A feedforward artificial neural network was used to correlate 956 experimentally measured thermal diffusivity
data of hydrocarbons and aromatics. A network consisted of one input, one hidden and one output layers is used to
estimate the thermal diffusivity of the hydrocarbons and aromatics. The obtained results revealed that using a
feedforward artificial neural network model containing 19 neurons in the hidden layer and tansig and purelin as
transfer functions in the hidden and output layers, respectively, led to an overall average absolute relative deviation
percent of 0.73%, which is an acceptable level of accuracy for a predictive model.
