Development of an accurate method to prognosticate choke flow coefficients for natural gas flow through nozzle and orifice type chokes

One of the main components in oil and gas production system is choke valve. The choke valve role is maintaining sufficient back pressure to prevent water gas coning and formation damage and also stabilizing fluid flow to reach the optimum production scenario. Chokes can be employed either on surface or subsurface to control the fluid flow characteristics to the downstream processing facilities such as flow rate, pressure, and velocity. Malfunction of choke may results in severe damages in safety, facilities, and environment. In this study, a rigorous method based on artificial intelligence is developed to predict the choke flow coefficient for subsonic natural gas flow through nozzle and orifice type chokes. Reynolds number and ratio of choke diameter to pipe diameter was utilized as input parameters. The method used in this study is radial basis function neural network coupled with genetic algorithm. The results showed great agreement with experimental data. In addition, the proposed method was compared with classic correlations. This comparison demonstrated the robustness and superiority of the GA-RBF model. (C) 2015 Elsevier Ltd. All rights reserved.