Artificial neural networks for spatial distribution of fuel assemblies in reload of PWR reactors

Edyene Oliveira; Victor Castro; Carlos Velasquez; Claubia Pereira

doi:10.15392/bjrs.v7i2B.770

Authors

Edyene Oliveira Universidade Federal de Minas Gerais
Victor Castro Universidade Federal de Minas Gerais
Carlos Velasquez Universidade Federal de Minas Gerais
Claubia Pereira Universidade Federal de Minas Gerais

DOI:

https://doi.org/10.15392/bjrs.v7i2B.770

Keywords:

Artificial Neural Networks, Computational Intelligence, Nuclear Reactors, PWR

Abstract

An artificial neural network methodology is being developed in order to find an optimum spatial distribution of the fuel assemblies in a nuclear reactor core during reloading. The main bounding parameter of the modeling was the neutron multiplication factor, k_eff. The characteristics of the network are defined by the nuclear parameters: cycle, burnup, enrichment, fuel type, and average power peak of each element. As for the artificial neural network, the ANN Feedforward Multi_Layer_Perceptron with various layers and neurons were constructed. Three algorithms were used and tested: LM (Levenberg-Marquardt), SCG (Scaled Conjugate Gradient) and BayR (Bayesian Regularization). The artificial neural network has implemented using MATLAB 2015a version. As preliminary results, the spatial distribution of the fuel assemblies in the core using a neural network was slightly better than the standard core.

Views: 185
PDF Downloads: 224

Downloads

Download data is not yet available.

References

AUGUSTO, C. S. P. JOÃO, NICOLAU, S. ANDRESSA, SCHIRRU, ROBERTO. PSO with Dynamic Topology and Random Keys method applied to Nuclear Reactor Reload, Brazil, 2015, Vol. 83, pp. 191-196.

BABAZADEH, DAVOOD, BOROUSHAKI, MEHRDAD, LUCAS CARO. Optimization Of Fuel Core Loading Pattern Design In: VVER Nuclear Power Reactors Using Particle Swarm Optimization (PSO), 2009, Iran, Elsevier, vol. 23, pp. 923-930.

CACUCI, D.G. Handbook of Nuclear Engineering, Springer Verlag, Alemanha, 2013.

CHAPOT, L. C. JORGE, SILVA, C. FEANNNDO, SCHIRRU, ROBERTO. A New Ap-proach to the Use Of Genetic Algorithms to Solve the Pressurized Water Reactor's Fuel Management Optimization Problem, Brazil, 1999, Pergamon, Vol. 26, pp. 641-651.

COCHRAN, Robert G. Tsoulfanidis, Nicholas. The Nuclear Fuel Cycle: Analysis and Man-agement, American Nuclear Society, 1999.

CHUNHUI DAI, XINYU WEI, YUN TAI, FUYU ZHAO, The Optimum Design of Power Distribution For Pressurized Water Reactor, China, 2012, Vol. 50, pp. 126-132.

DUDERSTADT, James and Louis J. Hamilton. Nuclear Reactor Analysis, Wiley, NY, 1976.

ERDOGAN, ADEM MELIH, GEC. A PWR Reload Optimization Code Using Artificial Neural Networks and Genetic Algorithms, Turkey, 2003, Elsevier, Vol. 30, pp. 35-53.

FARIA, EDUARDO FERNANDES, Otimização da Distribuição Espacial de Combustíveis Reprocessados Utilizando Técnicas de Redes Neurais, Dissertação, Ciências Técnicas Nucleares da Universidade Federal de Minas Gerais, Brazil, 1999.

FARIA, F. EDUARDO, PEREIRA, CLAUBIA. Nuclear Fuel Loading Pattern Optimization Using A Neural Network, Brazil, 2003, Pergamon, Vol. 30, pp. 603-613.

FOSTER, Artur R., Basic Nuclear Engineering, Third Edition, 1977.

GLADSTONE, Samuel. Ingenieria de Reactores Nucleares, Editorial Reverté, Barcelona, 1975.

GONZALVEZ, JOSÉ. Sensitivity study on e termining an efficient set of fuel assembly parameters in training data for designing of neural networks in hybrid genetic algorithms, Spain, 2005, Elsevier, Vol. 33, pp. 457-465.

HAYKIN, Simon. Neural Networks and Learning Machines, 3ª edição, New Jersey, Prentice Hall, 2009.

LEWIS, Elmer E. Fundamentals of Nuclear Reactor Physics, Academic Press, 1ª edição, 2008.

NICOLAU, S. ANDRESSA, SHIRRU, ROBERTO, LIMA, M. M.,ALAN. Nuclear Reactor Reload Using Quantum Inspired Algorithm, Brazil, 2012, Elsevier, Vol. 55, pp. 40-48.

OLIVEIRA, M. IONÁ, SCHIRRU, ROBERTO. Swarm Intelligence of Artificial Bees Applied To In-Core Fuel Management Optimization, Brazil, 2011, Vol. 38, pp. 1039-1045.

ORTIZ, J. JOSE, REQUENA, IGNACIO. Using A Multi-State Recurrent Neural Network To Optimize Loading Patterns In Bwrs, Spain, 2004, Elsevier, Vol. 31, pp. 789-803.

POURSALEHI, N, ZOLFAGHARI, MINUCHEHR. Multi-Objective Loading Pattern En-hancement Of PWR Based on the Discrete Firefly Algorithm, Teerã, Elsevier, 2012, Vol. 57, pp. 151-163.