English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This study focuses on implementing a real-time control system for a particleaccelerator facility that performs high energy physics experiments. A criticaloperating parameter in this facility is beam loss, which is the fraction ofparticles deviating from the accelerated proton beam into a cascade ofsecondary particles. Accelerators employ a large number of sensors to monitorbeam loss. The data from these sensors is monitored by human operators whopredict the relative contribution of different sub-systems to the beam loss.Using this information, they engage control interventions. In this paper, wepresent a controller to track this phenomenon in real-time using edge-MachineLearning (ML) and support control with low latency and high accuracy. Weimplemented this system on an Intel Arria 10 SoC. Optimizations at thealgorithm, high-level synthesis, and interface levels to improve latency andresource usage are presented. Our design implements a neural network, which canpredict the main source of beam loss (between two possible causes) at speeds upto 575 frames per second (fps) (average latency of 1.74 ms). The practicaldeployed system is required to operate at 320 fps, with a 3ms latencyrequirement, which has been met by our design successfully.

ML-based Real-Time Control at the Edge: An Approach Using hls4ml