Search

The different tasks of petroleum engineers such as well testing and simulation are highly function of reservoir fluids properties so the accuracy of these properties can affect the oil recovery. Solution gas oil ratio is one of these major properties so in this investigation, a new and accurate approach based on adaptive neuro-fuzzy interference system (ANFIS) algorithm was evolved to predict the solution gas oil ratio (Rs) as function of other properties of crude oil in operational conditions. In the current work, a comprehensive databank contains 1136 data points and was implemented for preparation and validation of ANFIS. By the evaluation of prediction algorithm, the coefficient of determination values in training and testing processes of Rs prediction were obtained 0.98125 and 0.96477, respectively. Furthermore, the proposed ANFIS was compared with the existing correlations in literature. These comparisons showed that the ANFIS performed in acceptable degree of accuracy for determination of Rs. [ABSTRACT FROM AUTHOR]

One of the important parameters illustrating the mass transfer process is the diffusion coefficient of carbon dioxide which has a great impact on carbon dioxide storage in marine ecosystems, saline aquifers, and depleted reservoirs. Due to the complex interpretation approaches and special laboratory equipment for measurement of carbon dioxide-brine system diffusivity, the computational and mathematical methods are preferred. In this paper, the adaptive neuro-fuzzy inference system (ANFIS) is coupled with five different evolutionary algorithms for predicting the diffusivity coefficient of carbon dioxide. The R2 values forthe testing phase are 0.9978, 0.9932, 0.9854, 0.9738 and 0.9514 for ANFIS optimized by particle swarm optimization (PSO), genetic algorithms (GA), ant colony optimization (ACO), backpropagation (BP), and differential evolution (DE), respectively. The hybrid machine learning model of ANFIS-PSO outperforms the other models. [ABSTRACT FROM AUTHOR]

Prediction of standard molar chemical exergy value for organic compounds is investigated using a quantitative structure-property relationship (QSPR) model combined with adaptive neuro-fuzzy inference system (ANFIS) strategy. Particle swarm optimization (PSO) method is also implemented to determine the optimal ANFIS structure. The proposed model uses three constitutional descriptors in model development's procedure. The QSPR-ANFIS model represents a great performance in prediction of the standard molar chemical exergy values with 0.9999, 44548, and 1.49 values for R2, RMSE, and %AARD, respectively. [ABSTRACT FROM AUTHOR]

The present contribution was aimed to estimate the vaporization enthalpy of petroleum fractions and pure hydrocarbons by using the combination of adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm (GA) called GA-ANFIS. This tool can approximate the vaporization enthalpy as a function of the specific gravity, molecular weight, and boiling point temperature with high accuracy based on 122 data gathered from the previously published literature. Furthermore, results from the proposed model have been compared with different correlations and its acceptable predictive ability against other correlations was proved in order to the estimation of the vaporization enthalpy. The percentage of absolute relative deviation and R-squared (R2) was 1.64% and 0.9967%, respectively. This tool is simple to use and can be of considerable help for petroleum engineers to have an accurate estimation of vaporization enthalpy of hydrocarbon fractions of pure hydrocarbons. [ABSTRACT FROM AUTHOR]

Nanofluid viscosity is an important physical property in convective heat transfer phenomena. However, the current theoretical models for nanofluid viscosity prediction are only applicable across a limited range. In this study, 1277 experimental data points of distinct nanofluid relative viscosity (NF-RV) were gathered from a plenary literature review. In order to create a general model, adaptive network-based fuzzy inference system (ANFIS) code was expanded based on the independent variables of temperature, nanoparticle diameter, nanofluid density, volumetric fraction, and viscosity of the base fluid. A statistical analysis of the data for training and testing (with R² = .99997) demonstrates the accuracy of the model. In addition, the results obtained from ANFIS are compared to similar experimental data and show absolute and maximum average relative deviations of about 0.42 and 6.45%, respectively. Comparisons with other theoretical models from previous research is used to verify the model and prove the prediction capabilities of ANFIS. Consequently, this tool can be of huge value in helping chemists and mechanical and chemical engineers - especially those who are dealing with heat transfer applications by nanofluids - by providing highly accurate predictions of NF-RVs. [ABSTRACT FROM AUTHOR]

Combustion of wastes is a promising source for energy recovery because of having appropriate higher heating value (HHV) in order to use as fuel. The present study was aimed to estimate HHV value using a hybrid adaptive neuro-fuzzy inference system and genetic algorithm called GA-ANFIS. This model can predict HHV as a function of carbon (%C), hydrogen (%H), oxygen (%O), nitrogen (%N), and sulfur (%S) mass percentages. This suggested model has been also compared with other published correlations, and based on obtained results, great accuracy of our model was confirmed. The obtained values of Mean Squared Error (MSE) and R-squared were 0.236 and 0.9983, respectively. Consequently, this model can be very valuable to have accurate prediction of waste HHV value. [ABSTRACT FROM AUTHOR]

The present study is proposed to develop the Adaptive Neuro-Fuzzy Inference System optimized by genetic algorithm to estimate CO2value in permeate stream using a hollow fiber polymeric membrane for separation of binary gas containing CO2and CH4in natural gas. To that end, a number of 65 samples was gathered from the literature. Results indicated that the proposed ANFIS model has great potential with high correlation (R2 = 0.9993) and less error (RMSE = 0.0064) for estimation of aforementioned parameter. [ABSTRACT FROM PUBLISHER]

Wax deposition in petroleum industry is one of the major problems requiring accurate predictive procedures to reduce the deficiencies and effective designing of the process. An adaptive neuro fuzzy inference system (ANFIS) model is proposed to predict the wax deposition in oily systems. Parameters of the ANFIS model are optimized using the particle swarm optimization (PSO) method. Results are then compared to those previously reported by Kamari et al., demonstrating better performance of the proposed ANFIS model. Statistical and graphical approaches are employed to investigate the reliability of the proposed model, illustrating the model's capability of precise estimation of the wax deposition. Coefficient of determination (R2) and mean squared error (MSE) values of 0.994 and 0.053 are obtained for the proposed ANFIS model, revealing the reliable prediction of wax deposition by the proposed ANFIS model. [ABSTRACT FROM PUBLISHER]

Owning to interesting properties of biosurfactants such as biodegradability and lower toxicity, they have broad application in the food industry, healthy products, and bioremediation as well as for oil recovery. The present study was aimed to develop a GA-ANFIS model for predicting the breakthrough curves for rhamnolipid adsorption over activated carbon. To that end, a set of 296 adsorption data points were utilized to train the proposed FIS structure. Different graphical and statistical methods were also used to evaluate the model’s accuracy and reliability. Results were then compared to those of the previously reported Artificial Neural Network (ANN) and Group Method Data Handling (GMDH) models. Absolute average deviation percentage (%AAD) for the proposed model was 1.71% which demonstrates lower value compared to those of ANN and GMDH models. The present ANFIS model can be of immense value for investigating breakthrough curve of rhamnolipid and also it can help chemist who dealing with biosurfactants. [ABSTRACT FROM AUTHOR]

Water existence in natural gas may cause difficulties in processing facilities and also transmission through pipelines. Therefore, it will be important to find a way to estimate water content values. An intelligent learning Adaptive Network-based Fuzzy Inference System (ANFIS) is introduced to estimate water content under a given temperature and pressure condition. Assessment of model's accuracy is carried out by determining mean relative error as 4.08% andR-squared value as 0.9996. Statistical analyses indicate the brilliant predictive ability of suggested ANFIS model. In addition, a comparison of our model's outcomes with other existence correlations also confirmed its satisfactory predictions. [ABSTRACT FROM AUTHOR]

Research for finding alternative fuel sources has been concluded that the renewable fuels such as biodiesel can be used as an alternative to fossil fuels because of the energy security reasons and environmental benefits. In the present study, a modeling study based on statistical learning theory has been investigated by the adaptive neuro-fuzzy interference system (ANFIS) approach for biodiesel production in non-catalytic supercritical methanol (SCM) method. This model has been applied for estimating the biodiesel yield as a function of temperature, pressure, reaction time, and Methanol/oil ratio. The results, the high value of R-squared (0.9978) and low value of absolute deviation (1.14%), support the suggested ANFIS model for being an effective approach for prediction of the biodiesel yield. A comparison between our model and another previous ANN-based model has been also carried out that indicates a great agreement of estimations of both models. [ABSTRACT FROM PUBLISHER]

The bitumen and heavy oil reservoirs are more in number than light crude oil reservoirs in the world. To increase the empty space between molecules and decrease viscosity, the bitumen was diluted with a liquid solvent such as tetradecane. Due to the sensitivity of enhanced oil recovery process, the accurate approximation for the viscosity of mentioned mixture is important. The purpose of this study was to develop an effective relation between the viscosity of Athabasca bitumen and heavy n-alkane mixtures based on pressure, temperature, and the weight percentage of n-tetradecane using the adaptive neuro-fuzzy inference system method. For this model, the value of MRE andR2was obtained as 0.34% and 1.00, respectively; so this model can be applied as an accurate approximation for any mixture of heavy oil with a liquid solvent. [ABSTRACT FROM AUTHOR]

Amino acid salt, especially sodium glycinate, was known as a new class of environment-friendly solution that is now being studied as a favorable alternative to amines. In the present collaboration, the Adaptive Network-based Fuzzy Inference System (ANFIS) was employed to estimate CO2loading capacity in the presence of aqueous sodium glycinate solution under broad ranges of temperature and pressure. The outcomes of suggested ANFIS model indicated their brilliant agreement with corresponding experimental values. The calculated values of mean relative error and R-squared were 2.93 and 0.988, respectively. Our suggested model can be of huge value for process engineers to have a simple and accurate tool in order to have rapid estimations of CO2solubility as a function of temperature, pressure, and mass composition of sodium glycinate solution. [ABSTRACT FROM AUTHOR]

Recent investigations have proved more worldwide availability of heavy crude oil resources such as bitumen than those with conventional crude oil. Diluting the bitumen through injection of solvents including tetradecane into such reservoirs to decrease the density and viscosity of bitumen has been found to be an efficient enhanced oil recovery approach. This study focuses on introducing an effective and robust density predictive method for Athabasca bitumen-tetradecane mixtures against pressure, temperature and solvent weight percent through implementation of adaptive neuro-fuzzy interference system technique. The emerged results of proposed model were compared to experimentally reported and correlation-based density values in different conditions. Values of 0.003805 and 1.00 were achieved for mean square error and R2, respectively. The developed model is therefore regarded as a highly appropriate tool for the purpose of bitumen-tetradecane mixture density estimation. [ABSTRACT FROM PUBLISHER]

The aim of this study was to utilize the adaptive neuro-fuzzy inference system to estimate the vaporization enthalpy of petroleum fractions and pure hydrocarbons. This tool predicts the vaporization enthalpy as function of the specific gravity, molecular weight, and boiling point temperature based on 122 data gathered from the previous published literatures. Moreover, a comparison was carried out between the present model and some popular models. Results fromthe adaptive neuro-fuzzy inference systemmodel showed its better predictive capability compared to previous models. The obtained values of root mean square error and R2 were 0.588 and 0.9934, respectively. This tool is simple to apply and can be of massive evaluation for petroleum engineers to have a great approximation of vaporization enthalpy of pure hydrocarbons hydrocarbon fractions. [ABSTRACT FROM AUTHOR]

To appropriate design and satisfactory performance of utilities in the gas processing and transmission plants, a crucial factor that should be taken in consideration is the natural gas water content. The present research aimed to develop a precise strategy for estimating sour gas/sweet gas water content ratio. This developed predictive tool is based on adaptive neuro-fuzzy inference system (ANFIS). In this regard, a comprehensive data bank that contains 1,126 data points was collected. This model predicts ratio of sour gas to sweet gas as function of pressure, temperature, and equilibrium H2S mole fraction. The ranges of pressure and temperature were 200–70000 KPa and 10–150°C, respectively. In addition, the equilibrium H2S mole fraction ranges between 0.076 and 0.492. Results obtained from the ANFIS model confirmed acceptable and reasonable predictive capability of this model. This tool is simple to use and can be help petroleum engineers to predict water content of natural gas at broad ranges of conditions. [ABSTRACT FROM PUBLISHER]

The aim of this contribution was to develop a simple tool based on fuzzy logic concepts to predict true vapor pressure of volatile petroleum products. In this regard, the adaptive neuro fuzzy inference system was evolved to estimate the true vapor pressure of volatile petroleum products as function of temperature and Reid vapor pressure. In addition, to determine optimal membership function parameters, the particle swarm optimization as an amazing evolutionary algorithm was applied. This predictive tool is suggested as a precise technique to measure the true vapor pressures of typical liquefied petroleum gases, natural gasoline, and motor fuel components at broad ranges of temperatures. This technique was trained and tested by 156 set of data points collected from the reference. The temperature range is 253–373 K and the range of Reid vapor pressure is 35–250 KPa. Results obtained from the present tool found to be in acceptable agreement with the actual reported data in the literature. The values of root mean square error and regression coefficient obtained 5.34 and 0.9975, respectively. [ABSTRACT FROM PUBLISHER]

Substituting conventional solvents for gas sweetening with ionic liquids (ILs) is an interesting way to specify superior design from energy consumption in regeneration and reduction solvent loss. In this study, based on the critical temperature (T c ), critical pressure (Pc), and molecular weight (Mw) of pure ionic liquids, a feed forward Multi-Layer Perceptron Artificial Neural Network (MLP-ANN), an Adaptive Neuro-Fuzzy Inference System (ANFIS) and a Radial Basis Function Artificial Neural Network (RBF-ANN) were developed to predict solubility of Hydrogen Sulfide in the presence of various ILs over wide ranges of temperature, pressure and concentration. To develop the aforementioned methods, 664 experimental data points collected from the literatures were employed. Moreover, to investigate the Hydrogen Sulfide solubility in ternary mixture containing Carbon Dioxide, Hydrogen Sulfide and ILs, MLP-ANN model was proposed. To propose MLP-ANN method for estimating H 2 S solubility in ternary mixture, 89 experimental data points collected from the previous published works were employed. To examine the ability of the methods suggested in this study different statistical criteria including R-Squared (R 2 ), Mean Squared Error (MSE), Standard Deviation (STD) and Mean Absolute Relative Error (MARE) were used. The values of R 2 and MSE achieved for the MLP-ANN model are 0.9951 and 0.000117 respectively. Furthermore, the values of R 2 and MSE for both ANFIS and RBF-ANN methods obtained 0.901, 0.002268 and 0.9679, 0.000787 respectively. In addition, R 2 and MSE of the MLP-ANN model for ternary mixtures are 0.9955 and 0.000082 correspondingly. Therefore, the ability and acceptable performance of using the MLP-ANN as an accurate model for estimating Hydrogen Sulfide solubility in ILs was showed versus other computational intelligence models. [ABSTRACT FROM AUTHOR]

Ionic liquids (ILs) are highly promising for industrial applications such as design and development of gas sweetening processes. For a safe and economical design, prediction of carbon dioxide solubility by a trustworthy model is really essential. In this research, based on the pressure and temperature of system and the critical properties such as critical temperature ( T c ) and critical pressure ( P c ) and also acentric factor ( ω ) and molecular weight (Mw) of pure ionic liquids, a multi-layer perceptron artificial neural network (MLP-ANN) and an adaptive neuro-fuzzy interference system (ANFIS) have been developed to estimate carbon dioxide solubility in presence of various ILs over wide ranges of pressure, temperature and concentration. To this end, 728 experimental data points collected from the literature have been used for implementation of these models. To verify the proposed models, regression analysis has been conducted on the experimental and predicted solubility of carbon dioxide in ILs. Moreover, in this study, a comparison between experimental carbon dioxide solubilities and predicted values of carbon dioxide solubility by thermodynamic models based on Peng–Robinson (PR) and Soave–Redlich–Kwong (SRK) equation of states has been performed. For MLP-ANN, coefficient of determination ( R 2 ) between experimental and predicted values is 0.9972 and mean squared errors (MSEs) is 0.000133 and the values of R 2 = 0.9336 and MSE = 0.002942 were obtained for ANFIS model while, the values of R 2 and MSE for PR-EOS were 0.7323 and 0.002702 respectively, and also, R 2 = 0.6989 and MSE = 0.005578 were obtained for SRK-EOS model. Therefore, in current study, ability and better performance of MLP-ANN as an accurate correlation for estimating carbon dioxide solubility in ILs was showed against other alternative models. [ABSTRACT FROM AUTHOR]

Conventional working fluids which are used in the heat transfer mediums have restricted the ability of heat removal. In this investigation, thermal performance of TiO 2 nanoparticles immersed in DI (de-ionized) water was evaluated. Introducing a combination of experimental and modeling approaches to forecast the amount of thermal conductivity using four different neural networks can be mentioned as the predominant aim of this investigation. Between MLP-ANN, ANFIS, LSSVM, and RBF-ANN Methods, the LSSVM produced better results with the lowest deviation factor and reflected the most accurate responses between the proposed models. The regression diagram of experimental and estimated values shows an R2 value of 0.9806 for training sets and 0.9579 for testing sections of the ANFIS method in part a, and in the b, c and d parts of the diagram, coefficients of determination were 0.9893 & 0.9967 and 0.9974 & 0.9992 and 0.9996 & 0.9989 for train and test stages of MLP-ANN, RBF-ANN and LSSVM models, respectively. Also, the effects of different parameters were investigated using a sensitivity analysis method which demonstrates that the temperature is the most affecting parameter on the thermal conductivity with a relevancy factor of 0.66866. • Thermal performance of TiO 2 nano-particles in de-ionized water is evaluated. • Presenting a combined method to predict thermal conductivity. • MLP, ANFIS, LSSVM, and RBF methods are applied to predict thermal conductivity. • Temperature is monitored to be the most affecting parameter on thermal conductivity. [ABSTRACT FROM AUTHOR]

One of the auspicious nanomaterials which has exceptionally enticed researchers is carbon nanotubes (CNTs) as the result of their excellent thermal properties. In this investigation, an experiment was carried out on three kinds of CNTs-nanofluids with various CNTs added to de-ionized water to compared and analyze their thermal conductivity properties. The main purpose of this study was to introduce a combination of experimental and modelling approaches to forecast the amount of thermal conductivity using four different neural networks. Between MLP-ANN, ANFIS, LSSVM, and RBF-ANN Methods, it was found that the LSSVM produced better results with the lowest deviation factor and reflected the most accurate responses between the proposed models. the regression diagram of experimental and estimated values shows an R2 coefficient of 0.9806 and 0.9579 for training and testing sections of the ANFIS method in part a, and in the b, c and d parts of the diagram, coefficients of determination were 0.9893& 0.9967 and 0.9974 & 0.9992 and 0.9996& 0.9989 for training and testing part of MLP-ANN, RBF-ANN and LSSVM models. Also, the effect of different parameters was investigated using a sensitivity analysis method which demonstrates that the temperature is the most affecting parameter on the thermal conductivity with a relevancy factor of 0.66866. [ABSTRACT FROM AUTHOR]