| Paper | Title | Page |
|---|---|---|
| TUPOST040 | Automated Intensity Optimisation Using Reinforcement Learning at LEIR | 941 |
|
||
| High intensities in the CERN Low Energy Ion Ring (LEIR) are achieved by stacking up to seven consecutive multi-turn injections from Linac3. Two inclined septa combined with a collapsing horizontal orbit bump allow a 6-D phase space painting via a linearly ramped mean momentum along the Linac3 pulse and injection at high dispersion. The beam is cooled and dragged longitudinally via electron cooling (e-cooling) into a stacking momentum. For optimal accumulation, the electron energy and trajectory need to match the ion energy and orbit at the e-cooler section. In this paper, a reinforcement learning (RL) agent is trained to adjust various e-cooler and Linac3 parameters to maximise the intensity at the end of the injection plateau. Variational Auto-Encoders (VAE) are used to compress longitudinal Schottky spectra into a compact representation as input for the RL agent. The RL agent is pre-trained on a surrogate model of the LEIR e-cooling dynamics, which in turn is learned from the data collected for the training of the VAE. The performance of the VAE, the surrogate model, and the RL agent is investigated in this paper. An overview of planned tests in the upcoming LEIR runs is given. | ||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOST040 | |
| About • | Received ※ 08 June 2022 — Revised ※ 13 June 2022 — Accepted ※ 17 June 2022 — Issue date ※ 10 July 2022 | |
| Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| TUPOST044 | Fortune Telling or Physics Prediction? Deep Learning for On-Line Kicker Temperature Forecasting | 957 |
|
||
| The injection kicker system MKP of the Super Proton Synchrotron SPS at CERN is composed of 4 kicker tanks. The MKP-L tank provides additional kick needed to inject 26 GeV Large Hadron Collider LHC 25 ns type beams. This device has been a limiting factor for operation with high intensity, due to the magnet’s broadband beam coupling impedance and consequent beam induced heating. To optimise the usage of the SPS and avoid idle (kicker cooling) time, studies were conducted to develop a recurrent deep learning model that could predict the measured temperature evolution of the MKP-L, using the beam conditions and temperature history as input. In a second stage, the ferrite temperature is also estimated putting together the external temperature predictions from accurate thermo-mechanical simulations of the kicker magnet. In this paper, the methodology is described and details of the neural network architecture used, together with the implementation of an ad-hoc loss function, are given. The results applied to the SPS 2021 operational data are presented. | ||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOST044 | |
| About • | Received ※ 06 June 2022 — Revised ※ 14 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 18 June 2022 | |
| Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| TUPOST045 | Overview of the Machine Learning and Numerical Optimiser Applications on Beam Transfer Systems for LHC and Its Injectors | 961 |
|
||
| Machine learning and numerical optimisation algorithms are getting more and more popular in the accelerator physics community and, thanks to the computing power available, their application in daily operation more likely. In the CERN accelerator complex, and specifically on the beam transfer systems, many promising exploitation of these numerical tools have been put in place in the last years. Some of the state-of-the-art machine learning models have been explored and used to solve problems that were never fully addressed in the past. In this paper, the most recent results of application of machine learning and numerical optimisation for injection, extraction and transfer of beam from machine and to experimental areas are presented. An overview of the possible next steps and shortcomings is finally discussed. | ||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOST045 | |
| About • | Received ※ 06 June 2022 — Revised ※ 14 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 10 July 2022 | |
| Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| WEIYGD1 | Achievements and Performance Prospects of the Upgraded LHC Injectors | 1610 |
|
||
| To provide HL-LHC performance, the CERN LHC injector chain underwent a major upgrade during an almost 2-year-long shutdown. In the first half of 2021 the injectors were gradually re-started with the aim to reach at least pre-shutdown parameters for LHC as well as for fixed target beams. The strategy of the commissioning across the complex, a summary of the many challenges and finally the achievements will be presented. Several lessons were learned and have been integrated to define the strategy for the performance ramp-up over the coming years. Remaining limitations and prospects for LHC beam parameters at the exit of the LHC injector chain in the years to come will be discussed. Finally, the emerging need for improved operability of the CERN complex will be addressed, with a description of the first efforts to meet the availability and flexibility requirements of the HL-LHC era while at the same time maximizing fixed target physics output. | ||
|
Slides WEIYGD1 [5.905 MB] | |
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-WEIYGD1 | |
| About • | Received ※ 08 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 09 July 2022 | |
| Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| WEPOST013 | Exploitation of Crystal Shadowing via Multi-Crystal Array, Optimisers and Reinforcement Learning | 1707 |
|
||
|
The CERN Super Proton Synchrotron (SPS) routinely delivers proton and heavy ion beams to the North experimental Area (NA) in the form of 4.8 s spills. To produce such a long flux of particles, resonant third integer slow extraction is used, which, by design, foresees primary beam lost on the electrostatic septum wires to separate circulating from extracted beam. Shadowing with thin bent crystal has been proposed and successfully tested in the SPS, as detailed in *. In 2021, a thin crystal was used for physics production showing results compatible with what measured during early testing. In this paper, the results from the 2021 physics run are presented also comparing particle losses at extraction with previous operational years. The setting up of the crystal using numerical optimisers is detailed, with possible implementation of reinforcement learning (RL) agents to improve the setting up time. Finally, the full exploitation of crystal shadowing via multi-array crystals is discussed, together with the performance reach in the SPS.
F.Velotti, et. al, "Septum shadowing by means of a bent crystal to reduce slow extraction beam loss", Phys. Rev. Accel. Beams 22, 093502 - Published 27 September 2019 |
||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-WEPOST013 | |
| About • | Received ※ 06 June 2022 — Revised ※ 14 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 02 July 2022 | |
| Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| WEPOST015 | Implementation of a Tune Sweep Slow Extraction with Constant Optics at MedAustron | 1715 |
|
||
| Conventional slow extraction driven by a tune sweep perturbs the optics and changes the presentation of the beam separatrix to the extraction septum during the spill. The constant optics slow extraction (COSE) technique, recently developed and deployed operationally at the CERN Super Proton Synchrotron to reduce beam loss on the extraction septum, was implemented at MedAustron to facilitate extraction with a tune sweep of operational beam quality. COSE fixes the optics of the extracted beam by scaling all machine settings with the beam rigidity following the extracted beam’s momentum. In this contribution the implementation of the COSE extraction technique is described before it is compared to the conventional tune sweep and operational betatron core driven cases using both simulations and recent measurements. | ||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-WEPOST015 | |
| About • | Received ※ 07 June 2022 — Revised ※ 16 June 2022 — Accepted ※ 17 June 2022 — Issue date ※ 18 June 2022 | |
| Cite • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |