Estimation of Multiphase Flow Properties using Computational Intelligence Models

Estimation of flow properties is essential in terms of the efficient usage of resources in drilling operations. Meanwhile, hydraulic characteristics of two phase fluids in annular geometries are not studied thoroughly. In this study, the flow patterns and liquid holdup characteristics of liquid-gas flow is analyzed using experimental data obtained from an eccentric pipe configuration. A high speed digital camera is used for recording the flow; in addition liquid holdup values are calculated using digital image processing techniques instead of empirical correlations or mechanistic measurements. At the same time through the acquired images, corresponding flow patterns are observed. Using the acquired images, estimation models are developed for air-water flow in horizontal eccentric annulus. This is conducted by using computational intelligence rather than conventional mechanistic models. The chosen models are nearest neighbor, backpropagation, decision trees and SVM. Input attributes are superficial Reynolds numbers for both liquid and gas phase. The output is the classified flow pattern and the liquid holdup value. SVM model turned out to be the best estimator for flow pattern identification process (%92.49 success rate for classifying 7 different flow patterns) whereas regression decision tree had the best performance for liquid holdup determination (RMSE of 0.0777).