1. Modelization of an Injector With Machine Learning
- Author
-
M.Debongnie†, Accelerator and Cryogenic Systems, Orsay, France and Laboratoire de Physique Subatomique et de Cosmologie, Université Grenoble-Alpes, CNRS/IN2P3, Grenoble, France F. Bouly, M. Baylac, Laboratoire de Physique Subatomique et de Cosmologie, France T. Junquera, France N. Chauvin, D. Uriot, Laboratoire de Physique Subatomique et de Cosmologie (LPSC), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Physique Nucléaire et de Physique des Particules du CNRS (IN2P3)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Institut de Recherches sur les lois Fondamentales de l'Univers (IRFU), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP)-Institut National de Physique Nucléaire et de Physique des Particules du CNRS (IN2P3)-Institut Polytechnique de Grenoble - Grenoble Institute of Technology-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA), Boland, Mark (Ed.), Tanaka, Hitoshi (Ed.), Button, David (Ed.), Dowd, Rohan (Ed.), Schaa, Volker RW (Ed.), Tan, Eugene (Ed.), Institut National de Physique Nucléaire et de Physique des Particules du CNRS (IN2P3)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), and Université Grenoble Alpes (UGA)
- Subjects
solenoid ,rfq ,LEBT ,[PHYS.PHYS.PHYS-ACC-PH]Physics [physics]/Physics [physics]/Accelerator Physics [physics.acc-ph] ,network ,MC5: Beam Dynamics and EM Fields ,Physics::Accelerator Physics ,Accelerator Physics ,proton - Abstract
Modern particle accelerator projects, such as MYRRHA, have very high stability and/or reliability requirements. To meet those, it is necessary to optimize or develop new methods for the control systems. One of the difficulties lies in the relatively long computation time of current beam dynamics codes. In this context, the very low computation time of neural network is of great attraction. However, a neural network has to be trained in order to be of any use. The training of a beam dynamic predictor uses a large dataset (experimental or simulated) that represents the dynamics over the parameter space of interest. Therefore, choosing the right training dataset is crucial for the quality of the neural network predictions. In this work, a study on the sampling choice for the training data is performed to train a neural network to predict the transmission of a beam through a low energy beam transport line and a Radiofrequency Quadrupole. We show and discuss the results obtained on training data set to model the IPHI and MYRRHA injectors., Proceedings of the 10th Int. Particle Accelerator Conf., IPAC2019, Melbourne, Australia
- Published
- 2019
- Full Text
- View/download PDF