Ponente
Descripción
Muography is an emergent non-destructive testing technique that uses cosmic muons to probe the interior of objects and structures. This technique can be employed to perform preventive maintenance of critical equipment in the industry in order to test the structural integrity of the facility. Several muography imaging algorithms based on machine learning methods are being developed in the recent years. These algorithms make exhaustive use of simulated data, usually using packages such as GEANT4, that exhaustively simulate the detector, to produce training samples. This work presents a faster alternative for the generation of simulated samples based on generative adversarial neural networks. A speed up factor of 80 is observed with this system without any significant degradation of the quality of the simulation.
Abstract
Muography is an emergent non-destructive testing technique that uses cosmic muons to probe the interior of objects and structures. This technique can be employed to perform preventive maintenance of critical equipment in the industry in order to test the structural integrity of the facility. Several muography imaging algorithms based on machine learning methods are being developed in the recent years. These algorithms make exhaustive use of simulated data, usually using packages such as GEANT4, that exhaustively simulate the detector, to produce training samples. This work presents a faster alternative for the generation of simulated samples based on generative adversarial neural networks. A speed up factor of 80 is observed with this system without any significant degradation of the quality of the simulation.
