| Summary: | Successful design of a carbon dioxide (CO2) flooding in enhanced oil recovery projects mostly depends on accurate
determination of CO2-crude oil minimum miscibility pressure (MMP). Due to the high expensive and time-consuming of
experimental determination of MMP, developing a fast and robust method to predict MMP is necessary. In this study, a new
method based on ε-insensitive smooth support vector regression (ε-SSVR) is introduced to predict MMP for both pure and
impure CO2 gas injection cases. The proposed ε-SSVR is developed using dataset of reservoir temperature, crude oil composition
and composition of injected CO2. To serve better understanding of the proposed, feed-forward neural network and radial basis
function network applied to denoted dataset. The results show that the suggested ε-SSVR has acceptable reliability and
robustness in comparison with two other models. Thus, the proposed method can be considered as an alternative way to monitor
the MMP in miscible flooding process.
|
|---|
