Critical heat flux prediction for safety analysis of nuclear reactors using machine learning

Critical Heat Flux (CHF) prediction is vital for pressurized water reactors because it is a crucial metric for nuclear power plants' economic effectiveness and reliability. It is also essential for the safety analysis of nuclear reactors as it is a limiting factor for the design and operation of nuclear power plants. Due to absence of no deterministic theory exists on its predictions, the method of predicting accurate CHF is not straight forward. This paper develops an intelligent tool for CHF prediction that covers a wide range of pressure, mass flowrate, and thermal flux. Two machine learning (ML) techniques, namely random forest and artificial neural networks, are used to predict CHF. A new dataset is developed from literature, covering a wide range of two-phase flow operating conditions to train and test the model. Then both ML techniques are compared with the widely used look-up table method for predicting CHF. The results show the superior predicting capabilities of both ML techniques, especially deep neural networks (DNN), over the conventional method. Parametric trends are also compared among these techniques. Furthermore, it can also be used as an online monitoring tool for reactor cores of nuclear power plants to predict extreme conditions.