Modeling liquid rate through wellhead chokes using machine learning techniques
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 we...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-54010-2 |
| _version_ | 1827310230489268224 |
|---|---|
| author | Mohammad-Saber Dabiri Fahimeh Hadavimoghaddam Sefatallah Ashoorian Mahin Schaffie Abdolhossein Hemmati-Sarapardeh |
| author_facet | Mohammad-Saber Dabiri Fahimeh Hadavimoghaddam Sefatallah Ashoorian Mahin Schaffie Abdolhossein Hemmati-Sarapardeh |
| author_sort | Mohammad-Saber Dabiri |
| collection | DOAJ |
| description | 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 (Pwh), gas-to-liquid ratio (GLR), and choke size (Dc). 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 Pwh 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. |
| first_indexed | 2024-04-24T19:56:21Z |
| format | Article |
| id | doaj.art-c4f8b4a2690141e2b9f3bb83c4ed29d9 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T19:56:21Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-c4f8b4a2690141e2b9f3bb83c4ed29d92024-03-24T12:19:24ZengNature PortfolioScientific Reports2045-23222024-03-0114111910.1038/s41598-024-54010-2Modeling liquid rate through wellhead chokes using machine learning techniquesMohammad-Saber Dabiri0Fahimeh Hadavimoghaddam1Sefatallah Ashoorian2Mahin Schaffie3Abdolhossein Hemmati-Sarapardeh4Department of Petroleum Engineering, Shahid Bahonar University of KermanUfa State Petroleum Technological UniversityInstitute of Petroleum Engineering, School of Chemical Engineering, University of TehranDepartment of Petroleum Engineering, Shahid Bahonar University of KermanDepartment of Petroleum Engineering, Shahid Bahonar University of KermanAbstract 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 (Pwh), gas-to-liquid ratio (GLR), and choke size (Dc). 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 Pwh 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.https://doi.org/10.1038/s41598-024-54010-2Wellhead chokesMachine learningChoke modelingCorrelation developmentLiquid rate of two-phase flowAdaboost-SVR |
| spellingShingle | Mohammad-Saber Dabiri Fahimeh Hadavimoghaddam Sefatallah Ashoorian Mahin Schaffie Abdolhossein Hemmati-Sarapardeh Modeling liquid rate through wellhead chokes using machine learning techniques Scientific Reports Wellhead chokes Machine learning Choke modeling Correlation development Liquid rate of two-phase flow Adaboost-SVR |
| title | Modeling liquid rate through wellhead chokes using machine learning techniques |
| title_full | Modeling liquid rate through wellhead chokes using machine learning techniques |
| title_fullStr | Modeling liquid rate through wellhead chokes using machine learning techniques |
| title_full_unstemmed | Modeling liquid rate through wellhead chokes using machine learning techniques |
| title_short | Modeling liquid rate through wellhead chokes using machine learning techniques |
| title_sort | modeling liquid rate through wellhead chokes using machine learning techniques |
| topic | Wellhead chokes Machine learning Choke modeling Correlation development Liquid rate of two-phase flow Adaboost-SVR |
| url | https://doi.org/10.1038/s41598-024-54010-2 |
| work_keys_str_mv | AT mohammadsaberdabiri modelingliquidratethroughwellheadchokesusingmachinelearningtechniques AT fahimehhadavimoghaddam modelingliquidratethroughwellheadchokesusingmachinelearningtechniques AT sefatallahashoorian modelingliquidratethroughwellheadchokesusingmachinelearningtechniques AT mahinschaffie modelingliquidratethroughwellheadchokesusingmachinelearningtechniques AT abdolhosseinhemmatisarapardeh modelingliquidratethroughwellheadchokesusingmachinelearningtechniques |