Search

Optics corrections in the LHC are based on a response matrix approach between available correctors and observables. Supervised learning has been applied to quadrupole error prediction at the LHC giving promising results in simulations and surpassing the performance of the traditional approach. A comparison of different algorithms is given and it is followed by the presentation of further possible concepts to obtain optics corrections using machine learning., Proceedings of the 10th Int. Particle Accelerator Conf., IPAC2019, Melbourne, Australia

Machine learning techniques are used in various scientific and industry fields as a powerful tool for data analysis and automatization. The presentation is devoted to exploration of relevant machine learning methods for beam diagnostics. The target is to provide an insight into modern machine learning techniques, which can be applied to improve current beam diagnostics and general applications in accelerators. Possible concepts for future applications are also presented., Proceedings of the 7\textsuperscript{th} Int. Beam Instrumentation Conf., IBIC2018, Shanghai, China

The fourth one-month Pb-Pb collision run brought LHC Run 2 to an end in December 2018. Following the tendency to reduce dependence on the configuration of the preceding proton run, a completely new optics cycle with the strongest ever focussing at the ALICE and LHCb experiments was designed and rapidly implemented, demonstrating the maturity of the collider’s operating modes. Beam-loss monitor thresholds were carefully adjusted to provide optimal protection from the multiple loss mechanisms in heavy-ion operation. A switch from a basic bunch-spacing of 100 ns to 75 ns was made as the beam became available from the injector chain. A new record luminosity, 6 times the original design and close to the operating value proposed for HL-LHC, provided validation of the strategy for mitigating quenches due to bound-free pair production (BFPP) at the interaction points of the ATLAS and CMS experiments. Most of the beam parameters of the HL-LHC Pb-Pb upgrade were attained during this run and the integrated luminosity goals for the first 10 years of LHC operation were substantially exceeded., Proceedings of the 10th Int. Particle Accelerator Conf., IPAC2019, Melbourne, Australia

Unsupervised learning includes anomaly detection techniques that are suitable for the detection of unusual events such as instrumentation faults in particle accelerators. In this work we present the application of decision trees-based algorithm to faulty BPMs detection at the LHC. This method achieves significant improvements in quality of optics measurements and allows to identify relevant signal properties that contribute to fault detection., Proceedings of the 10th Int. Particle Accelerator Conf., IPAC2019, Melbourne, Australia

Machine Learning (ML) techniques are widely used in science and industry to discover relevant information and make predictions from data. The application ranges from face recognition to High Energy Physics experiments. Recently, the application of ML has grown also in accelerator physics and in particular in the domain of diagnostics and control. The target is to provide an overview of ML techniques and to indicate beam diagnostics tasks where ML based solutions can be efficiently applied to complement or potentially surpass existing methods. Besides, a short summary of recent works will be given demonstrating the great interest for use of ML concepts in beam diagnostics and latest results of incorporating these concepts into accelerator problems, with the focus on beam optics related application., Proceedings of the 39th Free Electron Laser Conference, FEL2019, Hamburg, Germany

The application of machine learning methods and concepts of artificial intelligence can be found in various industry and scientific branches. In Accelerator Physics the machine learning approach has not found a wide application yet. This paper is devoted to evaluation of machine learning methods aiming to improve the optics measurements and corrections at LHC. The main subjects of the study are devoted to recognition and analysis of faulty beam position monitors and prediction of quadrupole errors using clustering algorithms, decision trees and artificial neural networks. The results presented in this paper clearly show the suitability of machine learning methods for the optics control at LHC and the potential for further investigation on appropriate approaches., Proceedings of the 9th Int. Particle Accelerator Conf., IPAC2018, Vancouver, BC, Canada

Transverse coupling has been linked to instabilities and reduction in dynamic aperture and is hence a crucial parameter to control in the LHC. In this article we describe the development to use driven oscillations to measure the transverse coupling with high intensity beams. The method relies on the use of the transverse damper to drive an oscillation in a similar way as with an AC-dipole. The calculation of the coupling is based on the turn-by-turn data from all available BPMs gated for the excited bunch., Proceedings of the 9th Int. Particle Accelerator Conf., IPAC2018, Vancouver, BC, Canada