Correlating Thermal Conductivity of Pure Hydrocarbons and Aromatics via Perceptron Artificial Neural Network Method

In this work, 954 experimental thermal conductivities for the neat hydrocarbons and aromatics were collected and fed to a feed-forward artificial neural network (ANN) model to correlate themwith a good level of accuracy. The performed statistical error analysis and comparison between the available correlations and group contribution methods revealed good accuracy of the proposed network. Based on the comparisons and statistical error analysis, the proposed ANN modelconsisted of three layers namely, input, hidden and output layers with 22 neurons in hidden layer leads to absolute average relative deviation percent (AARD%) of 0.2%.

کلیدواژه ها:

Thermal Conductivity ، Artificial Neural Network ، Critical Properties ، Hydrocarbons ، Aromatics