Title: Optimisation of gas lift performance using artificial neural network

Authors: Ahmed A. Elgibaly; Mohsen Elnoby; Moataz Eltantawy

Addresses: Faculty of Petroleum and Mining Engineering, Suez University, Egypt ' Faculty of Engineering, Future University, Cairo, Egypt ' Western Desert Petroleum Company, Alexandria, Egypt

Abstract: Gas lift is one of the most widespread methods of artificial lift technologies used when wells' production rate declines. Gas is employed to maintain the production by injecting gas into the tubing through a gas lift orifice. Lifting costs are generally low. However, capital costs of compression are very high, so it is necessary to optimise gas lift wells. In this paper, conventional nodal analysis models were used to predict the optimisation parameters based on wells system parameters. Artificial neural network (ANN) models were also used based on gas lift databases. ANN models were trained then tested against nodal analysis models. Also, this paper presents a new theory about the relative importance of gas lift system inputs on output parameters of gas lift system. [Received: June 9, 2020; Accepted: August 7, 2020]

Keywords: gas lift performance and optimisation; prediction; artificial neural network; ANN; optimum oil rate; optimum gas lift rate; Pipesim; MATLAB.

DOI: 10.1504/IJOGCT.2021.117160

International Journal of Oil, Gas and Coal Technology, 2021 Vol.28 No.1, pp.1 - 27

Received: 09 Jun 2020
Accepted: 07 Aug 2020
Published online: 19 Aug 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article