Average Absolute Deviation Percent Research Articles

Performance prediction of a supercritical CO2 Brayton cycle integrated with wind farm-based molten salt energy storage: Artificial intelligence (AI) approach

Using energy storage technologies in combination with renewable energy sources can improve power generation efficiency and reliability. Here, we predict the performance of a wind farm-based molten salt energy storage system combined with a supercritical CO2 Brayton cycle (s-CO2BC) with the aid of artificial intelligence (AI). For this purpose, the Grasshopper Optimization Algorithm (GOA) and Particle Swarm Optimization (PSO) are applied to train a Multilayer Perceptron Artificial Neural Network (MLP-ANN). The proposed AI approaches model the complex interactions between the wind farm, the molten salt energy storage, and the s-CO2BC components. Integrated system simulations under various operating conditions are used for training the performance prediction model. Power generation, energy storage, and system efficiency can all be accurately predicted by a trained AI model. In addition to providing valuable insight into the optimal operation and control strategies of the integrated system, the proposed approach enables the efficient utilization of renewable energy resources and energy storage to generate sustainable power. This study contributes to the development of AI-based optimization approaches and predicts the performance of integrated renewable energy systems, resulting in improved grid integration and stability. According to the results, the PSO method yields average absolute percentage deviations (AAPDs) between 0.47% and 0.51% across different parameters, while GOA yields AAPDs between 0.05% and 0.27%.

A new setup for speed of sound measurements and experimental data for nanofluids Al2O3 or Ag with water or ethylene glycol

The speed of sound of four different nanofluids consisting of Ag or Al2O3 nanoparticles and water or ethylene glycol base fluid is measured in the temperature range (298.15–343.15) K and at atmospheric pressure. One aim of this analysis is to learn whether the change from pure base fluid speed of sound to the nanofluid situation is a smooth or disruptive transition when adding nanoparticles. The measurements were conducted on the newly proposed apparatus consisting mainly of function generator, ultrasonic sensor, switch, voltage source, oscilloscope, ultrasonic container and the necessary sensors and equipment for data acquisition. The values for speed of sound were calculated based on the Time of Flight method. Deionised water and ethanol were used to calibrate the apparatus which is additionally tested with pure base fluids water and ethylene glycol and showed excellent agreement with average absolute percentage deviations between experimental and literature data for speed of sound of 0.12% and 0.36%, respectively,. Beside the temperature influence, the influence of the nanoparticle concentration on the speed of sound of nanofluid were investigated and followed. The analysis of the sound velocity allows insight into the molecular level interactions taking place between the nanoparticles and the base fluid molecules of the nanofluid. The decrease in velocity values with the increase of concentration, noticeable in the tested nanofluids, is a result of decrease in nanoparticle-fluid interaction and dominance of particle–particle interaction.

Wet fluidization characterization of potash particles in a pulsation-assisted fluidized bed

In order to improve fluidization behavior, pulsed airflow was employed to break agglomeration and eliminate channeling in a fluidized bed with wet potash particles. The effects of pulsation frequency, pulsed air to continuous flow ratio (r), and inlet relative humidity of the air on bubbling behavior were investigated via an electrical capacitance tomography system. A frequency of 1.0 Hz and an r of 0.33 with 0.1 s opening time were found to be the optimum condition, leading to the lowest minimum fluidization velocity (umf) and generation of homogeneous bubbles in size and shape. A new theoretical model was developed to predict the umf of wet particles in a fluidized bed by considering both the liquid bridge force and resonant force resulting from the pulsation. Average absolute deviation percentage values between the predicted umf and the experimental data were 13.8 and 20.7 for the dry and wet particles, respectively, indicating good agreement.

Demand Side Control for Energy Saving in Renewable Energy Resources Using Deep Learning Optimization

Convolutional neural networks a type of deep learning technology, are used for forecasting future power usage. The mean absolute error, mean square error, root mean square error, and mean constant percentage error are used to evaluate the performance of the models. These metrics are used to rank the models. Among the models tested, the CNN stack demonstrates the highest precision in estimating energy consumption and solar power output, with a mean absolute error of 0.015% points, a root mean square error of 0.23% points, and an average absolute percentage deviation of 1.71% points. However, for wind turbine (WT) energy generation, the recurrent neural network proves for most accurate model, achieving 0.070 as the median absolute percentage error is 2.65, Both the root of the mean square error and the average absolute error are 0.38. The training and validation data utilized in this study comprise the International Renewable Energy Agency’s data on solar power production, WT power generation, and the “ensue” dataset, which includes hourly power consumption information from the Pennsylvania, New Jersey, and Maryland interconnection.

Equilibrium absorption of CO2 in aqueous solution of N-dimethylamino ethanol and 2-(ethylamino)ethanol, measuring and thermodynamic modeling

The equilibrium carbon dioxide solubility in aqueous solutions of N-dimethylaminoethanol (DMAE) 40 wt% + 2-(ethylamino) ethanol (EAE) 5 wt% and DMAE 30 wt% + EAE 5 wt% was measured at various temperatures (313.15, 328.15, 343.15, 358.15 K) in the range of pressures from 6.5 to 236 kPa. The enthalpy of absorption of carbon dioxide was measured for the mixture of DMAE (40 wt%) + EAE (5 wt%), at 328.15 K. The Deshmukh-Mather model was used to correlate the equilibrium solubility of carbon dioxide data, and the model parameters were optimized. The optimized model could correlate the vapor-liquid equilibrium with the 9.4 average absolute percentage deviation (AAD%), and the obtained AAD% for enthalpy of absorption in aqueous solution of DMAE (40 wt%) + EAE (5 wt%) was 24.0.

Measurement of gas-liquid flows with the combination of thermal sensors and conductance sensor

Gas-liquid two-phase flow is a typical phenomenon in energy and industrial production. Thus, flow measurement of gas-liquid flow is vital in the exploration and extraction of oil and natural gas. The thermal sensors are based on convection heat transfer between heating elements and fluid. These sensors have been widely used in flow measurement because of their high precision, and low-pressure loss, and it is not affected by fluid conductivity and viscosity. This study utilized the thermal conductivity difference in liquid and gas to design a measurement system that combines thermal sensors and a conductance sensor. Among them, the thermal sensors contain 2 upstream and downstream thermal resistors and a total of 28 thermocouples distributed over 7 sections (4 for each section) to capture axial and sectional thermal information. A rotating electric field conductance sensor (REFCS) serves to accurately determine gas holdups. The model tests show that the separated flow models have better accuracy than the liquid-phase acceleration models and pressure drop models. Inspired by the classical separated flow models, an improved heat transfer model based on flow patterns is developed by adding an additional superficial velocity term. Based on the mechanism that the heat transfer is dominated by the liquid phase, the superficial velocities are measured in combination with the drift-flux model. Overall, the average absolute percentage deviations (AAPD) for both the heat transfer coefficients and superficial velocities are less than 5%, indicating that the improved model has excellent performance and robustness for flow prediction in 20 mm pipes.

A precise estimation for vibrational energies of diatomic molecules using the improved Rosen–Morse potential

In the context of the generalized fractional derivative, novel solutions to the D-dimensional Schrödinger equation are investigated via the improved Rosen-Morse potential (IRMP). By applying the Pekeris-type approximation to the centrifugal term, the generalized fractional Nikiforov-Uvarov method has been used to derive the analytical formulations of the energy eigenvalues and wave functions in terms of the fractional parameters in D-dimensions. The resulting solutions are employed for a variety of diatomic molecules (DMs), which have numerous uses in many fields of physics. With the use of molecular parameters, the IRMP is utilized to reproduce potential energy curves for numerous DMs. The pure vibrational energy spectra for several DMs are determined using both the fractional and the ordinary forms to demonstrate the effectiveness of the method utilized in this work. As compared to earlier investigations, it has been found that our estimated vibrational energies correspond with the observed Rydberg-Klein-Rees (RKR) data much more closely. Moreover, it is observed that the vibrational energy spectra of different DMs computed in the existence of fractional parameters are superior to those computed in the ordinary case for fitting the observed RKR data. Thus, it may be inferred that fractional order significantly affects the vibrational energy levels of DMs. Both the mean absolute percentage deviation (MAPD) and average absolute deviation (AAD) are evaluated as the goodness of fit indicators. According to the estimated AAD and MAPD outcomes, the IRMP is an appropriate model for simulating the RKR data for all of the DMs under investigation.

Liquid densities of n-octane, ethylcyclohexane and their binary mixtures {(x) n-octane) + (1 − x) ethylcyclohexane} at temperatures from (283 to 363) K and pressures up to 60 MPa

In this work, liquid densities of n-octane, ethylcyclohexane and their binary mixtures {(x) n-octane) + (1 − x) ethylcyclohexane} with mole fraction x= (0.200, 0.400, 0.600, 0.800) are reported. The density measurements were performed with a high-pressure vibrating-tube densimeter at temperatures from (283 to 363) K and pressures up to 60 MPa. The combined expanded uncertainties (0.95 level of confidence, k = 2) are estimated to be 16 mK for temperature, 0.062 MPa for pressure, and up to 0.6 kg/m3 for density. The experimental densities were correlated using the modified Tait equation. The average absolute percentage deviations of measurement results from the modified Tait equation correlations of n-octane, ethylcyclohexane and their binary mixtures {(x) n-octane) + (1 − x) ethylcyclohexane} are all lower than 0.1%. The isothermal compressibility and isobaric expansivity have also been derived from the experimental densities.

Assessment of a Parachor Model for the Surface Tension of Binary Mixtures

We compiled an experimental database for the surface tension of binary mixtures containing a wide variety of fluids, from the chemical classes (water, alcohols, amines, ketones, linear and branched alkanes, naphthenes, aromatics, refrigerants, and cryogens). The resulting data set includes 65 pure fluids and 154 binary pairs with a total of 8205 points. We used this database to test the performance of a parachor model for the surface tension of binary mixtures. The model uses published correlations to determine the parachors of the pure fluids. The model has a single, constant binary interaction parameter for each pair that was found by fitting experimental mixture data. It can be also used in a predictive mode when the interaction parameters are set to zero. We present detailed comparisons on the performance of the model for both cases. In general, the parachor model in a predictive mode without fitted interaction parameters can predict the surface tension of binary mixtures of non-polar mixtures such as linear and branched alkanes, linear and branched alkanes with naphthenes, aromatics with aromatics, aromatics with naphthenes, and mixtures of linear alkanes of similar sizes with an average absolute percentage deviation of about 3 % or less. Polar mixtures of halocarbons with other halocarbons and also polar/nonpolar mixtures of alkanes with halocarbons could be modeled with an average absolute deviation of less than 0.35 mN·m−1 with the use of a binary interaction parameter. The parachor model even with a fitted binary interaction parameter performs poorly for mixtures of water and organic compounds and is not recommended.

An improved volume translation model for PC-SAFT EOS based on a distance function

In this study, we develop an improved volume-translation model for perturbed-chain statistical associating fluid theory (PC-SAFT) equation of state (EOS). The new volume translation model is based on a distance function that measures the distance between the current condition and a critical point. This volume translation model is integrated into a particular version of PC-SAFT, which can exactly reproduce the critical points of pure compounds. The proposed volume-translated PC-SAFT EOS is found to exactly reproduce the critical properties of pure compounds (including critical pressure, critical temperature, and critical molar volume) and yield accurate reproductions of the saturated liquid density, liquid density, and vapor pressure of the selected 39 pure fluids over a wide range of temperatures and pressures, covering the critical and non-critical regions. Overall, the newly developed volume-translated SAFT EOS model yields average absolute percentage deviations (%AADs) of only 0.505, 0.470, and 0.676, in reproducing the saturated liquid density, liquid density, and vapor pressure, respectively.

Non-linear Regression Models for Predicting Biogas Yields from Selected Bio-wastes

The benefits of biogas as alternative energy to other fossil fuel sources, due to its renewability, environmentally friendly nature, health benefits, etc., cannot be overemphasized. There are numerous models for predicting biogas production rate from bio-materials, including the modified Gompertz equation. These models are primarily dependent on specific biomass parameters. When any of these parameters, like the slurry volume, changes, another round of experiments must be conducted and curve fitted before biogas yield predictions can be made. This could be time-consuming and costly. Using experimentally published data, simple empirical models can be developed for predicting biogas yields over a range of input parameters. This will eliminate the need for always performing experiments before biogas yield predictions can be made. In light of this, scarce literature provides explicit models for predicting biogas yield over a range of parameters based on published data. This study developed non-linear regression models using published data on parameters that affect biogas yields, like the slurry volume, carbon-to-nitrogen ratio, temperature, total solids, volatile solids, hydraulic retention time, and pH. The data covered seven readily available bio-wastes, including cow dung, cow dung with plant waste, cow dung with poultry dung, poultry dung with grass, pig dung, and plant wastes. On validation of the models, the results showed that the models had a relatively low standard error of estimates, Akaike information criterion, Schwarz criterion, and Hannan-Quinn information criterion. Furthermore, the coefficients of determination, R2, were between 94.62 and 98.93%. The percentage average absolute deviation (% AAD) for each model was less than 7 %. The non-linear models were found to adequately predict the biogas yields within the limits of the available data set.

Performance model evaluation of turbine flow meter in vertical gas-liquid two-phase flows

Aiming at the need for flow measurement of gas-liquid flows in domestic gas well production, this paper proposes a measurement method based on the combination of the turbine flow meter (TFM) and a rotating electric field conductance sensor (REFCS). In experiments, the REFCS is used for the measurement of the gas holdup. To verify the applicability of the TFM models investigated in the previous study, for the modeling part, the mass, momentum and torque models are evaluated in vertical upward gas-liquid two-phase flows. In our model test, the meter factor model of TFM considers the effects of the slip ratio between the gas and liquid phases and flow patterns. In particular, the gas holdup involved in calculating the slip ratio in the model evaluation is obtained from the REFCS measurements. Model test results show the torque model has better volumetric flow rate prediction accuracy than the mass and momentum models. In the present study, the ranges of the liquid and gas phases are Qw = 2–30 m3/d and Qg = 1–16 m3/d, it was found that the average absolute deviation (AAD) in the predicted volume flow rate is equal to 1.23 m3/d and the average absolute percentage deviation (AAPD) is equal to 7.69%. The evaluated results presented in this paper will allow better estimates of the volumetric flow rates of gas-liquid flows based on the combined TMF and REFCS measurements during the monitoring of gas well production.

Densities, Viscosities, and Derived Properties for Binary Mixtures of Long-Chain Alcohols of 1-Hexanol + 1-Pentanol, + 2-Pentanol, + 2-Methyl-1-butanol, + 1-Heptanol, and + 1-Octanol from 288.15 to 338.15 K

Densities and viscosities for binary mixtures of long-chain alcohols are important to design transfer heat and mass equipment and to interpret the kind of interactions that occur in the studied blends. Current investigation indicated the measurements of densities and viscosities for liquid mixtures of 1-hexanol + 1-pentanol, + 2-pentanol, + 2-methyl-1-butanol, + 1-heptanol, and + 1-octanol from 288.15 to 338.15 K at atmospheric pressure and over the whole range of mole fractions. A vibrating tube densimeter and a glass capillary viscometer were used to measure the density and viscosity of the alcohol binary mixtures, respectively. Experimental measurements of the pure alcohols have been compared with the data reported in the literature using average absolute percentage deviation (AAPD) as a criterion. The obtained results demonstrated for density an AAPD of 0.023% and for viscosity an AAPD of 0.597%, which is a good agreement between the experimental findings and literature data. Excess molar volume and viscosity deviation present negative deviations for all the alcohol mixtures at the conditions considered in this research. These results indicate that the mixture suffers a volume contraction, which is caused by intermolecular forces of attraction between different alcohol molecules. The Redlich–Kister equation is used to fit the excess molar volume and viscosity deviation. Kinematic viscosities of the binary blends have been calculated through the Nava-Ríos et al. and McAllister equations.

Hydrate phase equilibria of carbon dioxide/propane gas mixture in concentrated aqueous sodium chloride solutions: Experimental data and prediction

The information on hydrate equilibrium conditions of gas hydrate formers in concentrated NaCl solutions are the prerequisites for hydrate-based desalination methods. Hydrate dissociation conditions for CO2-C3H8 mixture, as a good candidate for this application, were measured for the temperature and pressure ranges of 269–283 K and 0.3–3.4 MPa, respectively using an isochoric pressure-search method. The used gas mixture was a solution of 10 mol% C3H8 + 90 mol% CO2 and NaCl concentrations varied between 8 and 12 wt%. The promoting effect of propane was obviously observed from the experimental data. This promoting effect nearly balanced the inhibitory effect of 12 wt% NaCl. A thermodynamic model was applied to predict the experimental data using SRK, PR, and VPT EOSs. All EOSs had accurate results for prediction of CO2 hydrate equilibrium pressures, with the best result by PR EOS. The overall average absolute percent deviation (AAPD) of PR EOS in pure water and 8 wt% NaCl solution were 5.29 and 3.8 %, respectively. For gas mixture (CO2-C3H8) in pure water, the best accuracy was obtained by using SRK EOS with AAPD of 4.44 %. However, the results of VPT and PR for gas mixture in NaCl solutions, were more accurate than SRK with AAPDs equal to 7.47 and 7.75 %, respectively.

Solubility of Cortisone and Hydrocortisone in Supercritical Carbon Dioxide and Ethanol

Cortisone and hydrocortisone are poorly water-soluble corticosteroids widely used to treat many inflammatory and immune diseases. In the prospect of employing them in pharmaceutical applications or analytical techniques involving cosolvent-modified supercritical fluids, their solubility has been determined, for the first time, in a mixture of supercritical CO2 and 2, 3, or 4 mol % of ethanol, at 318.15, 328.15, 348.15, and 373.15 K, and in the pressure range of 13–27 MPa. Tests were conducted in a semi-flow laboratory apparatus, and results were fitted with the most popular density-based correlations reported in the literature for ternary systems. Even though the two drugs exhibit similar molecular structures, the solubility of cortisone in the ethanol-scCO2 mixtures is on average 3.5 times higher than that of hydrocortisone. This is congruent with the fact that the solubility of cortisone in pure ethanol is higher. The seven-parameter Reddy–Madras model (adjusted absolute average percent deviation (AARD%) = 8.8%) proved to be the best correlating one for cortisone while the six-parameter Garlapati–Madras approach (AARD% = 11.6%) provided the best fitting for hydrocortisone. The reliability of the experimental results was also confirmed by the positive response to the Méndez-Santiago–Teja self-consistency test.

Measurement of Liquid–Liquid Flows Using Turbine Flowmeter and Conductance Sensor With Multiheight Electrodes in Vertical Pipes

Liquid–liquid two-phase flows are common industrial processes in chemical, petroleum, and other related fields. It is a great challenge for the flow measurement using the turbine flowmeter (TFM) in low-velocity liquid–liquid flows due to the serious slippage effect between the oil and water phases. The complex physical discrepancies between the two phases make the response of TFM vastly different from that in single-phase flow. This study proposes a system combining TFM and conductance sensors with multiheight electrodes (CSMHEs) to determine liquid–liquid two-phase flows. This study investigates the effects of phase distribution and slippage on the wheel hub drag torque. The model of wheel hub drag torque in different flow patterns is established, and a new variable meter factor model of TFM in liquid–liquid flows is constructed. Experiments in 20-mm simulated well reveal that the TFM can make accurate predictions of total flow rate and enable online measurements of individual phase superficial velocities. The absolute average percentage deviations (AAPDs) of superficial water and oil velocities are 2.01% and 7.24%, respectively.

Quantum mechanical and classical calculation of the transport and relaxation properties of He⋯CO2 complex using a new PES.

The intermolecular potential energy surface (PES) of He⋯CO2 van der Waals (vdW) complex was computed at the RCCSD(T)/aug-cc-pvQz-BF level of theory. The obtained potential was fitted to an exact mathematical model using the Legendre expansion method. The fitted PES model was then used to calculate the interaction second virial coefficients (B12) considering the classical and first quantum corrections, and compared with the available experimental data in the temperature range of T = 50-463.2 K. The results of the experimental and calculated B12 reasonably agree. The fitted potential was also applied to compute the transport and relaxation properties of He⋯CO2 complex from classical Mason-Monchick approximation (MMA) and Boltzmann weighting method (BWM), and the full quantum mechanical close-coupling (CC) solution of the Waldmann-Snider kinetic equation. The average absolute deviation percent (AAD%) of the experimental and CC calculated viscosity (η12) and diffusion coefficients (D12) were found to be 1.4% and 1.9%, respectively, which are in the range of the experimental uncertainties. However, the AAD% of MMA for η12 and D12 were found to be 11.2% and 11.9%, respectively. It was also found that as the temperature increased, the accuracy of MMA decreased compared to the CC method, which may be related to the elimination of the contribution of the rotational degrees of freedom, especially the off-diagonal elements in the classical MMA method. Furthermore, equilibrium classical molecular dynamics (MD) simulations based on the Green-Kubo time correlation function were performed using the Morse, LJ(12,6), and Vashishta potential models to calculate η12 and D12. The AAD% for η12 and D12 were found to be ∼13% and ∼30%, respectively, at the temperature range of T = 200-1000 K.

A novel friction factor model for wire-wrapped rod bundles

Wire-wrapped rod bundles are often considered for fast spectrum nuclear reactors, especially liquid metal cooled fast reactors (LMFRs). Accurate calculation of the pressure drops of these bundles is key for proper thermal–hydraulic design of the reactor. Existing models, while able to accurately predict bundle friction factor, are complex and can be difficult to use without utilizing a numerical implementation. In this paper, a new model for bundle friction factor is proposed based on exact laminar solutions of the Navier-Stokes equations for a simplified rod bundle geometry. These exact solutions can then be adjusted via geometric and empirical parameters to the prototypic geometry. The proposed model is able to calculate the bundle friction factor with an average absolute percent difference of 10.8 % compared to the available experimental data. This compares favourably to existing correlations, offering similar performance while minimizing the number of empirical coefficients and the overall effort required. The model is also valuable for determining a theoretical lower bound for bundle friction factor for a given geometry, with some data found to be lower (>10 %) than this bound. The overall methodology can also in principal be applied to other geometries where similar simplifications could be made.

Thermophysical Properties of Biodiesel with Ethyl Levulinate, Ethyl Acetoacetate, and Ethyl Pyruvate + MgO Mixtures from 288.15 to 338.15 K

Thermophysical properties are important to design the fuel system components and to evaluate new alternative fuels in diesel engine tests. Also, experimental properties allow us to understand the type of interactions present in the studied mixtures. Densities, viscosities, and refractive indices of biodiesel + ethyl levulinate, + ethyl acetoacetate, and + ethyl pyruvate with MgO mixtures have been measured from 288.15 to 338.15 K at 0.1 MPa over the whole composition range and at a constant concentration of 5 × 10–6 in mass fraction for MgO. Our experimental properties for the pure ketoesters agree with data reported in the literature within an average absolute percentage deviation of 0.056, 3.140, and 0.027 % for density, viscosity, and refractive index, respectively. Vibrating tube densimeter, glass capillary viscosimeter, and Abbemat refractometer have been used to measure the properties. Densities and viscosities of the biodiesel mixtures have been compared with the biodiesel fuel standard EN 14214. Flash point, cetane index, and calorific value of the biodiesel mixtures that meet the EN 14214 norm have been measured. Excess molar volume, viscosity deviation, and refractive index deviation are obtained from experimental data and correlated using the Redlich–Kister equation. Equations reported in the literature are used to correlate the thermophysical properties of the investigated mixtures.

Density and Refractive Index of Binary Ionic Liquid Mixtures with Common Cations/Anions, along with ANFIS Modelling

Ionic liquids have many interesting properties as they share the properties of molten salts as well as organic liquids, such as low volatility, thermal stability, electrical conductivity, non-flammability, and much more. Ionic liquids are known to be good solvents for many polar and nonpolar solutes. Combined with their special properties, ionic liquids are good replacements for the conventional toxic and volatile organic solvents. Each ionic liquid has different properties than others. In order to alter, tune, and enhance the properties of ionic liquids, sometimes, it is necessary to mix different ionic liquids to achieve the desired properties. However, using mixtures of ionic liquids in chemical processes requires reliable estimations of the mixtures’ physical properties such as refractive index and density. The ionic liquids used in this work are 1-butyl-3-methylimidazolium thiocyanate ([BMIM][SCN]), 1-butyl-3-methylimidazolium tetrafluoroborate ([BMIM][BF4]), 1-hexyl-3-methylimidazolium tetrafluoroborate ([HMIM][BF4]), and 1-hexyl-3-methylimidazolium hexafluorophosphate ([HMIM][PF6]). These ionic liquids were supplied by Io-li-tec and used as received. However, new measurements for the density and refractive index were taken for the pure ionic liquids to be used as reference. In the present work, the densities and refractive indices of four different binary mixtures of ionic liquids with common cations and/or anions have been measured at various compositions and room conditions. The accuracy of different empirical mixing rules for calculation of the mixtures refractive indices was also studied. It was found that the overall absolute average percentage deviation from the ideal solution in the calculation of the molar volume of the examined binary mixtures was 0.78%. Furthermore, all of the examined mixing rules for the calculation of the refractive indices of the mixtures were found to be accurate. However, the most accurate empirical formula was found to be Heller’s relation, with an average percentage error of 0.24%. Furthermore, an artificial intelligence model, an adaptive neuro-fuzzy inference system (ANFIS), was developed to predict the density and refractive index of the different mixtures studied in this work as well as the published literature data. The predictions of the developed model were analyzed by various methods including both statistical and graphical approaches. The obtained results show that the developed model accurately predicts the density and refractive index with overall R2, RMSE, and AARD% values of 0.968, 7.274, 0.368% and 0.948, 7.32 × 10−3 and 0.319%, respectively, for the external validation dataset. Finally, a variance-based global sensitivity analysis was formed using extended the Fourier amplitude sensitivity test (EFAST). Our modelling showed that the ANFIS model outperforms the best available empirical models in the literature for predicting the refractive index of the different mixtures of ionic liquids.