Developing correlation for prediction of DNB heat flux in subcooled flow boiling using artificial neural network-aided framework

Nguyen, T.-B.; Hirose, Yoshiyasu  ; Satou, Akira ; Abe, Satoshi  ; Shibamoto, Yasuteru 

To ensure light water reactor safety, accurate Departure from Nucleate Boiling (DNB) heat flux prediction is essential but remains challenging. This study used an Artificial Neural Network (ANN) to analyze six dimensionless variables, identifying mass flux, channel diameter, and subcooling as the most critical parameters. The resulting simplified correlation outperforms existing models in robustness, simplicity, and applicability across diverse operating conditions.