| Title |
Modeling Particle Stability Plots for Accelerator Optimization Using Adaptive Sampling |
| Authors |
- M. Schenk, L. Coyle, T. Pieloni
EPFL, Lausanne, Switzerland
- M. Giovannozzi, A. Mereghetti
CERN, Meyrin, Switzerland
- E. Krymova, G. Obozinski
SDSC, Lausanne, Switzerland
|
| Abstract |
One key aspect of accelerator optimization is to maximize the dynamic aperture (DA) of a ring. Given the number of adjustable parameters and the compute-intensity of DA simulations, this task can benefit significantly from efficient search algorithms of the available parameter space. We propose to gradually train and improve a surrogate model of the DA from SixTrack simulations while exploring the parameter space with adaptive sampling methods. Here we report on a first model of the particle stability plots using convolutional generative adversarial networks (GAN) trained on a subset of SixTrack numerical simulations for different ring configurations of the Large Hadron Collider at CERN.
|
| Funding |
This work is partially funded by the Swiss Data Science Center (SDSC), project C18-07. |
| Paper |
download TUPAB216.PDF [15.019 MB / 4 pages] |
| Export |
download ※ BibTeX
※ LaTeX
※ Text/Word
※ RIS
※ EndNote |
| Conference |
IPAC2021 |
| Series |
International Particle Accelerator Conference (12th) |
| Location |
Campinas, SP, Brazil |
| Date |
24-28 May 2021 |
| Publisher |
JACoW Publishing, Geneva, Switzerland |
| Editorial Board |
Liu Lin (LNLS, Campinas, Brazil); John M. Byrd (ANL, Lemont, IL, USA); Regis Neuenschwander (LNLS, Campinas, Brazil); Renan Picoreti (LNLS, Campinas, Brazil); Volker R. W. Schaa (GSI, Darmstadt, Germany) |
| Online ISBN |
978-3-95450-214-1 |
| Online ISSN |
2673-5490 |
| Received |
19 May 2021 |
| Accepted |
17 June 2021 |
| Issue Date |
22 August 2021 |
| DOI |
doi:10.18429/JACoW-IPAC2021-TUPAB216 |
| Pages |
1923-1926 |
| Copyright |
 Published by JACoW Publishing under the terms of the Creative Commons Attribution 3.0 International license. Any further distribution of this work must maintain attribution to the author(s), the published article's title, publisher, and DOI. |
|
