Performance evaluation of nano refrigerant operated thermosyphon using artificial neural network technique

Abstract

The present work is focused on evaluating the performance of a thermosyphon with internal fin and internal cut arrangement employing a mixture of nano particle Al2O3 and refrigerant R134a using artificial neural network. Using feed forward back propagation algorithm technique has used the data from the experimental studies to predict the thermosyphon performance. The input parameters to the algorithm were heat input, heat flux and cooling water temperatures and the output parameter predicted by the algorithm is heat transfer coefficient. It was inferred from the analysis that the predicted values of heat transfer coefficient were close to the actual experimental data. The artificial neural network model predicted the values in close agreement with the experimental values with an error of ±3%.