20–22 nov. 2024
IPHC, Strasbourg
Fuseau horaire Europe/Paris

Session

ML for accelerators

21 nov. 2024, 14:00
Amphi Grïnewald (IPHC, Strasbourg)

Amphi Grïnewald

IPHC, Strasbourg

Batiment 27, BP28, 67037 Cedex 2, 23 Rue du Loess, 67200 Strasbourg

Présidents de session

ML for accelerators

  • Hayg Guler (IJCLAB)
  • Francis Osswald (IPHC)

Documents de présentation

Aucun document.

  1. M. Abdelaziz Guelfane (CentraleSupélec), Ismail Cherkaoui (CentraleSupélec)
    21/11/2024 14:00
    Analysis : event classification, statistical analysis and inference, anomaly detection

    SuperKEKB and the future circular colliders aim at luminosity as high as of $10^{35} cm^{–2}s^{–1}$. This requires very high beams current and very small beam sizes (nano-beams). In order to reach such beam sizes the accelerator physicist needs to control beam quality and accelerator optics. In particular, controlling even small linear and nonlinear effects that can perturb the optics is...

    Go to contribution page
  2. Fatima Basbous (Arronax)
    21/11/2024 14:25
    Accelerator control

    ARRONAX, Accélérateur pour la Recherche en Radiochimie et Oncologie à Nantes Atlantique, est un cyclotron multi-particules capable de produire des protons à haute intensité (2 × 375 μA) et à haute énergie (70 MeV). Il assure la précision de la livraison des faisceaux ioniques à la cible en garantissant leur énergie et leurs propriétés requises. Cependant, des anomalies peuvent survenir,...

    Go to contribution page
  3. Francis Osswald (IPHC)
    21/11/2024 14:50
    Object detection and reconstruction

    We want to develop a new numerical analysis tool using artificial intelligence techniques to improve the denoising, segmentation, and reconstruction of images that characterize the beams of accelerated particles. These improvements aim to increase the accuracy of measurements, in particular to better characterize the halo of the beams, and reduce beam losses by ultimately making processes more...

    Go to contribution page
  4. Charly Lassalle (Université de Caen Normandie / GANIL)
    21/11/2024 15:15
    Analysis : event classification, statistical analysis and inference, anomaly detection

    We present works on heat load neural observers for the SPIRAL2 superconducting linear accelerator at GANIL. This virtual diagnostic focuses on superconducting (SC) radiofrequency (RF) cavities, which accelerate the particle beam. The cavities are housed in cryomodules, structures that ensure their cryogenic and radiofrequency operation in a superconducting state. Actuators control the pressure...

    Go to contribution page
  5. Valérie Gautard (CEA-Irfu)
    21/11/2024 16:10
    Simulations and surrogate models : replacing an existing complex physical model

    The technological advance of today’s storage rings and colliders elevated nonlinear beam dynamics to the forefront of accelerator design and operation. In the field of single-particle beam dynamics, the concept of dynamic aperture (DA), that is, the extent of the phase-space region where bounded motion occurs, is a key observable to guide the design of present, e.g. the CERN Large Hadron...

    Go to contribution page
  6. Hayg Guler (IJCLAB)
    21/11/2024 16:35
    Simulations and surrogate models : replacing an existing complex physical model

    Accurately modeling and simulating dynamic systems remains a central challenge in computational physics and numerical engineering. Traditional approaches, such as time series prediction and ordinary differential equation (ODE) modeling, have been widely explored in the literature. However, these methods fall short when applied to the complex and potentially discontinuous behavior of particle...

    Go to contribution page
  7. Damien Minenna (CEA/Irfu/DACM)
    21/11/2024 17:00
    Infrastructure : hardware and software for Machine Learning

    Designing superconducting magnets presents a challenge due to their multi-physics complexity, diverse analytical tools, and often imprecise specifications. To streamline this process, we introduce ALESIA, a novel optimisation and data management toolbox developed at CEA-IRFU.

    ALESIA leverages advanced algorithms, including nonlinear programming techniques, evolutionary algorithms, active...

    Go to contribution page
Ordre du jour en construction...