Prediction of thermal conductivity of ethylene glycol–water solutions by using artificial neural networks

The objective of this study is to develop an artificial neural network (ANN) model to predict the thermal conductivity of ethylene glycol–water solutions based on experimentally measured variables. The thermal conductivity of solutions at different concentrations and various temperatures was measured using the cylindrical cell method that physical properties of the solution are being determined fills the annular space between two concentric cylinders. During the experiment, heat flows in the radial direction outwards through the test liquid filled in the annual gap to cooling water. In the steady state, conduction inside the cell was described by the Fourier equation in cylindrical coordinates, with boundary conditions corresponding to heat transfer between the solution and cooling water. The performance of ANN was evaluated by a regression analysis between the predicted and the experimental values. The ANN predictions yield R2 in the range of 0.9999 and MAPE in the range of 0.7984% for the test data set. The regression analysis indicated that the ANN model can successfully be used for the prediction of the thermal conductivity of ethylene glycol–water solutions with a high degree of accuracy.