Prediction of dynamic heat transfer of 2-D bubble column using ANNs

摘要

The instantaneous local heat transfer rates in a 2-D column were measured by using a hotwire probe. An artificial neural network (ANN) was applied to correlate the flucturation of heat transfer rates with dynamic motions of bubble and liquid. The optimal structure of the artificial neural network was determined for the prediction of heat transfer rates. The trained ANN mode gives a good prediction of dynamic heat transfer with errors of less than 5%.