Optimization of an Oil Production System using Neural Networks and Genetic Algorithms

This paper proposes an optimization strategy which is based on neural networks and genetic algorithms to calculate the optimal values of gas injection rate and oil rate for oil production system. Two cases are analyzed: a) A single well production system and b) A production system composed by two gaslifted wells. For both cases an objective function is maximized to reduce production cost. The proposed strategy shows the ability of the neural networks to approximate the behavior of an oil production system and the genetic algorithms to solve optimization problems when a mathematical model is not available. Keywords-- Genetic algorithms, injection gaslift, neural network, optimization, oil production system, perceptron multilayer.

• Type: Journal
• Year: 2009
• Where: EUSFLAT
• Authors: Guillermo Jimenez de la Cruz, Jose A. Ruz-Hernandez, Evgen Shelomov, Ruben Salazar-Mendoza
• Keywords: EUSFLAT 2009, Fuzzy Logic, Genetic Algorithms, Neural Network, Production System