In the paper, two tools are used for estimation of second virial coefficient for gases and the obtained results are compared with the experimental data. The first tool is the computer program for estimation of second and third virial coefficients for gases and gas mixtures from basic properties of components. The computer program incorporates two empirical methods, the Tsonopoulos method to estimate second virial coefficients for nonpolar to polar pure gases and gas mixtures, and the method of Orbey and Vera to estimate third virial coefficients for nonpolar pure gases and gas mixtures. The second tool is the artificial neural network model (ANN) for correlation and prediction of second virial coefficients for gases. The neural network model was developed with the training variables: critical temperature, critical pressure, critical volume, acentric factor, dipole moment and temperature with the learning method back propagation of errors according to the best prediction error. The target variable was the second virial coefficient of gas. The neural network model has architecture (6,10,4,1). The training error was 0.3%. The network predicts the second virial coefficient with the average prediction error of 1.3%. The second virial coefficients for twenty gases are estimated with both tools. The comparison of results with experimental data shows that the computer program based on empirical methods, and the neural network model are appropriate tools for second virial coefficient prediction for gases, but more accurate results are obtained with the neural network model which gives good predictions of second virial coefficients for every gas.

The Kohonen neural networks were chosen to prepare a relevant model for fast selection of the most suitable phase equilibrium method(s) to be used in efficient vapor-liquid chemical process design and simulation. They were trained to classify the objects of the study (the known physical properties and parameters of samples) into none, one or more possible classes (possible methods of phase equilibrium) and to estimate the reliability of the proposed classes (adequacy of different methods of phase equilibrium). Out of the several ones the Kohonen network architecture yielding the best separation of clusters was chosen. Besides the main Kohonen map, maps of physical properties and parameters, and phase equilibrium probability maps were obtained with horizontal intersections of the neural network. A proposition of phase equilibrium methods is represented with the trained neural network.

In the paper Kohonen neural network is described as an alternative tool for a fast selection of the most suitable physical property estimation method to be used in efficient chemical process design and simulation. Kohonen neural networks are trained to suggest the appropriate method of phase equilibrium estimation on the basis of known physical properties of samples (objects of the study). In other words, they classify the objects into none, one or more possible classes (possible methods of phase equilibrium) and estimate the reliability of the proposed classes (adequacy of different methods of phase equilibrium). Kohonen map with almost clearly separated clusters of vapor, vapor/liquid and liquid phase regions and 15 probability maps for each of the specific phase equilibrium method, were obtained. The analysis of the results confirmed the hypothesis that the use of Kohonen neural networks for separation of the classes was correct.

In the paper Kohonen neural network as an alternative tool for fast selection of suitable physical property estimation method that is very important for efficient chemical process design and simulation is described. Neural networks should advice appropriate methods of phase equilibrium estimation on the basis of known physical properties. In other words, they should classify objects into none, one or more possible classes (possible methods of phase equilibrium) and estimate the reliability of the proposed classes (adequacy of different methods of phase equilibrium). From among several different artificial neural networks, Kohonen neural networks were chosen as the most appropriate for the specific problem. Probability maps for each specific phase equilibrium method were obtained as a result. The analysis of the results confirmed that the hypothesis to use Kohonen networks for separation of the classes was correct.

In this article an expert system called PHYP (PHYsical Properties) is described which aids engineers in the selection of an appropriate vapour-liquid equilibrium (VLE) method when performing various process calculations. Test examples demonstrate the ability of the expert system to solve problems from the field of phase equilibria in the shortest way without redundant questions to the user giving the results expected. PHYP was compared with the same purpose expert system CONPHYDE when solving, the same classification problems. For final solution, PHYP needs less user's assertions because of its smaller and more efficient decision tree. The expert system PHYP was generated by an automatic expert system shell, Assistant Professional. This way of building expert systems is much more efficient than development of a classic expert system like CONPHYDE which needs decision rules formulated by hand to be built into its inference network.