A unique artificial intelligence approach and mathematical model to accurately evaluate viscosity and density of several nanofluids from experimental data

A New 3D Mathematical Model for Simulating Nanofluid Flooding in a Porous Medium for Enhanced Oil Recovery

Two-phase Darcy's law is a well-known mathematical model used in the petrochemical industry. It predicts the fluid flow in reservoirs and can be used to optimize oil production using recent technology. Indeed, various models have been proposed for predicting oil recovery using injected nanofluids (NFs). Among them, numerical modeling is attracting the attention of scientists and engineers owing to its ability to modify the thermophysical properties of NFs such as density, viscosity, and thermal conductivity. Herein, a new model for simulating NF injection into a 3D porous media for enhanced oil recovery (EOR) is investigated. This model has been developed for its ability to predict oil recovery across a wide range of temperatures and volume fractions (VFs). For the first time, the model can examine the changes and effects of thermophysical properties on the EOR process based on empirical correlations depending on two variables, VF and inlet temperature. The governing equations obtained from Darcy's law, mass conservation, concentration, and energy equations were numerically evaluated using a time-dependent finite-element method. The findings indicated that optimizing the temperature and VF could significantly improve the thermophysical properties of the EOR process. We observed that increasing the inlet temperature (353.15 K) and volume fraction (4%) resulted in better oil displacement, improved sweep efficiency, and enhanced mobility of the NF. The oil recovery decreased when the VF (>4%) and temperature exceeded 353.15 K. Remarkably, the optimal VF and inlet temperature for changing the thermophysical properties increased the oil production by 30%.

Accurate prediction of dynamic viscosity of polyalpha-olefin boron nitride nanofluids using machine learning

This study focuses on predicting the dynamic viscosity of nanofluids, specifically Polyalpha-Olefin-hexagonal boron nitride (PAO-hBN) using machine learning models. The primary goal of this research is to assess and contrast the effectiveness of three distinct machine learning models: Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS). The main objective is the identification of a model that demonstrates the highest level of accuracy in predicting a nanofluid's viscosity namely, PAO-hBN nanofluids. The models were trained and validated using 540 experimental data points, where the mean square error (MSE) and the coefficient of determination R² were utilized for performance evaluation. The results demonstrated that all three models could predict the viscosity of PAO-hBN nanofluids accurately, but the ANFIS and ANN models outperformed the SVR model. The ANFIS and ANN models had similar performance, but the ANN model was preferred due to its faster training and computation time. The optimized ANN model had an R² of 0.99994, which indicates a high level of accuracy in predicting the viscosity of PAO-hBN nanofluids. The elimination of the shear rate parameter from the input layer improved the accuracy of the ANN model to an absolute relative error of less than 1.89% over the full temperature range (-19.7 °C-70 °C) compared to 11% in the traditional correlation-based model. These results suggest that the use of machine learning models can significantly improve the accuracy of predicting the viscosity of PAO-hBN nanofluids. Overall, this study demonstrated that the use of machine learning models, specifically ANN, can be effective in predicting PAO-hBN nanofluids' dynamic viscosity. The findings provide a new perspective on how to predict the thermodynamic properties of nanofluids with high accuracy, which could have important applications in various industries.

Numerical analysis of the chemically reactive EMHD flow of a nanofluid past a bi-directional Riga plate influenced by velocity slips and convective boundary conditions

This report presents the three-dimensional electromagnetohydrodynamic flow of a zinc-oxide–water nanofluid past a bidirectional Riga plate with velocity slips and thermal and mass convection conditions. The Cattaneo–Christov heat and mas flux model, thermal radiation, chemical reaction and activation energy are considered to analyze the flow problem. The volume fraction of the ZnO nanoparticles is taken 6% in this analysis. An appropriate set of similarity variables is used to transform the partial differential equations into ordinary differential equations. During this process, some parameters are found and influences of these factors on the flow profiles are shown and discussed in detail. A numerical technique called NDSolve is considered for the solution of the nanofluid flow problem. The results showed that higher solid volume fraction and slip parameter have reduced velocities profiles and the increasing solid volume fraction and thermal Biot number have increased the temperature profile. Additionally, the concentration Biot number has increased the concentration profile. The modified Hartmann number has significantly increased the velocity profile. Dual impacts in velocity profiles along primary and secondary direction has been observed due to stretching ratio parameter. A comparison of current results has been carried with a fine agreement amongst current and established results.