Mariea MARCU


In the paper, artificial neural networks and a regression equation were used to approximate the gas-lift performance curve in order to compare their performances. Also, a sensitivity study of the artificial neural network performances to the variation of its geometric parameters and the activation function was carried out. The data sets used to build the gas-lift performance curve have different characteristics identified by the number of data points and the presence or absence of the outliers. In all cases, the performances of the artificial neural network were better than those of the regression equation. However, if the data set contains many outliers, the artificial neural network, although it has smaller errors, tends to build an abnormal curve. 

Full Text:



Alkinani, H.H, Al-Hameedi, A.T.T., Dunn-Norman, Sh.., Flori. E.R., Alsaba, M.T., Amer, A.S., Application of Artificial Neural Networks in the Petroleum Industry. A Review, Paper Number SPE-195072-MS presented at the SPE Middle East Oil and Gas Show and Conference, Manama, Bahrain, 2019.

Behjoomanesh,M., Keyhani, M., Ehsan Ganji-Azad, Izadmehr, M., Riahi, S., Assessment of total oil production in gas lift process of wells using Box-Behnken design of experiments in comparison with traditional approach. Journal of Natural Gas Science and Engineering, Vol. 27, pp.1455-1461, 2015.

Li, H., Yu, H., Cao, N., Tian, H., Cheng, S., Applications of Artificial Intelligence in Oil and Gas Development, Archives of Computational Methods in Engineering, Vol. 28, pp.937–949, 2021.

Money, C., G., Adewumi, A.O., Obolo., M.O., Oil Well Characterization and Artificial Gas Lift Optimization using Neural Network combined with Genetic Algorithm, Discrete Dynamics in Nature and Society, Hindawi Publishing Corporation, Article ID 289239, 10 pp., 2014.

Namdar, H., Developing an Improved approach to solving a new gas lift optimization problem, Journal of Petroleum Exploration Production and Technology, No.9, pp.2965-2978, 2019.

Rashid, K., Bailey, W., Couet, B., A Survey of Methods for Gas lift Optimization, Modeling and Simulation in Engineering, ID 516807, 16 pp, 2012.

Tavakoli, R., Daryasafar, A, Keyhani, M., Behjoomanesh, M., Optimization of Gas Lift Allocation using Different Models, Recent Adv. Petrochem. Sci., Vol.1, No.2, pp.23-29, 2017.


  • There are currently no refbacks.