Neural network analysis of boiling heat transfer in pool boiling of single component liquids

Abstract

Paper presented at the 7th International Conference on Heat Transfer, Fluid Mechanics and Thermodynamics, Turkey, 19-21 July, 2010.

The objective of this study is to use Artificial Neural Network for boiling heat transfer at various operating conditions using the experimental data for different liquids. For training the networks, the standard feed forward back propagation algorithm was used and several types of structures were tested to obtain the most suitable network for the prediction of boiling curves. In this study four network structures were used with the variation of neurons and hidden layers. The suitability of the network depends upon the type of system and data chosen for training. It was observed that the predicted results were close to the actual experimental data for all liquids. The predictability of the network is extremely good if the training data are chosen appropriately. When all the data of the system were considered together for the training of the network, the performance was extremely good. The prediction of ANN results was very close to the actual experimental values with a mean absolute relative error less than 2.0 %.