IPAC2018 - List of Authors (Edelen, A.L.)

Paper	Title	Page
THYGBE1	Applying Artificial Intelligence to Accelerators	2925
	A. Scheinker, R.W. Garnett, D. Rees LANL, Los Alamos, New Mexico, USA D.K. Bohler SLAC, Menlo Park, California, USA A.L. Edelen, S.V. Milton CSU, Fort Collins, Colorado, USA
	Particle accelerators are being designed and operated over a wide range of complex beam phase space distributions. For example, the Linac Coherent Light Source (LCLS) upgrade, LCLS-II, is considering complex schemes such as two-color operation [1], while the plasma wake field acceleration facility for advanced accelerator experimental tests (FACET) upgrade, FACET-II, is planning on providing custom tailored current profiles [2]. Because of uncertainty due to limited diagnostics and time varying performance, such as thermal drifts, as well as collective effects and the complex coupling of large numbers of components, it is impossible to use simple look up tables for parameter settings in order to quickly switch between widely varying operating ranges. Several forms of artificial intelligence are currently being investigated in order to enable accelerators to quickly and automatically re-adjust component settings without human intervention. In this work we discuss recent progress in applying neural networks and adaptive feedback algorithms to enable automatic accelerator tuning and optimization. [1] A. A. Lutman et al., Nat. Photonics 10.11, 745 (2016). [2] V. Yakimenko et al., IPAC2016, Busan, Korea, 2016.
	Slides THYGBE1 [14.256 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THYGBE1
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THYGBE2	Results and Discussion of Recent Applications of Neural Network-Based Approaches to the Modeling and Control of Particle Accelerators
	A.L. Edelen CSU, Fort Collins, Colorado, USA S. Biedron University of New Mexico, Albuquerque, USA D.L. Bowring, B.E. Chase, D.R. Edstrom, J. Steimel Fermilab, Batavia, Illinois, USA J.P. Edelen RadiaSoft LLC, Boulder, Colorado, USA P.J.M. van der Slot Mesa+, Enschede, The Netherlands
	Here we highlight several examples from our work in applying neural network-based modeling and control techniques to particle accelerator systems, through a combination of simulation and experimental studies. We also discuss where the specific approaches used fit into the state of the art in deep learning for control, including limitations of the present state of the art (for example in efficiently dealing with noisy, time-varying, many-parameter systems, like those found in accelerators). We will also briefly clarify some of the terminology/taxonomy of artificial intelligence, and describe how the neural network approaches used here relate to other classes of algorithms that are familiar to the accelerator community. The particle accelerator applications discussed include resonant frequency control of Fermilab's PIP-II RFQ, fast switching between beam parameters in a compact THz FEL, modeling of the FAST low energy beamline at Fermilab, temperature control for the FAST RF gun, and trajectory control for the Jefferson Laboratory FEL.
	Slides THYGBE2 [37.657 MB]
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPMF025	Emittance Measurements at FAST Facility	4100
	J. Ruan, D.R. Broemmelsiek, D.J. Crawford, A.L. Edelen, J.P. Edelen, D.R. Edstrom, A.H. Lumpkin, P. Piot, A.L. Romanov, R.M. Thurman-Keup Fermilab, Batavia, Illinois, USA P. Piot Northern Illinois University, DeKalb, Illinois, USA
	Funding: *Operated by Fermi Research Alliance, LLC under Contract No. DE-AC02-07CH11359 with the United States Department of Energy. The FAST facility at Fermilab recently been commissioned has demonstrated the generation of electron beam within a wide range of parameter (energy, charge) suitable for accelerator-science and beam-physics experiments. This accelerator consists of a photo-electron gun, injector, ILC-type cryomodules, and multiple downstream beam-lines. It will mainly serve as injector for the upcoming Integrable Optical Test Accelerator (IOTA). At the same time we will also carry out a LINAC based intense gamma ray experiment based on the Inverse Compton scattering. It is essential to understand the beam emittance for both experiments. A number of techniques are used to characaterizing the beam emittance including slit based method and quad scan method. An on-line emittance measurement based on multi-slit method is developed so the emittance measured will be immediately available to support further beam optimization. In this report we will present the results from the emittance studies using this tool. We will also present the emittance measurement based on quads scan technique for the high energy beam line.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPMF025
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Applying Artificial Intelligence to Accelerators

2925

A. Scheinker, R.W. Garnett, D. Rees
LANL, Los Alamos, New Mexico, USA
D.K. Bohler
SLAC, Menlo Park, California, USA
A.L. Edelen, S.V. Milton
CSU, Fort Collins, Colorado, USA

Particle accelerators are being designed and operated over a wide range of complex beam phase space distributions. For example, the Linac Coherent Light Source (LCLS) upgrade, LCLS-II, is considering complex schemes such as two-color operation [1], while the plasma wake field acceleration facility for advanced accelerator experimental tests (FACET) upgrade, FACET-II, is planning on providing custom tailored current profiles [2]. Because of uncertainty due to limited diagnostics and time varying performance, such as thermal drifts, as well as collective effects and the complex coupling of large numbers of components, it is impossible to use simple look up tables for parameter settings in order to quickly switch between widely varying operating ranges. Several forms of artificial intelligence are currently being investigated in order to enable accelerators to quickly and automatically re-adjust component settings without human intervention. In this work we discuss recent progress in applying neural networks and adaptive feedback algorithms to enable automatic accelerator tuning and optimization.
[1] A. A. Lutman et al., Nat. Photonics 10.11, 745 (2016).
[2] V. Yakimenko et al., IPAC2016, Busan, Korea, 2016.

Slides THYGBE1 [14.256 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THYGBE1

Export •

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

THYGBE2

Results and Discussion of Recent Applications of Neural Network-Based Approaches to the Modeling and Control of Particle Accelerators

A.L. Edelen
CSU, Fort Collins, Colorado, USA
S. Biedron
University of New Mexico, Albuquerque, USA
D.L. Bowring, B.E. Chase, D.R. Edstrom, J. Steimel
Fermilab, Batavia, Illinois, USA
J.P. Edelen
RadiaSoft LLC, Boulder, Colorado, USA
P.J.M. van der Slot
Mesa+, Enschede, The Netherlands

Here we highlight several examples from our work in applying neural network-based modeling and control techniques to particle accelerator systems, through a combination of simulation and experimental studies. We also discuss where the specific approaches used fit into the state of the art in deep learning for control, including limitations of the present state of the art (for example in efficiently dealing with noisy, time-varying, many-parameter systems, like those found in accelerators). We will also briefly clarify some of the terminology/taxonomy of artificial intelligence, and describe how the neural network approaches used here relate to other classes of algorithms that are familiar to the accelerator community. The particle accelerator applications discussed include resonant frequency control of Fermilab's PIP-II RFQ, fast switching between beam parameters in a compact THz FEL, modeling of the FAST low energy beamline at Fermilab, temperature control for the FAST RF gun, and trajectory control for the Jefferson Laboratory FEL.

Slides THYGBE2 [37.657 MB]

Export •

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

THPMF025

Emittance Measurements at FAST Facility

4100

J. Ruan, D.R. Broemmelsiek, D.J. Crawford, A.L. Edelen, J.P. Edelen, D.R. Edstrom, A.H. Lumpkin, P. Piot, A.L. Romanov, R.M. Thurman-Keup
Fermilab, Batavia, Illinois, USA
P. Piot
Northern Illinois University, DeKalb, Illinois, USA

Funding: *Operated by Fermi Research Alliance, LLC under Contract No. DE-AC02-07CH11359 with the United States Department of Energy.
The FAST facility at Fermilab recently been commissioned has demonstrated the generation of electron beam within a wide range of parameter (energy, charge) suitable for accelerator-science and beam-physics experiments. This accelerator consists of a photo-electron gun, injector, ILC-type cryomodules, and multiple downstream beam-lines. It will mainly serve as injector for the upcoming Integrable Optical Test Accelerator (IOTA). At the same time we will also carry out a LINAC based intense gamma ray experiment based on the Inverse Compton scattering. It is essential to understand the beam emittance for both experiments. A number of techniques are used to characaterizing the beam emittance including slit based method and quad scan method. An on-line emittance measurement based on multi-slit method is developed so the emittance measured will be immediately available to support further beam optimization. In this report we will present the results from the emittance studies using this tool. We will also present the emittance measurement based on quads scan technique for the high energy beam line.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPMF025

Export •

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