Application of artificial neural networks modelling to spray impingement heat transfer

Abstract

Artificial neural networks (ANN) models were developed and applied to water spray cooling heat flux predictions. The model was applied to all the three regimes of heat transfer, namely nucleate boiling (where surface temperature is less than the one at critical heat flux), transition (where the surface temperature is less than the Leidenfrost temperature) and the film boiling (where the wall temperature is greater than the Leidenfrost temperature). The ANN model is well trained and proves to be an alternative numerical modelling technique to computational fluid dynamics (CFD) with numerical predictions comparable to the CFD predictions, but in real time mode.