A New Approach to Spatio-Temporal Calculation of Nuclear Reactor Cores Using Neural Computing

Abstract

In this paper, we describe an innovative method to model and solve spatio-temporal behavior of nuclear reactor cores via three-dimensional multilayer cellular neural networks. This method uses electrical elements and the existing duality between neutronic and thermal-hydraulic parameters of nuclear reactors. The relevant electrical circuit can be simulated by existing professional electrical circuit software. This research goes beyond our previous efforts to use a neural computing approach in the nuclear field. Modeling and solving simple nuclear reactor kinetic equations is now expanded to a complete dynamic calculation, integrating the core thermal-hydraulic models and the relevant feedback effects, in a heterogeneous reactor core.