Investigating Neutronic Parameters of a Thorium Fusion Breeder With Recurrent Neural Networks

Abstract

Artificial neural networks (ANNs) have recently been introduced to the nuclear engineering applications as a fast and flexible vehicle to modeling, simulation and optimization. In this paper, a new approach based on recurrent neural networks (RNNs) was presented for the neutronic parameters of a thorium fusion breeder. The results of the RNNs implemented for the tritium breeding ratio computation, energy multiplication factor and net U-233 production in a thorium fusion breeder and the results available in the literature obtained by using Scale 4.3 were compared. The drawn conclusions confirmed that the proposed RNNs could provide an accurate computation of the tritium breeding ratio computation, the energy multiplication factor and the net U-233 production of the thorium fusion breeder.