Summary
Equilibrium ratios play a fundamental role in the understanding of phase behavior of hydrocarbon mixtures. They are important in predicting compositional changes under varying temperatures and pressures conditions in reservoirs, surface separators, 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 using Neural Networks (NN). The method is applied to binary and multicomponent mixtures, K-values prediction accuracy is in the order of the tradition methods. However, computing speed is significantly faster.
Introduction
Equilibrium rations, more commonly known as K-values, relate the vapor mole fractions (yi), to the liquid mole fraction (xi) of a component (i) in a mixture,
(1)
In a fluid mixture consisting of different chemical components, K-values are dependent on mixture pressure, temperature, and composition of the mixture.
There are a number of methods for predicting K-values, basically these methods compute K-values explicitly or iteratively. The explicit methods correlate K-values with components parameters (i.e. critical properties), mixtures parameters (i.e. convergence pressure). Iterative methods are based on the equation of state (EOS) and are, usually, tuned with binary interaction parameters.
Literature search and experience in the phase behavior of hydrocarbon systems, have shown that current explicit methods are not accurate because they neglect compositional affects. EOS approach requires extensive amount of computational time, may have convergence problems, and must be supplied with good binary interaction parameters. In compositional reservoir simulation where million of K-values are required, the method becomes time consuming and adds to the complexity of simulation studies making some of them impractical.
Neural Networks (NN) are emerging technology that seems to offer two advantages, fast computation and accuracy. The objective of this paper is to show the potential of using NN for predicting K-values. Different NN where trained using the Scaled Conjugate Gradient (SCG), and where used to predict the K-values for binary and multicomponent mixtures.