The interaction between clay minerals in formations and drilling fluids was analyzed through a study of four core plugs in different types of fluid, including gas oil, anionic surfactant (SDS), non-ionic surfactant (PEG), and cationic surfactant (CTAB). The core plugs were cut for petrophysical tests, including permeability, saturation, X-ray diffraction, and petrographical analyses. The original samples contained clay minerals such as illite and smectite. A static immersion test revealed that swelling and dispersing changed the original petrophysical rock properties of the samples. The addition of nanoparticles of Ca, K, Na, Cl at low, high, and saturated salinity in sodium chloride (NaCl), potassium chloride (KCl), and calcium chloride (CaCl2) was used to reduce active shale and increase mud density from 8.33 to 11.8 ppg, improving petrophysical rock properties by reducing filtration and swelling. The permeability and water saturation were measured before and after core injection of the drilling fluids. The results showed that surfactants (PEG) > (SDS) > (CTAB) in a water-based drilling fluid improved fluid loss and viscosity and reduced the interfacial tension, shifting the reservoir wettability towards a more water-wet state in low, high, and saturation salinity. The use of surfactants in water-based mud reduced formation damage and increased well productivity.

In order to have a better control over the drilling process and reduce the overall cost of this drilling operation, engineers have tried to use soft computing (SC) techniques to conduct the pre-estimation of drilling events. It is critically important to estimate the annular pressure losses (APL) for non-Newtonian drilling muds within annulus in order to specify pump rates and also to be able to choose the most appropriate mud pump systems while conducting the drilling operations. To develop the vigorous and exact models to enable the prediction of APL, two popular models were employed, i.e., multilayer perceptron (MLP) [optimized by levenberg-marquardt (LM), bayesian regularization (BR), scaled conjugate gradient (SCG), Resilient back propagation (RB), and broyden fletcher goldfarb shanno (BFGS)] and radial basis function (RBF). Subsequently, applying a committee machine intelligent system (CMIS), the four top models were combined into a unit paradigm. Several tools such as error distribution diagram, cross plot, trend analysis, and cumulative frequency diagram were used in conjunction with statistical calculation to assess the efficiency of models. Consequently, the CMIS model was introduced as the most exact technique which has the greatest coefficient of determination (R2 close to one) as well as the lowest root mean square error (RMSE close to zero) for the tested dataset.

In order to have a better control over the drilling process and reduce the overall cost of this drilling operation, engineers have tried to use soft computing (SC) techniques to conduct the preestimation of drilling events. It is critically important to estimate the annular pressure losses (APL) for non-Newtonian drilling muds within annulus in order to specify pump rates and also to be able to choose the most appropriate mud pump systems while conducting the drilling operations. To develop the vigorous and exact models to enable the prediction of APL, two popular models were employed, i.e., multilayer perceptron (MLP) [optimized by levenbergmarquardt (LM), bayesian regularization (BR), scaled conjugate gradient (SCG), Resilient back propagation (RB), and broyden fletcher goldfarb shanno (BFGS)] and radial basis function (RBF). Subsequently, applying a committee machine intelligent system (CMIS), the four top models were combined into a unit paradigm. Several tools such as error distribution diagram, cross plot, trend analysis, and cumulative frequency diagram were used in conjunction with statistical calculation to assess the efficiency of models. Consequently, the CMIS model was introduced as the most exact technique which has the greatest coefficient of determination (R 2 close to one) as well as the lowest root mean square error (RMSE close to zero) for the tested dataset.