Neural networks versus Linear and Sequential Programming for Gas Lift Optimization in a two oil wells system

Author

Salazar-Mendoza, R. ; Jimenez de la C, G. ; Ruz-Hernandez, J.A.

Author_Institution

Inst. Mexicano del Petroleo, Campeche, Mexico

fYear

2009

fDate

14-19 June 2009

Firstpage

2756

Lastpage

2763

Abstract

Using a model-based optimization, a neural network model is developed to calculate 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. The results were compared with the linear and sequential programming for gas lift optimization. For both cases minimizing the objective function 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.

Keywords

linear programming; natural gas technology; neural nets; production engineering computing; gas injection rate; gas lift optimization; linear programming; mathematical model; model-based optimization; neural network model; objective function; oil production system; oil rate; oil wells system; sequential programming; single well production system; Costs; Linear programming; Neural networks; Particle separators; Performance evaluation; Petroleum; Production systems; Routing; Testing; Transmitters;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2009. IJCNN 2009. International Joint Conference on

Conference_Location

Atlanta, GA

ISSN

1098-7576

Print_ISBN

978-1-4244-3548-7

Type

conf

DOI

10.1109/IJCNN.2009.5179056

Filename

5179056