Back propagation neural network-based prediction of critical heat flux in vertical and inclined tubes

Due to their unique advantages, offshore floating nuclear power plants have broad application prospects. Unlike land-based reactors, it is essential to conduct in-depth research on the characteristics of Critical Heat Flux (CHF) under marine conditions, such as inclination, heaving, and rolling. Artificial neural networks renowned for strong fitting, prediction, classification capabilities, and robustness, are widely used in fields such as economics and engineering. This paper employs a back propagation neural network to predict the CHF of vertical and inclined tubes, defining an inclination factor—CHFR to quantify the impact of inclination on CHF. It also reveals the effects of pressure, mass flow rate, thermal equilibrium quality, and inclination angle on CHFR. The BP (Back Propagation)neural network-based method for predicting inclined CHF demonstrates high accuracy. The results of this study offer valuable insights for ensuring the safe operation of reactors under marine conditions.