Prediction of the evolution of the nuclear reactor core parameters using artificial neural network

Abstract

The main aim of the research was to design, implement and investigate an Artificial Neural Network (ANN) to predict the behavior of selected parameters of a nuclear reactor core. The studied core was a typical power-generating Pressurized Water Reactor (PWR). The PARCS v3.2 nodal-diffusion core simulator was used to generate training and validation data. The ANN was implemented using Python 3.8 code with Google’s TensorFlow 2.0 library. The effort was based to a large extent on the process of automatic transformation of generated data, which was later used in the process of the ANN development. Various ANN architectures were studied to obtain better accuracy of prediction. In this study, a special focus was put on the prediction of the fuel cycle length for a given core loading pattern. In addition, a conversion of the input data was applied, allowing for very good accuracy of the cycle length prediction ($>99$%).