Search

In order to fully study the influencing factors of asphaltene precipitation in CO2injection into shale reservoirs, this study is the first to use the modified Peng–Robinson equation of state (PR-EOS) considering fluid–solid interaction to study the effect of wettability on asphaltene precipitation. In this work, first, the PR-EOS is modified by adding a fluid–wall interaction term to consider the wettability effect, and critical properties of fluids in nanopores are incorporated. Then, the fugacity coefficients of fluid and gas calculated by the modified PR equation are coupled into the thermodynamic model of asphaltene precipitation in the shale reservoir. Subsequently, the proposed thermodynamic model is utilized to investigate the effects of wettability and CO2on asphaltene precipitation in a shale oil reservoir. The results reveal the following: (a) As the contact angle decreases, the asphaltene onset pressure will increase, and the amount of asphaltene precipitation will also increase. (b) The equilibrium system can be transformed from a three-phase system to a two-phase system by the wettability effect and confinement effect. (c) The wettability and CO2have a coupling effect on asphaltene precipitation of shale oil. When the contact angle is 120°, the mole fraction of CO2is 20%, and the lower asphaltene onset pressure (L-AOP) is 622.30 psi, which is close to the L-AOP without considering wettability and CO2(618.43 psi).

The initial productivity of oil wells is an important index in oilfield development. Due to the nonlinear relationship among the numerous affecting factors of productivity, productivity prediction methods based on seepage theory are difficult to characterize this nonlinear relationship. The machine learning method provides a novel theory to solve this problem. However, the data-driven machine learning method neglects the physical-based seepage theory. For balancing the advantage of the seepage model and the data-driven model, the productivity formula was used to guide the machine learning algorithm for achieving nonlinear regression in this study. Therefore, an innovative physics-guided eXtreme Gradient Boosting (XGBoost) trees algorithm was proposed to predict the initial productivity. The productivity formula was employed as the physical constraint and combined with the mean-square error (MSE) loss function of the XGBoost algorithm. A hyperparameter was introduced to balance the productivity formula and the MSE formula for constructing this adaptive physics-guided loss function. Moreover, the random subsampling cross-validation approach was adopted to train the XGBoost model. The grid search approach was introduced to optimize the hyperparameters of the model. The results show that based on the numerical simulator data, the initial productivity prediction accuracy of physics-guided XGBoost was verified as 94.67%, which was higher than the completely data-driven model. Moreover, the robustness of the novel adaptive physics-guided loss function for improving forecasting accuracy had been validated with sample sizes between 50 and 20000. By introducing the physics-guided sampling process and loss function, the applicability of the XGBoost algorithm has been extended to small sample conditions. Furthermore, the practical accuracy of physics-guided XGBoost was verified as 84.74% by 162 oil wells in the Penglai oilfield. Therefore, the application value of combining the physical knowledge with the XGBoost model has been confirmed in oilfield situations.

In order to fully investigate the pore-scale seepage mechanism for a two-phase flow, this study combines pore-scale experiments with lattice Boltzmann simulations to study the effects of geometrical factors and wettability. In this work, first, waterflooding experiments are performed on two water-wet micromodels with/without fractures at different injection rates. Oil recoveries as a function of injected time are determined by using a digital camera and an image-processing system. An optimal injection rate of the micromodel with fractures is 0.15 mL/min and that of the model without fractures is 0.1 mL/min. Then, the lattice Boltzmann method (LBM) is validated by simulating the contact angles and fluid distribution. At last, the LBM is used to further study the effects of different geometrical factors and five wettability conditions on waterflooding. The results reveal that the oil recovery factor of the model with a fracture in the flow direction (θ = 0°) is the lowest due to early water breakthrough. As the fracture becomes longer, the fingering phenomenon becomes obvious. In a circular section model, it is observed that the bridge-type residual oil occupies a small volume, which leads to a high displacement efficiency. In addition, because water–oil–grain contact lines move on a circular grain surface, the displacement pattern becomes more compact and high oil recovery is achieved in the water-wet model. However, oil is attached to the pore wall and forms an oil film in the square section model under oil-wet conditions, and the capillary force is resistant to the non-wetting invading phase to penetrate the blind-end of the pore, leading to low oil recovery.