Mean cross section prediction in PWR-MOX using neural network

ISBN 978-1-49-51-6286-2International audienceFuel depletion calculation codes require one-group mean cross sections of manynuclides to solve Bateman's equations. In such codes, the mean cross sections are assed by themean of iterative calls of Boltzmann equation solver thanks to neutron transport codes. This is atime consuming task, especially with Monte Carlo codes such as MCNP. This paper presents amethodology based on neural network for building a cross section predictor for a PWR reactorloaded with any MOX fuel. This approach allows performing fuel depletion calculation in lessthan one minute with an excellent accuracy. A maximum deviation of 3% on actinides is obtainedat the end of cycle between inventories calculated from neural networks and from the referencecoupled neutron transport / fuel depletion calculation