Simulation Supported Profile Reconstruction With Machine Learning

Autor: Singh, Rahul, Sapinski, Mariusz, Vilsmeier, Dominik
Jazyk: angličtina
Rok vydání: 2018
Předmět:
DOI: 10.18429/jacow-ibic2017-wepcc06
Popis: Measured IPM profiles can be significantly distorted due to displacement of residual ions or electrons by interaction with beam fields for high intensity or high energy beams. It is thus difficult to deduce the characteristics of the actual beam profile from the measurements. Neural network with multilayer perceptron (MLP)architecture is applied to reconstruct the actual beam profile from the measurement data. The MLP is trained using the IPM simulation tool developed under the IPMSim collaboration. The first results are presented in this contribution.
Proceedings of the 6th Int. Beam Instrumentation Conf., IBIC2017, Grand Rapids, MI, USA
Databáze: OpenAIRE