Developing an Artificial Intelligence Model to Predict Liquid Loading in Condensate Gas Wells

Liquid loading is a common issue for gas wells. Obviously better predictions of liquid loading will help operators in reducing costs less shutdowns and improve revenue more production. Several authors have introduced various mathematical equations to calculate the critical flow rate necessary to keep gas wells unloaded. This paper presents an Artificial Neural Network (ANN) model for predicting the minimum flow rate for continuous removal of liquids from the wellbore. The model is developed using field data from different gas wells. These data were used to train a three-layer back propagation (BP) neural network model. The model was tested against actual field data which was not used in the training phase. The results show that the developed model provides better predictions and higher accuracy than the published models. The present model provides prediction of the critical gas flow rates with mean square error of 8.61 and a correlation coefficient of 99.11%

کلیدواژه ها:

Liquid Loading ، Critical Rate ، Neural Network ، BP ، Intelligent Proxy