
Funding: Operated by Fermi Research Alliance, LLC under Contract No.DE-AC02-07CH11359 with the United States Department of Energy. Additional funding provided by Grant Award No. LAB 20-2261 [1] The Real-time Edge AI for Distributed Systems (READS) project’s goal is to create a Machine Learning (ML) system for real-time beam loss de-blending within the accelerator enclosure, which houses two accelerators: the Main Injector (MI) and the Recycler (RR). In periods of joint operation, when both machines contain high intensity beam, radiative beam losses from MI and RR overlap on the enclosure¿s beam loss monitoring (BLM) system, making it difficult to attribute those losses to a single machine. Incorrect diagnoses result in unnecessary downtime that incurs both financial and experimental cost. The ML system will automatically disentangle each machine¿s contributions to those measured losses, while not disrupting the existing operations-critical functions of the BLM system. Within this paper, the ML models, used for learning both local and global machine signatures and producing high quality inferences based on raw BLM loss measurements, will only be discussed at a high-level. This paper will focus on the evolution of the architecture, which provided the high-frequency, low-latency collection of synchronized data streams to make real-time inferences. Performed at Northwestern with support from the Departments of Computer Science and Electrical and Computer Engineering |
|||
Slides TU3C02 [17.830 MB] | |||
DOI • | reference for this paper ※ doi:10.18429/JACoW-IBIC2023-TU3C02 | ||
About • | Received ※ 07 September 2023 — Revised ※ 10 September 2023 — Accepted ※ 12 September 2023 — Issue date ※ 25 September 2023 | ||
Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | ||
WE3I01 | Gas Jet-Based Fluorescence Profile Monitor for Low Energy Electrons and High Energy Protons at LHC | electron, experiment, photon, injection | 312 |
|
|||
The ever-developing accelerator capabilities of increasing beam intensity, e.g. for High Luminosity LHC (HL-LHC), demand novel non-invasive beam diagnostics. As a part of the HL-LHC project a Beam Gas Curtain monitor (BGC), a gas jet-based fluorescence transverse profile monitor, is being developed. The BGC uses a supersonic gas jet sheet that traverses the beam at 45° and visualizes a two-dimensional beam-induced fluorescent image. The principle of observing photons created by fluorescence makes the monitor insensitive to present electric or magnetic fields. Therefore, the monitor is well suited for high-intensity beams such as low-energy electron beam of Hollow Electron Lens (HEL), and HL-LHC proton beam, either as a profile or an overlap monitor. This talk will focus on the first gas jet measured transverse profile of the 7keV hollow electron beam. The measurements were carried out at the Electron Beam Test Stand at CERN testing up to 5A beam for HEL. A comparison with Optical Transition Radiation measurements shows consistency with the BGC results. The BGC installation of January 2023 at LHC is shown, including past results from distributed gas fluorescence tests. | |||
Slides WE3I01 [7.338 MB] | |||
DOI • | reference for this paper ※ doi:10.18429/JACoW-IBIC2023-WE3I01 | ||
About • | Received ※ 06 September 2023 — Revised ※ 08 September 2023 — Accepted ※ 27 September 2023 — Issue date ※ 02 October 2023 | ||
Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | ||
WEP046 | Progress on Distributed Image Analysis from Digital Cameras at ELSA using the RabbitMQ Message Broker | interface, framework, controls, network | 449 |
|
|||
In the course of modernization of camera based imaging and image analysis for accelerator hardware and beam control at the ELSA facility, a distributed image processing approach was implemented, called FGrabbit. We utilize the RabbitMQ message broker to share the high data throughput from image acquisition, processing, analysis, display and storage between different work stations to achieve an optimum efficacy of the involved hardware. Re-calibration of already deployed beam profile monitors using machine vision algorithms allow us to perform qualitative beam photometry measurements to obtain beam sizes and dynamics with good precision. We describe the robustness of the calibration, image acquisition and processing and present the architecture and applications, such as the programming- and web-interface for machine operators and developers. | |||
DOI • | reference for this paper ※ doi:10.18429/JACoW-IBIC2023-WEP046 | ||
About • | Received ※ 07 September 2023 — Revised ※ 08 September 2023 — Accepted ※ 15 September 2023 — Issue date ※ 28 September 2023 | ||
Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | ||