Model identification for gas condensate reservoirs by using ANN method based on well test data

The well testing technique has been frequently used in order to identify hydrocarbon reservoir models and estimate the associated parameters such as permeability, skin factor, etc. The analysis of well test data acquired from gas condensate reservoirs is basically different from oil and dry gas reservoirs often exhibiting a complex behavior due to the formation of condensate inside the reservoir. The first step in well test analysis is the detection of reservoir model and its boundaries usually performed through trial-and-error procedures. Previous investigations indicate that the radial composite model is the best feasible model for well test analysis of gas condensate reservoirs. The radial composite model refers to those reservoirs consisting of two separate regions: (1) a circular inner zone with the well at the center, and (2) an infinite outer zone. The best multi-layer perceptron (MLP) configuration is also selected through evaluating the accuracy criteria of various developed MLP networks i.e., measuring the mean relative (MRE) and mean square errors (MSE). The total classification accuracies (TCAs) of two methods used in this study indicate that the coupled MLP clustering model (with a TCA equal to 93.3%) has a better performance than that of the single MLP (with a TCA of 88.65%).