Gasified fluids are preferred for achieving underbalanced conditions for drilling operations. Proper estimation of hydraulic requirements for such fluids becomes a more important issue for trajectories with highly-inclined angles and longer sections. Flow of two-phase fluids through circular pipes has, relatively, been well understood. However, flow of twophase fluids through annular sections is still a challenge. Many attempts have been conducted to model two-phase flow through annular geometries, but still there exists an uncertainity at this area. This study approaches to estimate the flow pattern and frictional pressure losses of two-phase fluids flowing through horizontal annular geometries using Artificial Neural Networks (ANN) rather than proposing a mechanistic model. Experimental data collected from experiments conducted at Middle East Technical University, Petroleum & Natural Gas Engineering Multiphase Flow Loop, as well as from literature in order to train the ANN. Flow is characterized using superficial Reynolds numbers for both liquid and gas phase for simplicity. The results showed that ANN could estimate flow patterns with a high accuracy (error is less than ± 5%), and frictional pressure losses with an error less than ± 10%. It is also observed that proper selection of ANN is important for accurate estimations.
Two-phase flow is the flow phenomenon of two different fluid phases flowing simultaneously through a conduit. Generally, liquid and gas phases are the components of this commonly encountered flow type. As liquid and gas phases are flowing through a conduit, different flow patterns develop as a function of velocities of both phases as shown in figure-1. Since 1950's, the flow problem of two-phase fluids has been the subject of research in many different engineering practices.
In petroleum industry, the applications of two-phase flow start from drilling and continue till the refining process. In depleted or mature reservoirs, underbalanced drilling techniques are required in order to prevent any possible formation damages while drilling injection/production wells. Thus, in order to determine the design parameters for such wells accurately, the flow behavior of aerated fluids should be well known. Another important usage of two-phase flow takes place during the transportation of the produced oil and gas via the pipelines. Since the oil and gas fields are mainly in remote onshore areas or in offshore, the pipeline systems are of great importance. Reliable engineering calculations should be carried out as the overall distances of these pipeline systems are considered.
With the improving technology, the innovative methods demand for the better understanding of two-phase flow systems. As in case of underbalanced drilling of extended reach wells, the flow problem becomes more complicated when compared with single-phase flow of drilling mud in conventional drilling.
When this wide range of application of two-phase flow in petroleum engineering is considered, the appropriate determination of flow parameters of two-phase fluid systems becomes highly important. The focus of this study is to determine flow patterns and frictional pressure losses of aerated fluid flow through horizontal annuli using artificial neural networks (ANN).
