Exploration of genetic algorithms to build a balanced neutron spectra dataset useful to train unfolding techniques based on artificial neural networks

Diverse domains need neutrons unfolding technics to assess the incident neutron energy spectrum. Examples are radiation protection, nuclear reactor physics or criticality safety. Traditionally, methods based on the Bayesian approach requires an initial guess of the solution which may significantly i...

Full description

Saved in:
Bibliographic Details
Main Authors: Bouhadida Maha, Hmede Rodayna, Brovchenko Mariya, Monange Wilfried, Vinchon Thibaut, Ducasse Quentin, Trompier François
Format: Article
Language:English
Published: EDP Sciences 2024-01-01
Series:EPJ Web of Conferences
Online Access:https://www.epj-conferences.org/articles/epjconf/pdf/2024/12/epjconf_snamc2024_17011.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850206947454746624
author Bouhadida Maha
Hmede Rodayna
Brovchenko Mariya
Monange Wilfried
Vinchon Thibaut
Ducasse Quentin
Trompier François
author_facet Bouhadida Maha
Hmede Rodayna
Brovchenko Mariya
Monange Wilfried
Vinchon Thibaut
Ducasse Quentin
Trompier François
author_sort Bouhadida Maha
collection DOAJ
description Diverse domains need neutrons unfolding technics to assess the incident neutron energy spectrum. Examples are radiation protection, nuclear reactor physics or criticality safety. Traditionally, methods based on the Bayesian approach requires an initial guess of the solution which may significantly impact the unfolding result. This work proposes a novel method for neutron spectrum reconstruction using machine learning (ML) techniques trained on a large dataset. To ensure the ML algorithm to perform on a large domain of application particular attention has been paid to the dataset creation. We propose a comparison of two methods of building large dataset where the most adequate solution is obtained using a dynamic genetic algorithm (GA). This GA targets optimal combinations of 48 parameters to generate a variety of neutron spectra. The resulting dataset is then used to train a new convolutional neural network architecture for unfolding neutron spectra. Obtained performance metrics of the tested architecture show high efficiency and emphasize the added value of the built dataset.
format Article
id doaj-art-bbd2cee0be69412eb77c42f8e232c960
institution OA Journals
issn 2100-014X
language English
publishDate 2024-01-01
publisher EDP Sciences
record_format Article
series EPJ Web of Conferences
spelling doaj-art-bbd2cee0be69412eb77c42f8e232c9602025-08-20T02:10:39ZengEDP SciencesEPJ Web of Conferences2100-014X2024-01-013021701110.1051/epjconf/202430217011epjconf_snamc2024_17011Exploration of genetic algorithms to build a balanced neutron spectra dataset useful to train unfolding techniques based on artificial neural networksBouhadida Maha0Hmede Rodayna1Brovchenko Mariya2Monange Wilfried3Vinchon Thibaut4Ducasse Quentin5Trompier François6Institut de Radioprotection et de Sûreté Nucléaire (IRSN)Institut de Radioprotection et de Sûreté Nucléaire (IRSN)Institut de Radioprotection et de Sûreté Nucléaire (IRSN)Institut de Radioprotection et de Sûreté Nucléaire (IRSN)Institut de Radioprotection et de Sûreté Nucléaire (IRSN)Institut de Radioprotection et de Sûreté Nucléaire (IRSN)Institut de Radioprotection et de Sûreté Nucléaire (IRSN)Diverse domains need neutrons unfolding technics to assess the incident neutron energy spectrum. Examples are radiation protection, nuclear reactor physics or criticality safety. Traditionally, methods based on the Bayesian approach requires an initial guess of the solution which may significantly impact the unfolding result. This work proposes a novel method for neutron spectrum reconstruction using machine learning (ML) techniques trained on a large dataset. To ensure the ML algorithm to perform on a large domain of application particular attention has been paid to the dataset creation. We propose a comparison of two methods of building large dataset where the most adequate solution is obtained using a dynamic genetic algorithm (GA). This GA targets optimal combinations of 48 parameters to generate a variety of neutron spectra. The resulting dataset is then used to train a new convolutional neural network architecture for unfolding neutron spectra. Obtained performance metrics of the tested architecture show high efficiency and emphasize the added value of the built dataset.https://www.epj-conferences.org/articles/epjconf/pdf/2024/12/epjconf_snamc2024_17011.pdf
spellingShingle Bouhadida Maha
Hmede Rodayna
Brovchenko Mariya
Monange Wilfried
Vinchon Thibaut
Ducasse Quentin
Trompier François
Exploration of genetic algorithms to build a balanced neutron spectra dataset useful to train unfolding techniques based on artificial neural networks
EPJ Web of Conferences
title Exploration of genetic algorithms to build a balanced neutron spectra dataset useful to train unfolding techniques based on artificial neural networks
title_full Exploration of genetic algorithms to build a balanced neutron spectra dataset useful to train unfolding techniques based on artificial neural networks
title_fullStr Exploration of genetic algorithms to build a balanced neutron spectra dataset useful to train unfolding techniques based on artificial neural networks
title_full_unstemmed Exploration of genetic algorithms to build a balanced neutron spectra dataset useful to train unfolding techniques based on artificial neural networks
title_short Exploration of genetic algorithms to build a balanced neutron spectra dataset useful to train unfolding techniques based on artificial neural networks
title_sort exploration of genetic algorithms to build a balanced neutron spectra dataset useful to train unfolding techniques based on artificial neural networks
url https://www.epj-conferences.org/articles/epjconf/pdf/2024/12/epjconf_snamc2024_17011.pdf
work_keys_str_mv AT bouhadidamaha explorationofgeneticalgorithmstobuildabalancedneutronspectradatasetusefultotrainunfoldingtechniquesbasedonartificialneuralnetworks
AT hmederodayna explorationofgeneticalgorithmstobuildabalancedneutronspectradatasetusefultotrainunfoldingtechniquesbasedonartificialneuralnetworks
AT brovchenkomariya explorationofgeneticalgorithmstobuildabalancedneutronspectradatasetusefultotrainunfoldingtechniquesbasedonartificialneuralnetworks
AT monangewilfried explorationofgeneticalgorithmstobuildabalancedneutronspectradatasetusefultotrainunfoldingtechniquesbasedonartificialneuralnetworks
AT vinchonthibaut explorationofgeneticalgorithmstobuildabalancedneutronspectradatasetusefultotrainunfoldingtechniquesbasedonartificialneuralnetworks
AT ducassequentin explorationofgeneticalgorithmstobuildabalancedneutronspectradatasetusefultotrainunfoldingtechniquesbasedonartificialneuralnetworks
AT trompierfrancois explorationofgeneticalgorithmstobuildabalancedneutronspectradatasetusefultotrainunfoldingtechniquesbasedonartificialneuralnetworks