Neural Networks and Evolutionary Algorithms for the Prediction of Thermodynamic Properties for Chemical Engineering

In this paper 1 we report results for the prediction of thermo-dynamic properties based on neural networks, evolutionary algorithms and a combination of them. We compare backpropagation trained networks and evolution strategy trained networks with two physical models. Experimental data for the enthalpy of vaporization were taken from the literature in our investigation. The input information for both neural network and physical models consists of parameters describing the molecular structure of the molecules and the temperature. The results show the good ability of the neural networks to correlate and to predict the ther-modynamic property. We also conclude that backpropagation training outperforms evolutionary training as well as simple hybrid training.