Neural Networks for Modeling and Control of Particle Accelerators

We describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being dev...

Descripción completa

Detalles Bibliográficos
Autores principales: Edelen, A.L., Biedron, S.G., Chase, B.E., Edstrom, D., Milton, S.V., Stabile, P.
Lenguaje:eng
Publicado: 2016
Materias:
Accelerators and Storage Rings
Acceso en línea:https://dx.doi.org/10.1109/TNS.2016.2543203
http://cds.cern.ch/record/2226404
_version_ 1780952415053283328
author Edelen, A.L.
Biedron, S.G.
Chase, B.E.
Edstrom, D.
Milton, S.V.
Stabile, P.
author_facet Edelen, A.L.
Biedron, S.G.
Chase, B.E.
Edstrom, D.
Milton, S.V.
Stabile, P.
author_sort Edelen, A.L.
collection CERN
description We describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.
id cern-2226404
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2016
record_format invenio
spelling cern-22264042021-05-04T07:18:14Zdoi:10.1109/TNS.2016.2543203http://cds.cern.ch/record/2226404engEdelen, A.L.Biedron, S.G.Chase, B.E.Edstrom, D.Milton, S.V.Stabile, P.Neural Networks for Modeling and Control of Particle AcceleratorsAccelerators and Storage RingsWe describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.Particle accelerators are host to myriad nonlinear and complex physical phenomena. They often involve a multitude of interacting systems, are subject to tight performance demands, and should be able to run for extended periods of time with minimal interruptions. Often times, traditional control techniques cannot fully meet these requirements. One promising avenue is to introduce machine learning and sophisticated control techniques inspired by artificial intelligence, particularly in light of recent theoretical and practical advances in these fields. Within machine learning and artificial intelligence, neural networks are particularly well-suited to modeling, control, and diagnostic analysis of complex, nonlinear, and time-varying systems, as well as systems with large parameter spaces. Consequently, the use of neural network-based modeling and control techniques could be of significant benefit to particle accelerators. For the same reasons, particle accelerators are also ideal test-beds for these techniques. Many early attempts to apply neural networks to particle accelerators yielded mixed results due to the relative immaturity of the technology for such tasks. The purpose of this paper is to re-introduce neural networks to the particle accelerator community and report on some work in neural network control that is being conducted as part of a dedicated collaboration between Fermilab and Colorado State University (CSU). We describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.We describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.FERMILAB-PUB-16-121-ADarXiv:1610.06151FERMILAB-PUB-16-121-ADoai:cds.cern.ch:22264042016-10-19
spellingShingle Accelerators and Storage Rings
Edelen, A.L.
Biedron, S.G.
Chase, B.E.
Edstrom, D.
Milton, S.V.
Stabile, P.
Neural Networks for Modeling and Control of Particle Accelerators
title Neural Networks for Modeling and Control of Particle Accelerators
title_full Neural Networks for Modeling and Control of Particle Accelerators
title_fullStr Neural Networks for Modeling and Control of Particle Accelerators
title_full_unstemmed Neural Networks for Modeling and Control of Particle Accelerators
title_short Neural Networks for Modeling and Control of Particle Accelerators
title_sort neural networks for modeling and control of particle accelerators
topic Accelerators and Storage Rings
url https://dx.doi.org/10.1109/TNS.2016.2543203
http://cds.cern.ch/record/2226404
work_keys_str_mv AT edelenal neuralnetworksformodelingandcontrolofparticleaccelerators
AT biedronsg neuralnetworksformodelingandcontrolofparticleaccelerators
AT chasebe neuralnetworksformodelingandcontrolofparticleaccelerators
AT edstromd neuralnetworksformodelingandcontrolofparticleaccelerators
AT miltonsv neuralnetworksformodelingandcontrolofparticleaccelerators
AT stabilep neuralnetworksformodelingandcontrolofparticleaccelerators

Ejemplares similares