| Article | |
| Title | Experimental Demonstration of Machine Learning Application in LHC Optics Commissioning |
| Author(s) | Fol, Elena (CERN) ; Cardona, Javier (Colombia, U. Natl.) ; Carlier, Felix (CERN) ; Dilly, Joschua (CERN) ; Hofer, Michael (CERN) ; Keintzel, Jacqueline (CERN) ; Le Garrec, Mael (CERN) ; Maclean, Ewen (CERN) ; Persson, Tobias (CERN) ; Soubelet, Felix (CERN) ; Tomás García, Rogelio (CERN) ; Wegscheider, Andreas (CERN) |
| Publication | 2022 |
| Number of pages | 4 |
| In: | JACoW IPAC 2022 (2022) 359-362 |
| In: | 13th International Particle Accelerator Conference (IPAC 2022), Bangkok, Thailand, 12 - 17 Jun 2022, pp.359-362 |
| DOI | 10.18429/JACoW-IPAC2022-MOPOPT047 |
| Subject category | Accelerators and Storage Rings |
| Accelerator/Facility, Experiment | CERN LHC |
| Abstract | Recently, we conducted successful studies on the suitability of machine learning (ML) methods for optics measurements and corrections, incorporating novel ML-based methods for local optics corrections and reconstruction of optics functions. After performing extensive verifications on simulations and past measurement data, the newly developed techniques became operational in the LHC commissioning 2022. We present the experimental results obtained with the ML-based methods and discuss future improvements. Besides, we also report on improving the Beam Position Monitor (BPM) diagnostics with the help of the anomaly detection technique capable to identify malfunctioning BPMs along with their possible fault causes. |
| Copyright/License | CC-BY-3.0 |
Corresponding record in: Inspire
Record created 2023-01-11, last modified 2023-01-11
