No abstract

This paper shows the importance of Artificial Intelligence (AI) techniques as a practical engineering tool for predicting and estimating the gas flow rate through chokes. Studying the single gas flow through wellhead chokes is vital to the oil industry, not only to ensure the accurate estimation of gas flow rate but also to keep equipments protected from damage due to high gas flow rate. It also has the potential to avoid sand problems. Many studies have investigated the predictability of gas flow through chokes. In this paper, we reviewed, evaluated and compared the predictive performance of the available choke correlations in literature with five AI techniques. 162 data points were used to develop five AI models for predicting the gas flow rate. The data were fed to the five AI techniques Artificial Neural Network (ANN), Fuzzy Logic (FL), Support Vector Machine (SVM), Functional Network (FN) and Decision Tree (DT) (ANN, FL, SVM, FN and DT) and the results were optimized for each technique. The new models were found to perform better than the correlation and give the lowest error, with a mean absolute percentage error of 0.83%. Because of these reduced errors, the proposed AI-based models can improve gas flow rate prediction through chokes. The results of this paper will provide a better alternative to predictive modeling of petroleum reservoir properties. It will also open windows of opportunity for researchers and engineers to explore advanced machine learning techniques such as hybrids and ensembles for continued improvement of petroleum exploration and production.

The process of “hysteresis” has widely attracted the attention of researchers and investigators due to its usage in many disciplines of science and engineering. Economics, physics, chemistry, electrical, mechanical, and petroleum engineering are some examples of disciplines that encounter hysteresis. However, the meaning of hysteresis varies from one field to another, and therefore, many definitions occur for this phenomenon depending on the area of interest. The “hysteresis” phenomenon in petroleum engineering has gained the attention of researchers and investigators lately, because of the role that plays in reservoir engineering and reservoir simulation. Hysteretic effects influence reservoir performance. Therefore, an accurate estimation of rock and fluid property curves has an essential role in evaluating hydrocarbon recovery processes. In this paper, a comprehensive review of research and growth on the hysteresis of wettability for its applications in petroleum engineering is reported. Also, theoretical and experimental investigations of hysteresis of wettability are compared and discussed in detail. The review highlights a range of concepts in existing models and experimental processes for wettability hysteresis. Furthermore, this paper tracks the current development of hysteresis and provides insight for future trends in the research. Finally, it reveals an outlook on the research challenges and weaknesses of hysteresis of wettability.

No abstract

The mathematical approach is the most commonly used approach in reservoir simulation. The classical mathematical approach considers numerous impractical assumptions leading toward the development of unrealistic reservoir simulator. In contrast, recently developed engineering approach is much promising as it has numerous advantages, such as – scope of bypassing the formulation of partial differential equations and discretization of partial differential equations, the ability to avoid rigorous and complex mathematics, and capability of realistic representation of reservoir behaviour through eliminating spurious assumptions. The present study outlines the route map for developing a reservoir simulator using an engineering approach. Major challenges encountered in reservoir simulation and the fundamentals of various available modelling approaches are addressed in this paper. The outlook for both classical mathematical approach and engineering approach are reviewed along with their strengths and weaknesses. Fluid flow equations are derived based on the proposed engineering approach. To do that, a set of non-linear algebraic flow equations in the time integral form is developed using the mass balance equation, an equation of state, and a constitutive equation without going through the formulation of partial differential equations and discretization step. The time integral is then approximated to obtain the non-linear algebraic flow equations for all the gridblocks of the reservoir. The significance of the engineering approach for describing the accurate fluid flow through porous media is compared to the to conventional mathematical approach. The engineering approach provides the same fluid flow equations as the classical mathematical approach for both the radial cylindrical and cartesian coordinate system but, without going through the formulation of partial differential equations and discretization step. Much simpler ordinary differential equation solvers, e.g., Runge-Kutta method or Euler method can be used in the engineering approach to obtain the solution, whereas the classical mathematical approach does not have this advantage. Both the classical mathematical approach and the engineering approach treat the initial conditions in the same way. If classical mathematical approach uses second-order approximation then the same accuracy is obtained for both approaches in treating the boundary conditions. The engineering approach provides more precise dealing to the constant pressure boundary condition for block-centred gridding system in case of using the first-order approximation. The engineering approach gives the justification of using the central difference approximation for second order space derivative in classical mathematical approach. Results show that the proposed engineering approach based fluid flow model provides better flow prediction than the conventional mathematical approach based flow model. The outcome of this study will help engineers and researchers to develop more transparent simulator instead of creating a black box where the natural chaotic behaviour of the underground reservoir will be more understandable.