An approach based on neural networks for gas lift optimization

Abstract

Using a model-based optimization, a neural network model is used to compute the optimal values of gas injection rate and oil rate of a gas lift production system. Two cases are analyzed: a) A single well production system and b) A production system composed by two gas lifted wells. For both cases minimizing the objective function of the proposed strategy shows the ability of the neural networks to approximate the behavior of an oil production system and to solve optimization problems when a mathematical model is not available. The results obtained via our approach based on neural networks for gas lift optimization are best than other approaches based on linear programming and non linear programing. © 2010 Springer-Verlag Berlin Heidelberg.