An Accuracy Comparison Between Artificial Neural Network and Some Conventional Empirical Relationships in Estimation of Relative Permeability

Author: Khaz'ali A. R.  

Publisher: Taylor & Francis Ltd

ISSN: 1091-6466

Source: Petroleum Science and Technology, Vol.29, Iss.15, 2011-01, pp. : 1603-1614

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

The reservoir rock relative permeability values are measured through the Special Core Analysis Laboratory (SCAL) experiments. Because SCAL experiments are expensive and time-consuming, usually a mathematical model is developed to estimate the relative permeability values whereas no SCAL test has been run. The authors compare the accuracy of the Artificial Neural Network (ANN) and some empirical equations in estimating the two-phase relative permeability values. The final results indicate that ANN is a much more accurate approach than the empirical equations.