A neural network to predict reactor core behaviors
摘要
The global fuel management problem in BWRs（Boiling Water Reactors） can be understood as a very complex optimization problem,where the variables represent design decisions and the quality assessment of each solution is done through a complex and computational expensive simulation.This last aspect is the major impediment to perform an extensive exploration of the design space,mainly due to the time lost evaluating non promising solutions.In this work,we show how we can train a Multi-Layer Perceptron（MLP） to predict the reactor behavior for a given configuration.The trained MLP is able to evaluate the configurations immediately,thus allowing performing an exhaustive evaluation of the possible configurations derived from a stock of fuel lattices,fuel reload patterns and control rods patterns.For our particular problem,the number of configurations is approximately 7.7×1010;the evaluation with the core simulator would need above 200 years,while only 100hours were required with our approach to discern between bad and good configurations.The later were then evaluated by the simulator and we confirm the MLP usefulness.The good core configurations reached the energy requirements,satisfied the safety parameter constrains and they could reduce uranium enrichment costs.