Modeling of the movement of rich gas in a porous medium in immiscible, near miscible and miscible conditions.

Gas injection is one of the most common enhanced oil recovery techniques in oil reservoirs. In this regard, pure gas, such as carbon dioxide (CO2), nitrogen (N2), and methane (CH4) was employed in EOR process. The performance of pure gases in EOR have been investigated numerically, but till now, numerical simulation of injection of rich gases has been scared. As rich gases are more economical and can result in acceptable oil recovery, numerical study of the performance of rich gases in EOR can be an interesting subject. Accordingly, in the present work the performance of rich gases in the gas injection process was investigated. Methane has been riched in liquefied petroleum gas (LPG), natural gas liquid (NGL), and Naphtha. Afterwards, the process of gas injection was simulated and the effect of injection fluids on the relative permeability, saturation profile of gas, and fractional flow of gas was studied. Our results showed that as naphtha is a heavier gas than the two other ones, IFT of oil-rich gas with naphtha is lower than other two systems. Based our results, gas oil ratio (GOR) and injection pressure did not affect the final performance of injection gas that has been riched in NGL and LPG. However, when GOR was 1.25 MSCF/STB, rich gas with naphtha moved with a higher speed in the domain and the relative permeability of each fluid and fractional flow of gas were affected. The same result was achieved at higher injection pressure. When injection pressure was 2000 psi, movement of gas with higher speed in the domain, alteration of relative permeability and changes in the fractional flow of gas were obvious. Therefore, based on our result, injection of naphtha with low pressure and high GOR was suggested for considered oil.

Modelling rate of penetration in drilling operations using RBF, MLP, LSSVM, and DT models.

One of the most important problems that the drilling industry faces is drilling cost. Many factors affect the cost of drilling. Increasing drilling time has a significant role in increasing drilling costs. One of the solutions to reduce drilling time is to optimize the drilling rate. Drilling wells at the optimum time will reduce the time and thus reduce the cost of drilling. The drilling rate depends on different factors, some of which are controllable and some are uncontrollable. In this study, several smart models and a correlation were proposed to predict the rate of penetration (ROP) which is very important for planning a drilling operation. 5040 real data points from a field in the South of Iran have been used. The ROP was modelled using Radial Basis Function, Decision Tree (DT), Least Square Vector Machine (LSSVM), and Multilayer Perceptron (MLP). Bayesian Regularization Algorithm (BRA), Scaled Conjugate Gradient Algorithm and Levenberg-Marquardt Algorithm were employed to train MLP and Gradient Boosting (GB) was used for DT. To evaluate the accuracy of the developed models, both graphical and statistical techniques were used. The results showed that DT-GB model with an R2 of 0.977, has the best performance, followed by LSSVM and MLP-BRA with R2 of 0.971 and 0.969, respectively. Aside from that, the proposed empirical correlation has an acceptable accuracy in spite of simplicity. Moreover, sensitivity analysis illustrated that depth and pump pressure have the highest effects on ROP. In addition, the leverage approach approved that the developed DT-GB model is valid statistically and about 1% of the data are suspected or out of the applicability domain of the model.