Nuclear Reactors Safety Core Parameters Prediction using Artificial Neural Networks

Abstract

The present work investigates an appropriate algorithm based on Multilayer Perceptron Neural Network (MPNN), Apriori association rules and Particle Swarm Optimization (PSO) models for predicting two significant core safety parameters; the multiplication factor K eff and the power peaking factor P max of the benchmark 10 MW IAEA LEU research reactor. It provides a comprehensive analytic method for establishing an Artificial Neural Network (ANN) with selforganizing architecture by finding an optimal number of hidden layers and their neurons, a less number of effective features of data set and the most appropriate topology for internal connections. The performance of the proposed algorithm is evaluated using the 2-Dimensional neutronic diffusion code MUDICO-2D to obtain the data required for the training of the neural networks. Simulation results demonstrate the effectiveness and the notability of the proposed algorithm comparing with Trainlm-LM, quasi-Newton (Trainbfg-BFGS), and Resilient Propagation (trainrp-RPROP) algorithms.

Surrogate Model of Predicting Eigenvalue and Power Distribution by Convolutional Neural Network

“…The linearized parameter or macro data in the core are used as the input. Early examples of research into the model include the prediction of power peak factor (Mazrou and Hamadouche, 2004;Souza and Moreira, 2006;Niknafs et al, 2010;Saber et al, 2015), eigenvalue (Mazrou and Hamadouche, 2004;Saber et al, 2015), departure from nucleate boiling ratio (Lee and Chang, 2003), and core reload program (Kim et al, 1993a;Kim et al, 1993b;Hedayat et al, 2009). However, previous studies with the MLP model have failed to find any link between the input data and the environment.…”