Use of neural networks for prediction of vapor/liquid equilibrium K values for light-hydrocarbon mixtures

Equilibrium ratios play a fundamental role in the understanding of phase behavior of hydrocarbon mixtures. They are important in pre-dieting compositional changes under varying temperature and pressure in reservoirs, surface separators, and production and transportation facilities. In particular, they are critical for reliable and successful compositional reservoir simulation. This paper presents a new approach for predicting K values with neural networks (NN's). The method is applied to binary and multicomponent mixtures, and K-value prediction accuracy is on the order of the traditional methods. However, computing speed is significantly faster.