Abstract: The present invention relates to a technique for estimating core performance which includes the steps of: dividing a reactor core into a plurality of core portions, each consisting of at least one fuel assembly, then further dividing each of the core portions into segments by planes perpendicular to the axis thereof and allocating a parallel processing apparatus having a plurality of arithmetic processing units, a memory for storing processing data of the arithmetic processing units, and communications circuitry for transferring data with respect to the arithmetic processing units, in a manner such that the arithmetic processing units correspond to the segments of the core. Data on the power distribution for the entire core portion to which a corresponding segment belongs is transferred to each arithmetic processing unit, before each of the arithmetic processing units performs thermal hydraulic calculations.

Abstract: To facilitate architecting of a multiple neural network, irrespective of the quantity of cases and the complexity of case dependence relationship, sets of input instances and the desirable outputs corresponding thereto are stored; the stored sets are read in sequence to discriminate whether all variables included in the input instances of the read set are included in the outputs of any given stored set, to mark variables not included in the outputs of any sets; the sets whose input instances include only the marked variables are selected from among the read sets; unit neural networks for learning the selected sets are formed and simultaneously variables included in the outputs of the formed unit neural networks are marked; a unit neural network for learning any given set is formed; and the formed unit neural networks are connected to each other to architect a multiple neural network.