Estimation of flow properties in eccentric annulus using digital image processing and artificial intelligence techniques

In drilling operations estimation of flow properties such as flow pattern, liquid holdup, pressure drop and cutting concentration is beneficial in terms of cost, time and efficient usage of resources for well to be opened. There is a lack of research both for hydraulic behavior and for cutting transportation mechanism of two phase fluids in annular geometries. One of the aims of this study is to observe the pressure drop and flow patterns experimentally in two phase and multiphase flows in eccentric annulus. The second aim is to detect the liquid holdup and cutting concentration of these flows using digital image processing techniques. The last aim is to estimate the flow pattern, liquid holdup and pressure drop for two phase (air and water) flow in horizontal eccentric annulus. This is conducted by using artificial intelligence techniques rather than conventional mechanistic models. In this study nearest neighbor algorithm, artificial neural networks, and decision trees are used as artificial intelligence technique. Flow is generalized by representing it as superficial Reynolds numbers for both liquid and gas phase. The results showed that the back propagation neural network gives the best results for estimation models. In air and water flow, 7 flow patterns are estimated with an accuracy of 10%; and liquid holdup and pressure drop are estimated with an average error of 14.4% and 3.8% (0.0274 psi), respectively.