Mean cross section prediction in PWR-MOX using neural network

Abstract : Fuel depletion calculation codes require one-group mean cross sections of many nuclides to solve Bateman's equations. In such codes, the mean cross sections are assed by the mean of iterative calls of Boltzmann equation solver thanks to neutron transport codes. This is a time consuming task, especially with Monte Carlo codes such as MCNP. This paper presents a methodology based on neural network for building a cross section predictor for a PWR reactor loaded with any MOX fuel. This approach allows performing fuel depletion calculation in less than one minute with an excellent accuracy. A maximum deviation of 3% on actinides is obtained at the end of cycle between inventories calculated from neural networks and from the reference coupled neutron transport / fuel depletion calculation.
Type de document :
Communication dans un congrès
Nuclear Fuel Cycle for a Low-Carbon Future (GLOBAL 2015), Sep 2015, Paris, France. GLOBAL 2015 Proceedings pp.840-846, 2015
Liste complète des métadonnées

http://hal.in2p3.fr/in2p3-01247904
Contributeur : Emmanuelle Vernay <>
Soumis le : mercredi 23 décembre 2015 - 09:33:51
Dernière modification le : mardi 16 janvier 2018 - 14:39:48

Identifiants

  • HAL Id : in2p3-01247904, version 1

Citation

B. Leniau, B. Mouginot, N. Thiollière, X. Doligez, A. Bidaud, et al.. Mean cross section prediction in PWR-MOX using neural network. Nuclear Fuel Cycle for a Low-Carbon Future (GLOBAL 2015), Sep 2015, Paris, France. GLOBAL 2015 Proceedings pp.840-846, 2015. 〈in2p3-01247904〉

Partager

Métriques

Consultations de la notice

159