PVT DATA-ANALYSIS USING NEURAL-NETWORK MODELS

PVT data analysis is performed for pure gases and vapors using neural network based models. The resulting equations of state (EOS) are explicit forms of the compressibility factor as a function of the reduced temperature and pressure, and the acentric factor. In order to represent the whole domain of pressure and temperature, two EOS have been developed, one equation specifically covering the critical region. These two equations were obtained by fitting a large number of experimental data points (about 1000 and 1500, respectively) characterizing the behavior of several pure components (5 and 8, respectively). The EOS have been applied successfully to various other components and were found to give accurate predictions for a reduced pressure as high as 10. Derivation of the fugacity coefficient is also presented.