Modeling liquid rate through wellhead chokes using machine learning techniques

Mohammad-Saber Dabiri; Fahimeh Hadavimoghaddam; Sefatallah Ashoorian; Mahin Schaffie; Abdolhossein Hemmati-Sarapardeh

doi:10.1038/s41598-024-54010-2

Modeling liquid rate through wellhead chokes using machine learning techniques

Sci Rep. 2024 Mar 23;14(1):6945. doi: 10.1038/s41598-024-54010-2.

Authors

Mohammad-Saber Dabiri¹, Fahimeh Hadavimoghaddam², Sefatallah Ashoorian³, Mahin Schaffie⁴, Abdolhossein Hemmati-Sarapardeh^{5

6}

Affiliations

¹ Department of Petroleum Engineering, Shahid Bahonar University of Kerman, Kerman, Iran. m.s_dabiri97@yahoo.com.
² Ufa State Petroleum Technological University, Ufa, Russia, 450064.
³ Institute of Petroleum Engineering, School of Chemical Engineering, University of Tehran, P.O. Box: 11155-4563, Tehran, Iran.
⁴ Department of Petroleum Engineering, Shahid Bahonar University of Kerman, Kerman, Iran.
⁵ Department of Petroleum Engineering, Shahid Bahonar University of Kerman, Kerman, Iran. hemmati@uk.ac.ir.
⁶ State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum (Beijing), Beijing, China. hemmati@uk.ac.ir.

Abstract

Precise measurement and prediction of the fluid flow rates in production wells are crucial for anticipating the production volume and hydrocarbon recovery and creating a steady and controllable flow regime in such wells. This study suggests two approaches to predict the flow rate through wellhead chokes. The first is a data-driven approach using different methods, namely: Adaptive boosting support vector regression (Adaboost-SVR), multivariate adaptive regression spline (MARS), radial basis function (RBF), and multilayer perceptron (MLP) with three algorithms: Levenberg-Marquardt (LM), bayesian-regularization (BR), and scaled conjugate gradient (SCG). The second is a developed correlation that depends on wellhead pressure (P_wh), gas-to-liquid ratio (GLR), and choke size (D_c). A dataset of 565 data points is available for model development. The performance of the two suggested approaches is compared with earlier correlations. Results revealed that the proposed models outperform the existing ones, with the Adaboost-SVR model showing the best performance with an average absolute percent relative error (AAPRE) of 5.15% and a correlation coefficient of 0.9784. Additionally, the results indicated that the developed correlation resulted in better predictions compared to the earlier ones. Furthermore, a sensitivity analysis of the input variable was also investigated in this study and revealed that the choke size variable had the most significant effect, while the P_wh and GLR showed a slight effect on the liquid rate. Eventually, the leverage approach showed that only 2.1% of the data points were in the suspicious range.

Keywords: Adaboost-SVR; Choke modeling; Correlation development; Liquid rate of two-phase flow; Machine learning; Wellhead chokes.