Artificial neural network based prediction of heat transfer in a vertical thermosiphon reboiler

Abstract

Paper presented at the 6th International Conference on Heat Transfer, Fluid Mechanics and Thermodynamics, South Africa, 30 June - 2 July, 2008.

The present study deals with the prediction of heat transfer coefficients for water and benzene using ANN in a vertical thermosiphon reboiler. The experimental data from the literature were used for training of feed forward artificial neural network with error back propagation technique. Different training algorithms have been applied with different hidden layers and nodes to train the network. It was observed that the heat transfer coefficients predicted was close to the experimental data within the maximum error of ± 20 %. If more exhaustive input data were fed then error would have become still lesser. It has been observed that some algorithms are very efficient with respect to training time in comparison to other algorithms.