Prediction Study on PCI Failure of Reactor Fuel Based on a Radial Basis Function Neural Network

Abstract

Pellet-clad interaction (PCI) is one of the major issues in fuel rod design and reactor core operation in water cooled reactors. The prediction of fuel rod failure by PCI is studied in this paper by the method of radial basis function neural network (RBFNN). The neural network is built through the analysis of the existing experimental data. It is concluded that it is a suitable way to reduce the calculation complexity. A self-organized RBFNN is used in our study, which can vary its structure dynamically in order to maintain the prediction accuracy. For the purpose of the appropriate network complexity and overall computational efficiency, the hidden neurons in the RBFNN can be changed online based on the neuron activity and mutual information. The presented method is tested by the experimental data from the reference, and the results demonstrate its effectiveness.

A Constraint-Based Random Search Algorithm for Optimizing Neural Network Architectures and Ensemble Construction in Detecting Loss of Coolant Accidents in Nuclear Power Plants

“…Souza et al [12] developed a RBF network capable of online identifying the accidental dropping of the control rod at the reactor core of a pressurised water reactor. Wei X et al [13] developed self-organizing radial basis function (RBF) networks to predict fuel rod failure of nuclear reactors. Santhosh et al [3] trained a neural network on a transient dataset generated using RELAP5-3D to detect the size of a break, the location of the break in the PHT with the availability of the emergency core cooling system (ECCS) which automatically shuts down the reactor to prevent a subsequent accident.…”

A constraint-based genetic algorithm for optimizing neural network architectures for detection of loss of coolant accidents of nuclear power plants

“…Baraldi P et al [12] proposed an ensemble of fuzzy c-mean classifiers to identify the faults in the feed water system of a boiling water reactor. Wei X et al [57] developed self-organizing RBF networks to predict fuel rod failure of nuclear reactors. Souza [48] developed a RBF network capable of online identifying the accidental dropping of the control rod at the reactor core of a pressurised water reactor.…”