IPAC2018 - List of Authors (Rees, D.)

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)

THPAL025	New Drift-Tube Linac RF Systems at LANSCE	3680
	J.T.M. Lyles, R.E. Bratton, M.S. Prokop, D. Rees LANL, Los Alamos, New Mexico, USA
	Funding: Work supported by the United States Department of Energy, National Nuclear Security Agency, under contract DE-AC52-06NA25396. LANSCE has restored the proton drift-tube linac (DTL) to high-power capability after the original RF-power tube manufacturer could no longer supply devices that consistently met our high-average power requirement. Thales TH628L Diacrodes® now supply RF power to three of the four DTL tanks. These tetrodes reused the existing infrastructure including water-cooling systems, coaxial transmission lines, high-voltage power supplies and capacitor banks. Each transmitter uses a combined pair of power amplifiers to produce up to 3- MW peak and 360- kW of mean power. A new intermediate power amplifier was simultaneously developed using a TH781 tetrode. Design and prototype testing of the high-power stages was completed in 2012, with commercialization following in 2013. Each installation was accomplished during a 4 to 5 month beam outage each year from 2014-2016. A new digital low-level RF control system was designed, built and placed into operation in 2016. The interaction of the dual power amplifiers, the I/Q LLRF, and the DTL cavities provided many challenges that were overcome. The replacement RF systems have completely met our accelerator requirements.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPAL025
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)

THPAL025

New Drift-Tube Linac RF Systems at LANSCE

3680

J.T.M. Lyles, R.E. Bratton, M.S. Prokop, D. Rees
LANL, Los Alamos, New Mexico, USA

Funding: Work supported by the United States Department of Energy, National Nuclear Security Agency, under contract DE-AC52-06NA25396.
LANSCE has restored the proton drift-tube linac (DTL) to high-power capability after the original RF-power tube manufacturer could no longer supply devices that consistently met our high-average power requirement. Thales TH628L Diacrodes® now supply RF power to three of the four DTL tanks. These tetrodes reused the existing infrastructure including water-cooling systems, coaxial transmission lines, high-voltage power supplies and capacitor banks. Each transmitter uses a combined pair of power amplifiers to produce up to 3- MW peak and 360- kW of mean power. A new intermediate power amplifier was simultaneously developed using a TH781 tetrode. Design and prototype testing of the high-power stages was completed in 2012, with commercialization following in 2013. Each installation was accomplished during a 4 to 5 month beam outage each year from 2014-2016. A new digital low-level RF control system was designed, built and placed into operation in 2016. The interaction of the dual power amplifiers, the I/Q LLRF, and the DTL cavities provided many challenges that were overcome. The replacement RF systems have completely met our accelerator requirements.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2018-THPAL025

Export •

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