|
Development of Epsilon-insensitive smooth support vector regression forpredicting minimum miscibility pressure in CO2 flooding |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Shahram Mollaiy-Berneti 2. Mehdi Abedi-Varaki |
| Title | Development of Epsilon-insensitive smooth support vector regression forpredicting minimum miscibility pressure in CO2 flooding |
| Publisher | Research and Development Office, Prince of Songkla University |
| Publication Year | 2561 |
| Journal Title | Songklanakarin Journal of Science and Technology |
| Journal Vol. | 40 |
| Journal No. | 1 |
| Page no. | 53 |
| Keyword | CO2 flooding, minimum miscibility pressure, Epsilon-insensitive smooth support vector regression, feed-forward neural network, radial basis function network |
| URL Website | http://rdo.psu.ac.th/sjstweb/index.php |
| ISSN | 0125-3395 |
| Abstract | Successful design of a carbon dioxide (CO2) flooding in enhanced oil recovery projects mostly depends on accuratedetermination of CO2-crude oil minimum miscibility pressure (MMP). Due to the high expensive and time-consuming ofexperimental determination of MMP, developing a fast and robust method to predict MMP is necessary. In this study, a newmethod based on ?-insensitive smooth support vector regression (?-SSVR) is introduced to predict MMP for both pure andimpure CO2 gas injection cases. The proposed ?-SSVR is developed using dataset of reservoir temperature, crude oil compositionand composition of injected CO2. To serve better understanding of the proposed, feed-forward neural network and radial basisfunction network applied to denoted dataset. The results show that the suggested ?-SSVR has acceptable reliability androbustness in comparison with two other models. Thus, the proposed method can be considered as an alternative way to monitorthe MMP in miscible flooding process. |
