Article
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Accurate estimation of interfacial tension (IFT) in crude oil/brine system is of great importance for many processes in petroleum and chemical engineering. The current study plays emphasis on introducing the "Gradient Boosting Decision Tree (GBDT)" and ''Adaptive Boosting Support Vector Regression (AdaBoost SVR)" as novel powerful machine learning tools to determine the IFT of crude oil/brine system. Two sorts of models have been developed using each of these two data-driven methods. The first kind includes six inputs, namely pressure (P), temperature (T) and four parameters describing the proprieties of crude oil (total acid number (TAN) and specific gravity (SG) and brine (NaCl equivalent salinity () and pH), while the second kind deals with four inputs (without including pH and TAN). To this end, an extensive databank including 560 experimental points was considered , in which 80% of the points were employed for the training phase and the remaining part was utilized as blind test data. Results revealed that the proposed approaches provide very satisfactory predictions, and the implemented GBDT model with six inputs is the most accurate model of all with an average absolute relative error of 1.01%. Moreover, the outcomes of the GBDT model are better than literature models. Finally, outlier diagnostic using Leverage approach was performed to investigate the applicability domain of the GBDT model and to evaluate the quality of employed data.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Boosting method is a variant of ensemble approach that was proposed by Schapire [36]. This method fundamentally aims at combining underperforming predictors, which are also termed as "learner", to establish another predictor with better performance [37,38]. In a simpler term, these weak predictors would undergo sequential training phase in which each predictor emphasizes on rectifying the previous predictors. ...
... This denotes that a predefined loss function is minimized by adding a new predictor at each iteration of gradient descent to attain better training outcome [39]. Basically, residual errors (the difference between actual output i n t e r n a t i o n a l j o u r n a l o f h y d r o g e n e n e r g y 4 7 ( 2 0 2 2 ) 3 9 5 9 5 e3 9 6 0 5 and predicted output) produced by the previous predictor would apply to the new predictor [38]. For a more vivid explanation, the algorithm of GBR is summarized as follows: ...
Article
Full-text available
During the last years, there has been a surge of interest in cleaner ways for producing energy in order to successfully handle the climate issues caused by the consumption of fossil fuels. The production of hydrogen (H 2) is among the techniques which have grown up as attractive strategies towards energy transition. In this context, underground hydrogen storage (UHS) in saline aquifers has turned into one of the greatest challenges in the context of conserving energy for later use. The interfacial tension (IFT) of the H 2-brine system is a paramount parameter which affects greatly the successful design and implementation of UHS. In this study, robust machine learning (ML) techniques, viz., genetic programming (GP), gradient boosting regressor (GBR), and multilayer perceptron (MLP) optimized with Levenberg-Marquardt (LMA) and Adaptive Moment Estimation (Adam) algorithms were implemented for establishing accurate paradigms to predict the IFT of the H 2-brine system. The obtained results exhibited that the proposed models and correlation provide excellent estimations of the IFT. In addition, it was deduced that MLP-LMA out-performs the other models and the existing correlation in the literature. MLP-LMA yielded R 2 and AAPRE values of 0.9997 and 0.1907%, respectively. Lastly, the trend analysis demonstrated the physical coherence and tendency of the predictions of MLP-LMA.
... In the following section, some of the recent models in this area are briefly reviewed. It should be noted, as the dominant fluids that exist in the reservoir are oil and water, that the majority of ML models were developed to predict the IFT in oil−brine [22,23], water−hydrocarbon [24,25], brine−hydrocarbon [26][27][28], and CO 2 −brine [29][30][31][32] systems. Ahmadi and Mahmoudi [33] predicted the gas-oil IFT with least squares support vector machines (LSSVM) as a well-known ML method. ...
... Artificial neural networks (ANNs) are a subset of ML and are at the heart of DL algorithms [40]. In the last decades, a wide range of engineering problems has been solved by inductive ML algorithms [23,24,41]. ANNs are suited towards tasks that include fuzzy or incomplete information, complex and ill-defined problems, and incomplete data sets, where they are usually decided on a visional basis. ...
Article
Full-text available
The combustion of fossil fuels from the input of oil refineries, power plants, and the venting or flaring of produced gases in oil fields leads to greenhouse gas emissions. Economic usage of greenhouse and flue gases in conventional and unconventional reservoirs would not only enhance the oil and gas recovery but also offers CO2 sequestration. In this regard, the accurate estimation of the interfacial tension (IFT) between the injected gases and the crude oils is crucial for the successful execution of injection scenarios in enhanced oil recovery (EOR) operations. In this paper, the IFT between a CO2/N2 mixture and n-alkanes at different pressures and temperatures is investigated by utilizing machine learning (ML) methods. To this end, a data set containing 268 IFT data was gathered from the literature. Pressure, temperature, the carbon number of n-alkanes, and the mole fraction of N2 were selected as the input parameters. Then, six well-known ML methods (radial basis function (RBF), the adaptive neuro-fuzzy inference system (ANFIS), the least square support vector machine (LSSVM), random forest (RF), multilayer perceptron (MLP), and extremely randomized tree (extra-tree)) were used along with four optimization methods (colliding bodies optimization (CBO), particle swarm optimization (PSO), the Levenberg–Marquardt (LM) algorithm, and coupled simulated annealing (CSA)) to model the IFT of the CO2/N2 mixture and n-alkanes. The RBF model predicted all the IFT values with exceptional precision with an average absolute relative error of 0.77%, and also outperformed all other models in this paper and available in the literature. Furthermore, it was found that the pressure and the carbon number of n-alkanes would show the highest influence on the IFT of the CO2/N2 and n-alkanes, based on sensitivity analysis. Finally, the utilized IFT database and the area of the RBF model applicability were investigated via the leverage method.
... Also, in 2019, the prediction of IFT between oil and brine was the interest of several studies. Kiomarsiyan and Esfandiarian [211], Abooali et al. [212], and Amar et al. [213] were the scholars who attempted to forecast the IFT in oil/brine systems with the aid of intelligent models. Kiomarsiyan and Esfandiarian [211] utilized a grid partitioning based FIS to predict the IFT in oil/brine systems as a function of P, T, the carbon number of hydrocarbon, and ionic strength of brine. ...
... Fig. 4.31 shows the absolute relative deviation versus the number of testing subset. Amar et al. [213] introduced two novel intelligent models, namely, adaptive boosting support vector regression (AdaBoost SVR) and gradient boosting DT (GBDT), to model the IFT between crude oil and brine. Two sets of IFT models were developed through each of these models. ...
Book
Applications of Artificial Intelligence Techniques in the Petroleum Industry gives engineers a critical resource to help them understand the machine learning that will solve specific engineering challenges. The reference begins with fundamentals, covering preprocessing of data, types of intelligent models, and training and optimization algorithms. The book moves on to methodically address artificial intelligence technology and applications by the upstream sector, covering exploration, drilling, reservoir and production engineering. Final sections cover current gaps and future challenges. Key Features Teaches how to apply machine learning algorithms that work best in exploration, drilling, reservoir or production engineering. Helps readers increase their existing knowledge on intelligent data modeling, machine learning and artificial intelligence, with foundational chapters covering the preprocessing of data and training on algorithms. Provides tactics on how to cover complex projects such as shale gas, tight oils, and other types of unconventional reservoirs with more advanced model input.
... In the above equations, is the predicted value of the model for input , while the is the training data for . This nature-inspired algorithm can be employed to solve both classification and regression problems [38]. This algorithm contains internal nodes, leaf nodes, root nodes, and branches. ...
... Schematic illustration of a typical decision tree3.5.1. Gradient BoostingGradient boosting works like a functional gradient descent that applies a new learner to residual errors made by the previous learner to minimize a certain loss at each step of gradient descent[38]. Like other boosting techniques, various loss functions can be considered. ...
Article
Water-flooding is one of the main options employed by the oil industry to meet the world's ever-increasing demand for oil, as the primary source of energy. This approach is highly prone to cause formation damage if the injected water is not compatible with the formation brine. In this study, decision tree optimized with gradient boosting (GBDT), cascade-forward back-propagation network (CFBPN), and generalized regression neural networks (GRNN) were employed, as relatively novel intelligent models, for the first time to develop accurate models to estimate the formation damage during a waterflooding operation in terms of damaged permeability. To compare the performance of these models, radial basis function (RBF) and multilayer perceptron (MLP) neural networks were also developed. The Levenberg-Marquardt algorithm (LMA), scaled conjugate gradient (SCG), and Bayesian regularization (BR) were used for training the MLP and CFBPN models. The results of this study showed the outperformance of the proposed GBDT model compared to the other developed models as well as previously proposed ones with an average absolute percent relative error (AAPRE) of 0.1465 % and correlation coefficient (R²) of 0.9991 for the whole dataset. According to the results, the accuracy of the developed models could be ranked as follows: GBDT > CFBPN-LM > CFBPN-BR > RBF > MLP-LM > GRNN > MLP-BR > CFBPN-SCG > MLP-SCG. Moreover, it was shown that the GBDT mode could estimate more than 90 % of points with an absolute relative error of lower than 0.5 %. The trend analysis showed the high capability of the developed models in detecting the physical trend of the formation damage with variation of inputs. Then, the variable impact analysis was performed for this model, and the results reflect the high dependency of the model's predictions on the volume of injected water (Vinj), initial permeability (Ki), and ionic concentration of sulfate. Lastly, the Leverage approach was employed to determine suspected points as well as the applicability realm of the GBDT model. The results of the outlier detection indicated that only 4 points (0.93 % of the dataset) were detected as outliers, and the applicability realm of the proposed GBDT was verified. The findings of this communication shed light on the application of intelligent models and their power in predicting the formation damage caused during water-flooding operations before their occurrence.
... Decision tree (DT) is another intelligent model that is inspired by the nature, which is usable in classification as well as regression problems [34]. A DT is comprised of a root node, internal nodes, and leaf (terminal) nodes. ...
... This supervised optimization algorithm employs predictive models as weak models for regression and classification problems. Based on the functional gradient descent concept, the gradient boosting algorithm minimizes a specific loss by assigning a new learner to residual errors shown by a prior learner [34]. This approach can employ various kinds of loss functions. ...
Article
Full-text available
Surfactant-polymer flooding is one of the most important enhanced oil recovery (EOR) techniques, which refers to the injection of surfactant slugs and polymer drives. Two crucial decision-making parameters in EOR operations are net present value (NPV) and oil recovery factor (RF). Herein, various intelligent models, based on multilayer perceptron (MLP), cascade neural network (CNN), radial basis function (RBF), neural networks as well as support vector regression (SVR), and decision tree (DT) algorithms are proposed toward estimating these two parameters with respect to polymer drive size, surfactant slug size, the salinity of polymer drive, Kv/Kh ratio, surfactant concentration, and polymer concentration in polymer drive and surfactant slug. The results exhibited the outperformance of the CNN model trained with the Levenberg Marquardt algorithm in forecasting the RF and NPV with average absolute errors of 0.66% and 1.95%, respectively. Moreover, the results of the sensitivity analysis reflected that the most effective inputs on the predicted value of RF were surfactant concentration and surfactant slug size, while surfactant concentration and polymer concentration in surfactant slug could considerably affect the NPV model’s output. Lastly, the outlier detection analysis revealed that the employed data is valid and only two points were detected as outliers.
... The GBDT is an ensemble method that combines a number of base estimators (decision trees) with the gradient boosting algorithm in order to improve the robustness over a single estimator. The GBDT has empirically proven to be highly efficient and promising for solving various regression and classification problems in the field of energy and petroleum engineering [22,23]. However, to the best knowledge of the authors, the application of GBDT in estimating the adsorption isotherm has not yet been reported. ...
Article
Full-text available
The accurate determination of methane adsorption isotherms in coals is crucial for both the evaluation of underground coalbed methane (CBM) reserves and design of development strategies for enhancing CBM recovery. However, the experimental measurement of high-pressure methane adsorption isotherms is extremely tedious and time-consuming. This paper proposed the use of an ensemble machine learning (ML) method, namely the gradient boosting decision tree (GBDT), in order to accurately estimate methane adsorption isotherms based on coal properties in the Qinshui basin, China. The GBDT method was trained to correlate the adsorption amount with coal properties (ash, fixed carbon, moisture, vitrinite, and vitrinite reflectance) and experimental conditions (pressure, equilibrium moisture, and temperature). The results show that the estimated adsorption amounts agree well with the experimental ones, which prove the accuracy and robustness of the GBDT method. A comparison of the GBDT with two commonly used ML methods, namely the artificial neural network (ANN) and support vector machine (SVM), confirms the superiority of GBDT in terms of generalization capability and robustness. Furthermore, relative importance scanning and univariate analysis based on the constructed GBDT model were conducted, which showed that the fixed carbon and ash contents are primary factors that significantly affect the adsorption isotherms for the coal samples in this study.
... The impact of each variable, partitioned into sub-intervals, on group error for HFT prediction by GEP-based correlation is examined in Figure 7. Besides, Figure 8 GEP In another step, a comparison was carried out between the performance of the proposed GEPbased correlation with the different preexisting approaches in the literature, namely those proposed by Berge [41], Motiee [45], Safamirzaei [50], Towler and Mokhatab [47], Salufu and Nwakwo [49], Baillie and Wichert [43], and Mann et al. [44]. The comparison was done for the whole database, and the statistical performance gained from the aforementioned models is reported in Table 5 and illustrated graphically in the bar plots of Figure 9. Table 5 and Figure 9 clearly reveal that GEP-based correlation has the highest integrity and efficiency Examining and defining the applicability realm of a proposed paradigm, and distinguishing any suspected data from the employed experimental measurements, is a paramount step to prove the statistical validity of a model and delineate its coverage with respect to the variables [91][92][93][94][95]. To this end, outliers detection, which allows the identification of individual datums that can be doubtful due to the errors and uncertainties of the experimental tasks, is frequently conducted [96,97]. ...
Article
The accurate determination of hydrate formation temperature (HFT) is an extremely vital step in the context of designing processes containing hydrates. Due to the prohibitive time and the expensive cost of the experimental procedures, some empirical and theoretical approaches have been developed for estimating HFT. However, most of these prior approaches are associated with a lack of generalization, low accuracy, and the non-consideration of some paramount impacting factors. In this study, a reliable and simple-to-use correlation was implemented for predicting HFT of different natural gas types, including sour, acid, and sweet gases. The correlation was established using a powerful explicit-based machine learning technique, namely gene expression programming (GEP). A widespread database encompassing 279 experimental measurements was employed in the learning and testing phases of this method. Results showed that the outcomes of the correlation cohered with the real measurements of HFT. Besides, it was found that GEP-based correlation provided excellent prediction performance and it outperformed the best preexisting models. GEP-based correlation can predict HFT with an average absolute relative error (AARE) of 0.1397%. In addition, the generated hydrate curves by GEP-based correlation overlapped the real ones with a high degree of accuracy. Lastly, the statistical validity of GEP-based correlation was documented using outliers detection.
... As a result, the outcomes corresponding to several independent runs of the mixed method are similar. To test the robustness and stability, the process of the hybrid algorithm is computed with 20 repetitions [45][46][47]. The computational steps of the AdaBoost.RT-BP and Adaboost-SVR can be find in the supplementary materials. ...
Article
Full-text available
Different cultivars of pear trees are often planted in one orchard to enhance yield for its gametophytic self-incompatibility. Therefore, an accurate and robust modelling method is needed for the non-destructive determination of leaf nitrogen (N) concentration in pear orchards with mixed cultivars. This study proposes a new technique based on in-field visible-near infrared (VIS-NIR) spectroscopy and the Adaboost algorithm initiated with machine learning methods. The performance was evaluated by estimating leaf N concentration for a total of 1285 samples from different cultivars, growth regions, and tree ages and compared with traditional techniques, including vegetation indices, partial least squares regression, singular support vector regression (SVR) and neural networks (NN). The results demonstrated that the leaf reflectance responded to the leaf nitrogen concentration were more sensitive to the types of cultivars than to the different growing regions and tree ages. Moreover, the AdaBoost.RT-BP had the best accuracy in both the training (R 2 = 0.96, root mean relative error (RMSE) = 1.03 g kg −1) and the test datasets (R 2 = 0.91, RMSE = 1.29 g kg −1), and was the most robust in repeated experiments. This study provides a new insight for monitoring the status of pear trees by the in-field VIS-NIR spectroscopy for better N managements in heterogeneous pear orchards.
... In 1984, the classification and regression tree (CART) was introduced as a supervised non-parametric learning algorithm (Breiman et al., 1984), which can be applied to regression and classification problems (Amar et al., 2019). A decision tree is called "The regression tree (RT)" or "The classification tree (CT)" based on the problem they are applied to (Hemmati-Sarapardeh et al., 2020a). ...
Article
No one can deny the ever-increasing importance of oil since it has influenced every aspect of humans' life. One of the most important pressure-volume-temperature (PVT) properties of crude oil, which is needed in a majority of production and reservoir engineering calculations, is the saturation pressure (bubble point pressure (Pb)). Having accurate knowledge about Pb is significant for both academia and industry. This communication concentrates on providing reliable experimental data from constant composition expansion (CCE) test as well as rigorous compositional models to predict saturation pressure of crude oils based on oil composition (H2S, N2, CO2, C1 to C7+), reservoir temperature, C7+ specifications (molecular weight and specific gravity). Seven advanced machine learning approaches, namely, decision trees (DTs), random forest (RF), extra trees (ETs), cascade-forward back-propagation network (CFBPN), and generalized regression neural networks (GRNN) as well as multilayer perceptron (MLP) and radial basis function (RBF) neural networks were used for modeling. The CFBPN and MLP models were trained by three different training algorithms, namely scaled conjugate gradient (SCG), Bayesian regularization (BR), and Levenberg-Marquardt (LM). The modeling was done based on a databank consisting of 206 data points (130 points were previously published in the literature plus 76 points determined experimentally in this study). The results show that the DT model could provide the most reliable prediction with an average absolute percent relative error (AAPRE) of 4.43%. The efficiency of various equations of state (EoS) and empirical correlations were checked. According to the results, Peng-Robinson (PR) and the correlation developed by Elsharkawy were the most efficient EoS and empirical correlation with AAPRE values of 8.46% and 12.05%, respectively. Then, the sensitivity analysis revealed that the Pb was extremely affected by methane and C7+ mole percent. Finally, the Leverage approach confirmed the validity of the employed data, detecting only 7 points as outliers.
... Finally, outlier detection was conducted to determine the statistical validity of the GRNN model and the dataset upon which it was based. Because of its accuracy [81], the leverage approach was useed to detect outliers in this study and subsequently visualized using a Williams plot [82][83][84]. In this diagram, the standardized residual (R) values resulting from model predictions are mapped in relation to hat (H) values, which denote the diagonal elements of the hat matrix and are described as follows [81,85]: ...
Article
Geological carbon dioxide (CO2) storage (GCS) in saline aquifers has been recognized as a promising way to slow down global CO2 emissions. The residual and solubility trapping efficiency of CO2 in saline aquifers play a crucial role in monitoring CO2 sequestration performance. Due to this fact, the goal of this paper is to determine the effectiveness of three robust machine learning (ML) models — a general regression neural network (GRNN) model and two multilayer perceptron (MLP) models respectively optimized with the Levenberg-Marquardt algorithm (LMA) and Bayesian Regularization (BR) — in predicting the residual trapping index (RTI) and solubility trapping index (STI) of CO2 in saline aquifers. A comprehensive and wide-ranging dataset was compiled from the literature, including over 1,910 simulation samples from numerous CO2 field models. The predicted results revealed that all the proposed ML techniques have an excellent agreement with simulation data. In addition, the error analyses and a comparison of statistical indicators indicated that the GRNN model was more accurate than the MLP-LMA and MLP-BR models as well as two ML models developed in previous studies. The GRNN model exhibited overall coefficient of determination (R2) values of 0.9995 and 0.9998 and average absolute relative error (ARE) percentages of 0.7413% and 0.2950% for RTI and STI, respectively. Furthermore, a trend analysis confirmed the robustness of the GRNN model, as predicted and simulated RTI and STI exhibited strong overlap under four different sets of input parameters. Moreover, the Williams plot reveals that the validity of GRNN model was affirmed, and only a small suspected data was detected from the collected database. Therefore, the GRNN model proposed in this study could serve as a template for evaluating the feasibility of future GCS projects in saline aquifers. Lastly, the findings of this study can help better understanding the promising of machine learning techniques for predicting CO2 trapping efficiency in geological storage sites. https://authors.elsevier.com/a/1eW1Q3iH4IDIR
... Decision tree (DT). Decision Tree, a nature-inspired supervised learning algorithm, has been widely utilized in the literature and can be used for classification and regression 57 . This algorithm consists of four elements: root node, which is the topmost node in the tree carrying the input data; leaf nodes, which are the final section of the flowchart and denotes the output of the system; internal nodes, which are placed between the root and leaf nodes; branches, which are the connection between nodes. ...
Article
Full-text available
Determining the solubility of non-hydrocarbon gases such as carbon dioxide (CO2) and nitrogen (N2) in water and brine is one of the most controversial challenges in the oil and chemical industries. Although many researches have been conducted on solubility of gases in brine and water, very few researches investigated the solubility of power plant flue gases (CO2–N2 mixtures) in aqueous solutions. In this study, using six intelligent models, including Random Forest, Decision Tree (DT), Gradient Boosting-Decision Tree (GB-DT), Adaptive Boosting-Decision Tree (AdaBoost-DT), Adaptive Boosting-Support Vector Regression (AdaBoost-SVR), and Gradient Boosting-Support Vector Regression (GB-SVR), the solubility of CO2–N2 mixtures in water and brine solutions was predicted, and the results were compared with four equations of state (EOSs), including Peng–Robinson (PR), Soave–Redlich–Kwong (SRK), Valderrama–Patel–Teja (VPT), and Perturbed-Chain Statistical Associating Fluid Theory (PC-SAFT). The results indicate that the Random Forest model with an average absolute percent relative error (AAPRE) value of 2.8% has the best predictions. The GB-SVR and DT models also have good precision with AAPRE values of 6.43% and 7.41%, respectively. For solubility of CO2 present in gaseous mixtures in aqueous systems, the PC-SAFT model, and for solubility of N2, the VPT EOS had the best results among the EOSs. Also, the sensitivity analysis of input parameters showed that increasing the mole percent of CO2 in gaseous phase, temperature, pressure, and decreasing the ionic strength increase the solubility of CO2–N2 mixture in water and brine solutions. Another significant issue is that increasing the salinity of brine also has a subtractive effect on the solubility of CO2–N2 mixture. Finally, the Leverage method proved that the actual data are of excellent quality and the Random Forest approach is quite reliable for determining the solubility of the CO2–N2 gas mixtures in aqueous systems.
... It's noteworthy, however, that the miniaturized tree may encounter the so-called horizon effect problem, in which the DT might not comprehensively model the given target. The interested readers are referred to the literature for further information in this regard [30,31]. ...
Article
Full-text available
Gas injection has emerged over the recent decades as a promising technology to enhance oil recovery in various fields worldwide. The efficiency and success of a gas injection operation can be assessed through a number of vital experimental studies. Interfacial Tension (IFT) between the injected gas and the displacing fluid is a key parameter playing an eminent role in the foregoing studies. The main scope of this work is making a progress in modeling the IFTs between diverse n-alkanes and Methane (CH4), Carbon Dioxide (CO2), and Nitrogen (N2) natural gases. For this purpose, two smart AI-based approaches of Cascaded Feedforward Neural Network (CFNN) and Decision Tree Learning (DT) were used to simultaneously model the IFTs between foregoing immiscible binary systems as a function of pressure, temperature, the gases properties, and the properties of the liquid. Several statistical measures and graphical descriptions were employed to aid the accuracy analysis of the proposed models. Both developed CFNN and DT networks represented desirable close-to-reality predictions in all binary systems. Besides, CFNN established itself as the most robust model for all studies binary systems with RMSE values of 0.5924, 0.5649, and 0.5870 mN/m, and R² values of 0.9902, 0.9910, and 0.9904 for the train, test, and overall data, respectively.
... In 1984, Breiman et al. introduced a new supervised non-parametric learning algorithm, namely, the classification and regression tree (CART), 22 which is applicable to both classification and regression problems. 23 With respect to the problem they are being applied to, a decision tree is termed "The classification tree (CT)" or "The regression tree (RT)". 24 Variable selection, data manipulation, handling of missing values, and prediction were among the most popular fields in which DTs have been employed 25 owing to their simplicity, interpretability, ability to provide graphical representation, and low computational cost. ...
Article
Full-text available
This communication primarily concentrates on developing reliable and accurate compositional oil formation volume factor (Bo) models using several advanced and powerful machine learning (ML) models, namely, extra trees (ETs), random forest (RF), decision trees (DTs), generalized regression neural networks, and cascade-forward back-propagation network, alongside radial basis function and multilayer perceptron neural networks. Along with these models, seven equations of state (EoSs) were employed to estimate Bo. The performance of the developed ML models and employed EoSs was assessed through various statistical and graphical evaluations. Overall, the ML models could provide much more accurate predictions in comparison to EoSs. However, the results indicated that tree-based models, specifically ET models, could outperform the other models and can be reliably applied for estimating Bo. The most reliable ET model could predict Bo with a total average error of 1.17%. Lastly, the outlier detection approach verified the dataset’s consistency detecting only 17 (out of 1224) data points as outliers for the proposed Bo models.
... Figure 1 presents a schematic image of the proposed AdaBoost-SVR in this study. 75 is derived from natural sources and may be used to tackle both regression and classification problems. Root nodes, leaf nodes, internal nodes, and branches make up this system. ...
Article
Full-text available
Knowledge of the solubilities of hydrocarbon components of natural gas in pure water and aqueous electrolyte solutions is important in terms of engineering designs and environmental aspects. In the current work, six machine-learning algorithms, namely Random Forest, Extra Tree, adaptive boosting support vector regression (AdaBoost-SVR), Decision Tree, group method of data handling (GMDH), and genetic programming (GP) were proposed for estimating the solubility of pure and mixture of methane, ethane, propane, and n-butane gases in pure water and aqueous electrolyte systems. To this end, a huge database of hydrocarbon gases solubility (1836 experimental data points) was prepared over extensive ranges of operating temperature (273–637 K) and pressure (0.051–113.27 MPa). Two different approaches including eight and five inputs were adopted for modeling. Moreover, three famous equations of state (EOSs), namely Peng-Robinson (PR), Valderrama modification of the Patel–Teja (VPT), and Soave–Redlich–Kwong (SRK) were used in comparison with machine-learning models. The AdaBoost-SVR models developed with eight and five inputs outperform the other models proposed in this study, EOSs, and available intelligence models in predicting the solubility of mixtures or/and pure hydrocarbon gases in pure water and aqueous electrolyte systems up to high-pressure and high-temperature conditions having average absolute relative error values of 10.65% and 12.02%, respectively, along with determination coefficient of 0.9999. Among the EOSs, VPT, SRK, and PR were ranked in terms of good predictions, respectively. Also, the two mathematical correlations developed with GP and GMDH had satisfactory results and can provide accurate and quick estimates. According to sensitivity analysis, the temperature and pressure had the greatest effect on hydrocarbon gases’ solubility. Additionally, increasing the ionic strength of the solution and the pseudo-critical temperature of the gas mixture decreases the solubilities of hydrocarbon gases in aqueous electrolyte systems. Eventually, the Leverage approach has revealed the validity of the hydrocarbon solubility databank and the high credit of the AdaBoost-SVR models in estimating the solubilities of hydrocarbon gases in aqueous solutions.
... For developing a predictive model, a range of hyper-parameters had to be assigned, such as the number of decision tree learners, a subset of the ensemble for initial feeding to the learners, the upper limit of the allowable depth, the lowest number of leaves, number of features, and number of data points in the separated sample as the sample split 45 . ...
Article
Full-text available
Arsenic in drinking water is a serious threat for human health due to its toxic nature and therefore, its eliminating is highly necessary. In this study, the ability of different novel and robust machine learning (ML) approaches, including Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), Gradient Boosting Decision Tree (GBDT), and Random Forest (RF) was implemented to predict the adsorptive removal of arsenate [As(V)] from wastewater over 13 different metal-organic frameworks (MOFs). A large experimental dataset was collected under various conditions. The adsorbent dosage, contact time, initial arsenic concentration, adsorbent surface area, temperature, solution pH, and the presence of anions were considered as input variables, and adsorptive removal of As(V) was selected as the output of the models. The developed models were evaluated using various statistical criteria. The obtained results indicated that the LightGBM model provided the most accurate and reliable response to predict As(V) adsorption by MOFs and possesses R2, RMSE, STD, and AAPRE (%) of 0.9958, 2.0688, 0.0628, and 2.88, respectively. The expected trends of As(V) removal with increasing initial concentration, solution pH, temperature, and coexistence of anions were predicted reasonably by the LightGBM model. Sensitivity analysis revealed that the adsorption process adversely relates to the initial As(V) concentration and directly depends on the MOFs surface area and dosage. This study proves that ML approaches are capable to manage complicated problems with large datasets and can be affordable alternatives for expensive and time-consuming experimental wastewater treatment processes.
Article
There are many applications with the two-phase flow of gas (hydrocarbon, non-hydrocarbon, and their mixture) and water in different courses of gas recovery from natural gas resources and gas storage/sequestration programs. As the interface of gas-water is crucial in such systems, precise prediction of gas-water interfacial tension (IFT) can aid in the simulation and development of such processes. Artificial intelligence techniques (AIT) are being used to estimate IFT. In this paper, the IFT of the gas and water system was estimated based on models built using a comprehensive data set comprised of 2658 experimental data points. These cover a wide range of input parameters, i.e., specific gravity (0.5539–1.5225), temperature (278.1–477.5944 K), pressure (0.01–280 MPa), and water salinity (0–200,000 ppm). The intelligent models include Least-Squares Boosting (LS-Boost), Multilayer perceptron (MLP), Least Square Support Vector Machine (LSSVM), and Committee machine intelligent system (CMIS). The models reproduce the IFT data in 7.4–81.69 mN/m. The modeling approaches contain new hybrid forms in which Imperialist Competitive Algorithm (ICA), Grey Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), Levenberg-Marquardt algorithm (LM), Bayesian regularization algorithm (BR), Scaled conjugate gradient algorithm (SCG), and Coupled Simulated Annealing (CSA) were used for optimization and learning purposes. Statistical and graphical analyses were implemented to check the agreement between the prediction and evaluation data. The results show a reasonable coherence for most models, among which the CMIS approach exhibited a promising performance. CMIS was accurate even in conditions of varying specific gravity, pressure, temperature, and salinity. The findings were also compared with available models in the literature and demonstrated superior predictions of the CMIS model. Also, outlier detection by the Leverage approach demonstrates the validity of the gathered dataset and, subsequently, the CMIS model.
Article
Full-text available
As the global temperature continues to rise, people have become increasingly concerned about global climate change. In order to help China to effectively develop a carbon peak target completion plan, this paper proposes a carbon emission prediction model based on the improved whale algorithm-optimized gradient boosting decision tree, which combines four optimization methods and significantly improves the prediction accuracy. This paper uses historical data to verify the superiority of the gradient boosting tree prediction model optimized by the improved whale algorithm. In addition, this study also predicted the carbon emission values of China from 2020 to 2035 and compared them with the target values, concluding that China can accomplish the relevant target values, which suggests that this research has practical implications for China’s future carbon emission reduction policies.
Article
Ionic liquids (ILs) have attracted a great deal of attention as vital compounds that are widely used in various industries, such as the chemical and petroleum industries. Therefore, determining the properties of ionic liquids, such as electrical conductivity (EC), is an important issue. In this study, four different machine learning approaches including K-nearest neighbours (KNN), extreme gradient boosting (XGB), adaptive boosting-decision tree (Ada-DT), and adaptive boosting-support vector regression (Ada-SVR) were established to predict EC of ILs based on two categories namely: (I) smart models based on ILs chemical structure and temperature, and (II) smart models based on ILs thermodynamic properties and temperature. For this purpose, 2625 laboratory data points corresponding to 225 ILs have been used. The results showed that based on Model (I), KNN model with root mean square error (RMSE) and coefficient of determination (R²) values of 0.1976 and 0.9935, respectively, is the best model in predicting EC. Also, based on Model (II), the XGB model with RMSE and R² values of 0.1447 and 0.9965, respectively, is the most powerful and accurate model for estimating electrical conductivity. Sensitivity analysis revealed that temperature and molecular weight have a direct and inverse effect on increasing the electrical conductivity of ILs, respectively. The investigation of the effects of different chemical bonds (in the chemical structure of ionic liquids) on ILs EC showed that -CH2- and >N- substructures have the most negative and positive effect on EC, respectively. Also, the proposed smart paradigms were capable of accurately predicting the effect cation alkyl chain length on electrical conductivity. Based on the leverage technique assessment more than 95% of total data points are in a valid region which indicates that intelligent models are reliable. Consequently, the introduction of intelligent models based on the chemical structure of ILs, the much broader data bank, and the higher accuracy of the proposed models are among the innovations and advantages of this study compared to the previous researches. Findings of this study highlights that chemical structure-intelligence based approaches provide robust, reliable and accurate way to predict EC of ILs.
Article
Oil/water interfacial tension (IFT) is an important parameter in petroleum engineering, especially for enhanced-oil-recovery (EOR) techniques. Surfactant and low-salinity EOR target IFT reduction to improve oil recovery. IFT values can be determined by empirical correlation, but widely used thermodynamic-based correlations do not account for the surface-activities characteristic of the polar/nonpolar interactions caused by naturally existing components in the crude oil. In addition, most crude oils included in these correlations come from conventional reservoirs, which are often dissimilar to the low-asphaltene crude oils produced from shale reservoirs. This study presents a novel oil-composition-based IFT correlation that can be applied to shale-crude-oil samples. The correlation is dependent on the saturates/aromatics/resins/asphaltenes (SARA) analysis of the oil samples. We show that the crude oil produced from most unconventional reservoirs contains little to no asphaltic material. In addition, a more thorough investigation of the effect of oil components, salinity, temperature, and their interactions on the oil/water IFT is provided and explained using the mutual polarity/solubility concept. Fifteen crude-oil samples from prominent US shale plays (i.e., Eagle Ford, Middle Bakken, and Wolfcamp) are included in this study. IFT was measured in systems with salinity from 0 to 24% and temperatures up to 195°F.
Article
Adsorption process was simulated in this study for removal of Hg and Ni from water using nanocomposite materials. The used nanostructured material for the adsorption study was a combined MOF and layered double hydroxide, which is considered as MOF-LDH in this work. The data were obtained from resources and different machine learning models were trained. We selected three different regression models, including elastic net, decision tree, and Gradient boosting, to make regression on the small data set with two inputs and two outputs. Inputs are Ion type (Hg or Ni) and initial ion concentration in the feed solution (C0), and outputs are equilibrium concentration (Ce) and equilibrium capacity of the adsorbent (Qe) in this dataset. After tuning their hyper-parameters, final models were implemented and assessed using different metrics. In terms of the R2-score metric, all models have more than 0.97 for Ce and more than 0.88 for Qe. The Gradient Boosting has an R2-score of 0.994 for Qe. Also, considering RMSE and MAE, Gradient Boosting shows acceptable errors and best models. Finally, the optimal values with the GB model are identical to dataset optimal: (Ion = Ni, C0 = 250, Ce = 206.0). However, for Qe, it is different and is equal to (Ion = Hg, C0 = 121.12, Ce = 606.15). The results revealed that the developed methods of simulation are of high capacity in prediction of adsorption for removal of heavy metals using nanostructure materials.
Article
The mechanism models based on structure-oriented lumping (SOL) deliver a satisfactory prediction on the properties and yield distribution of the products from fluid catalytic cracking (FCC). However, with high complexity and low computing efficiency, such a model is increasingly unable to meet the needs of refineries to produce lighter and greener products using heavier and poorer feedstocks. Therefore, in this paper, a modeling approach hybridizing molecular mechanism and data models was proposed to describe the maximizing iso-paraffins (MIP) technology of the FCC process. This proposed model showed assured prediction accuracy with shortened computing time and thus was appropriate for online application. In this work, model simplification was carried out: less molecules and reactions (3078 and 5216, respectively) were adopted, along with a simplified reactor model, which largely reduced the computation load. CatBoost algorithm was also adopted for constructing a data model, to compensate for the accuracy loss resulting from the simplified SOL mechanism model. Combining with the mechanism model, it ensured the accuracy of prediction while greatly shortened the computing time. Furthermore, to overcome the strong coupling between the process variables to be solved, this work adopted the method of case-based reasoning (CBR) to optimize the process and expanded the case base with the prediction results of the hybrid model, which ensured the feasibility of the solution parameters and shortened the computing time. The hybrid model and the corresponding process optimization strategy proposed were then applied to an industrial FCC MIP process for verification. The results show that the hybrid model could assure the prediction accuracy (comparable with the conventional mechanism model) while the computing time was reduced from more than 20 h to less than 1 min. In the process optimization validation test, the total liquid yield increased by 1.19% on average for 43 out of 50 sets of operating configurations and the coke yield decreased by 1.05% on average. This work provides a good solution for the online process optimization of FCC.
Preprint
Full-text available
Machine learning algorithms have been extensively exploited in (renewable) energy research, due to their flexibility, automation and ability to handle big data. Among the most prominent machine learning algorithms are the boosting ones, which are known to be "garnering wisdom from a council of fools", thereby transforming weak learners to strong learners. Boosting algorithms are characterized by both high flexibility and high interpretability. The latter property is the result of recent developments by the statistical community. In this work, we provide understanding on the properties of boosting algorithms to facilitate a better exploitation of their strengths in energy research. In this respect, (a) we summarize recent advances on boosting algorithms, (b) we review relevant applications in energy research with those focusing on renewable energy (in particular those focusing on wind energy and solar energy) consisting a significant portion of the total ones, and (c) we describe how boosting algorithms are implemented and how their use is related to their properties. We show that boosting has been underexploited so far, while great advances in the energy field (in which renewable sources play a key role) are possible both in terms of explanation and interpretation, and in terms of predictive performance.
Article
Full-text available
Decision tree methodology is a commonly used data mining method for establishing classification systems based on multiple covariates or for developing prediction algorithms for a target variable. This method classifies a population into branch-like segments that construct an inverted tree with a root node, internal nodes, and leaf nodes. The algorithm is non-parametric and can efficiently deal with large, complicated datasets without imposing a complicated parametric structure. When the sample size is large enough, study data can be divided into training and validation datasets. Using the training dataset to build a decision tree model and a validation dataset to decide on the appropriate tree size needed to achieve the optimal final model. This paper introduces frequently used algorithms used to develop decision trees (including CART, C4.5, CHAID, and QUEST) and describes the SPSS and SAS programs that can be used to visualize tree structure.
Article
Full-text available
Fifty years have passed since the publication of the first regression tree algorithm. New techniques have added capabilities that far surpass those of the early methods. Modern classification trees can partition the data with linear splits on subsets of variables and fit nearest neighbor, kernel density, and other models in the partitions. Regression trees can fit almost every kind of traditional statistical model, including least-squares, quantile, logistic, Poisson, and proportional hazards models, as well as models for longitudinal and multiresponse data. Greater availability and affordability of software (much of which is free) have played a significant role in helping the techniques gain acceptance and popularity in the broader scientific community. This article surveys the developments and briefly reviews the key ideas behind some of the major algorithms.
Article
Full-text available
The flow of oil and water in naturally fractured reservoirs (NFR) can be highly complex and a simplified model is presented to illustrate some main features of this flow system. NFRs typically consist of low-permeable matrix rock containing a high-permeable fracture network. The effect of this network is that the advective flow bypasses the main portions of the reservoir where the oil is contained. Instead capillary forces and gravity forces are important for recovering the oil from these sections. We consider a linear fracture which is symmetrically surrounded by porous matrix. Advective flow occurs only along the fracture, while capillary driven flow occurs only along the axis of the matrix normal to the fracture. For a given set of relative permeability and capillary pressure curves, the behavior of the system is completely determined by the choice of two dimensionless parameters: (i) the ratio of time scales for advective flow in fracture to capillary flow in matrix $\alpha =\tau ^f/\tau ^m$ ; (ii) the ratio of pore volumes in matrix and fracture $\beta =V^m/V^f$ . A characteristic property of the flow in the coupled fracture–matrix medium is the linear recovery curve (before water breakthrough) which has been referred to as the “filling fracture” regime Rangel-German and Kovscek (J Pet Sci Eng 36:45–60, 2002), followed by a nonlinear period, referred to as the “instantly filled” regime, where the rate is approximately linear with the square root of time. We derive an analytical solution for the limiting case where the time scale $\tau ^{m}$ of the matrix imbibition becomes small relative to the time scale $\tau ^{f}$ of the fracture flow (i.e., $\alpha \rightarrow \infty $ ), and verify by numerical experiments that the model will converge to this limit as $\alpha $ becomes large. The model provides insight into the role played by parameters like saturation functions, injection rate, volume of fractures versus volume of matrix, different viscosity relations, and strength of capillary forces versus injection rate. Especially, a scaling number $\omega $ is suggested that seems to incorporate variations in these parameters. An interesting observation is that at $\omega =1$ there is little to gain in efficiency by reducing the injection rate. The model can be used as a tool for interpretation of laboratory experiments involving fracture–matrix flow as well as a tool for testing different transfer functions that have been suggested to use in reservoir simulators.
Article
Full-text available
In this research, effect of temperature, pressure, salinity, surfactant concentration, and surfactant type on interfacial tension (IFT) and critical micelle concentration of Saudi Arabian crude oil and various aqueous phases were investigated. The temperature ranged from ambient condition to 90°C, and the pressures were varied from atmospheric to 4,000 psi (27.58 MPa). Surfactant solutions were prepared using several aqueous phases, i.e., purified water, 10% brine consisting of 100% NaCl, 10% brine consisting of 95% NaCl and 5% CaCl2, and 10% brine consisting of 83% NaCl and 17% CaCl2. Out of 13 commercial surfactants, only three surfactants showed good solubility in pure water and brine. Those are Zonyl FSE Fluorosurfactant®, Triton X-100®, and Triton X-405®. Therefore, they were investigated thoroughly by measuring their efficiency in reducing the crude oil-aqueous phase IFT. Based on this screening process, laboratory surfactant flooding experiments for crude oil recovery were conducted using Triton X-405 and Triton X-100. The chemical flood was made at both original oil in place and at residual oil in place subsequent to conventional water flooding. Based on the obtained results, both surfactants were efficient, and more oil was recovered than that obtained through water flooding. Comparing both surfactant solutions, it was observed that Triton X-405 was more efficient than Triton X-100 at the same surfactant concentration and reservoir conditions.
Article
Detailed understanding of the behavior of crude oils and their interactions with reservoir formations and other in-situ fluids can help the engineers to make better decisions about the future of oil reservoirs. As an important property, interfacial tension (IFT) between crude oil and brine has great impacts on the oil production efficiency in different recovery stages due to its effects on the capillary number and residual oil saturation. In the present work, a new mathematical model has been developed to estimate IFT between crude oil and brine on the basis of a number of physical properties of crude oil (i.e., specific gravity, and total acid number) and the brine (i.e., pH, NaCl equivalent salinity), temperature, and pressure. Genetic programming (GP) methodology has been implemented on a data set including 560 experimental data to develop the IFT correlation. The correlation coefficient (R² = 0.9745), root mean square deviation (RMSD = 1.8606 mN/m), and average absolute relative deviation (AARD = 3.3932%) confirm the acceptable accuracy of the developed correlation for the prediction of IFT.
Article
An effective design and optimum production strategies of a well depend on the accurate prediction of its bottom hole pressure (BHP) which may be calculated or determined by several methods. However, it is not practical technically or economically to apply for a well test or to deploy a permanent pressure gauge in the bottom hole to predict the BHP. Consequently, several correlations and mechanistic models based on the known surface measurements have been developed. Unfortunately, all these tools (correlations & mechanistic models) are limited to some conditions and intervals of application. Therefore, establish a global model that ensures a large coverage of conditions with a reduced cost and high accuracy becomes a necessity. In this study, we propose new models for estimating bottom hole pressure of vertical wells with multiphase flow. First, Artificial Neural Network (ANN) based on back propagation training (BP-ANN) with 12 neurons in its hidden layer is established using trial and error. The next methods correspond to optimized or evolved neural networks (optimize the weights and thresholds of the neural networks) with Grey Wolves Optimization (GWO), and then its accuracy to reach the global optima is compared with 2 other naturally inspired algorithms which are the most used in the optimization field: Genetic Algorithm (GA) and Particle Swarms Optimization (PSO). The models were developed and tested using 100 field data collected from Algerian fields and covering a wide range of variables. The obtained results demonstrate the superiority of the hybridization ANN-GWO compared with the 2 other hybridizations or with the BP learning alone. Furthermore, the evolved neural networks with these global optimization algorithms are strongly shown to be highly effective to improve the performance of the neural networks to estimate flowing BHP over existing approaches and correlations.
Article
The optimization of water alternating gas injection (WAG) process is a complex problem, which requires a significant number of numerical simulations that are time-consuming. Therefore, developing a fast and accurate replacing method becomes a necessity. Proxy models that are light mathematical models have a high ability to identify very complex and non-straightforward problems such as the answers of numerical simulators in brief deadlines. Different static proxy models have been used to date, where a predefined model is employed to approximate the outputs of numerical simulators such as field oil production total (FOPT) or net present value, at a given time and not as functions of time. This study demonstrates the application of time-dependent multi Artificial Neural Networks as a dynamic proxy to the optimization of a WAG process in a synthetic field. Latin hypercube design is used to select the database employed in the training phase. By coupling the established proxy with genetic algorithm (GA) and ant colony optimization (ACO), the optimum WAG parameters, namely gas and water injection rates, gas and water injection half-cycle, WAG ratio and slug size, which maximize FOPT subject to some time-depending constraints, are investigated. The problem is formulated as a nonlinear optimization problem with bound and nonlinear constraints. The results show that the established proxy is found to be robust and an efficient alternative for mimicking the numerical simulator performances in the optimization of the WAG. Both GA and ACO are strongly shown to be highly effective in the combinatorial optimization of the WAG process.
Article
Nitrogen is of paramount importance for many processes in chemical and petroleum engineering; including enhanced oil recovery, gas injection for pressure maintenance, and gas recycling. Precise estimation of interfacial tension (IFT) between N2 and the reservoir hydrocarbons is, therefore indispensable. However, experimental measurement of IFT is expensive and time consuming. Therefore, reliable model for estimating IFT is vital. In this communication, the IFT between N2 and n-alkanes was modeled over a wide range of pressure (0.1–69 MPa) and temperature (295–442 K) based on the principle of corresponding state theory using dimensionless pressure and dimensionless temperature. Three well-known models; namely, Multilayer Perceptron (MLP) Neural Networks (optimized by Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG), or Bayesian Regularization (BR)), two Radial Basis Function (RBF) Neural Networks (optimized by Particle Swarm optimization (PSO) technique or Genetic Algorithm (GA)) and one Least Square Support Vector Machine (LSSVM) (optimized by coupled simulated annealing) were used to develop robust and accurate models for predicting IFT based on the proposed dimensionless parameters. Results suggested that the developed MLP-LM was the most accurate model of all with an average absolute relative error of 1.38%. MLP-LM model was compared with three well-known models in the literature; namely Density Gradient Theory (DGT), Linear Gradient Theory (LGT), and Parachor approaches combined with the Volume Translated Predictive Peng Robinson Equation of State (VT-PPR EOS) and the recently developed model by Hemmati-Sarapardeh and Mohagheghian. In addition to the advantage of being normal alkane-independent, results showed that the proposed MLP-LM model is superior to published models. Lastly, the quality of the literature IFT data and the applicability domain of MLP-LM model were evaluated using the Leverage approach.
Article
Nuclear magnetic resonance (NMR) is used in geological characterization to investigate the internal structure of geomaterials filled with fluids containing ¹H and ¹³C nuclei. Subsurface NMR measurements are generally acquired as well logs that provide information about fluid mobility and fluid-filled pore size distribution. Acquisition of subsurface NMR log is limited due to operational and instrumentation challenges. We implement a variational autoencoder (VAE) for improved training of a neural network (NN) to generate the NMR-T2 distributions along a 300-ft depth interval in a shale petroleum system at 11,000-ft depth below sea level. Subsurface mineral and kerogen volume fractions, fluid saturations, and T2 distributions acquired at 460 discrete depth points were used as the training data set. The trained VAE-NN successfully predicts the T2 distributions for 100 discrete depths at an R² of 0.75 and normalized root-mean-square deviation of 15%.
Article
In this work, four prompt and robust techniques have been used to introduce new generalized models for estimation of the physical properties of pure substances, including molecular weight and acentric factor. These methods were developed based on radial basis function (RBF) neural networks, group method of data handling (GMDH), multilayer perceptron (MLP), and least square support vector machine (LSSVM) techniques. Models were introduced based on a set of experimental data including 563 pure compounds that were collected from available literature. Input parameters for estimation of molecular weight were considered as specific gravity and normal boiling point. Critical temperature, critical pressure and normal boiling point were selected as inputs for estimation of the acentric factor. Statistical and graphical error analyses normal boiling point revealed that all of the developed models are accurate. The designed RBF models give the most accurate results with an AAPRE of 5.98% and 1.92% for molecular weight and acentric factor, respectively. The developed GMDH models are in the form of simple correlations, which can be used easily in hand calculation problems without any need to computers. Comparison of the developed models with the available methods showed that all of the developed models are more accurate than the existing methods. Using the relevancy factor, the impact of each input parameter on the output results was determined. Additionally, to find out the applicability region of the developed models, and to demonstrate the reliability of the models, the Leverage method has been used. There are few data out of the applicability domain of the proposed models. All the statistical and graphical resolutions, demonstrate the reliability of the developed models in estimating the molecular weight and acentric factor.
Article
Thesupport-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data.High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Article
The interfacial tension (IFT) of water-hydrocarbon system is one of the most important parameters in various fields of chemical, petroleum and process industries. Laboratory measurement of interfacial tension is laborious, time demanding and involves costly experimental setup. Current study presents genetic programming (GP) as a powerful tool in order to develop a novel correlation for estimation of IFT in hydrocarbon-water systems under wide ranges of experimental conditions. To achieve this mission, a comprehensive databank comprising 1075 experimentally measured data points were acquired from the literature reports. Four influencing factors of hydrocarbon critical temperature, experiment temperature, pressure and water/hydrocarbon density difference were considered as independent correlating variables to design and develop the genetic model. Comprehensive error analysis demonstrates the superiority of the proposed genetic model with R² = 0.91 and AARD = 4.38% in comparison with literature data. The predictability of the genetic model was further compared with a recently published model and other well-known empirical correlations reported in literature. The result suggests that the proposed tool is of great value for fast and precise estimation of water/hydrocarbon IFT.
Article
Due to unique physical and chemical properties of ionic liquids (ILs), they received lots of attention in many industrial fields and are widely under research. Ionic liquids, also are emerging as important components for applications in electrochemical devices. To develop their applications and achieving desire properties, they are usually mixed with organic solvents. Applying ionic liquids in many applications needs the accurate and reliable data of electrical conductivity of ILs and their mixtures. To this end, a total of 224 experimental data were collected from literature and divided randomly into two datasets: 179 data was selected as training set and the remained 45 data was used as a testing set. Afterwards, a reliable modeling technique is developed for modeling the electrical conductivity of the ILs ternary mixtures. This approach is called least square support vector machine (LSSVM). The model parameters were optimized using the method of couple simulated annealing (CSA). The input model parameters were, temperature of the system, melting point, molecular weight and mole percent of each component. A comprehensive error investigation was carried out, yielding the well accordance between the predictions of the model and experimental data. The presented model can predict the dependency of electrical conductivity variations with input variables. Moreover, the sensitivity analyses demonstrated that, among the selected input parameters, the average melting point of mixture has the largest effect on the electrical conductivity. Furthermore, suspected data were detected using the Leverage approach, residual, Williams plot and statistical hat matrix. Except seven data points, the all data appear to be reliable.
Article
Interfacial tension (IFT) is a key parameter which affects the remaining oil in place and fluid distributions in an oil reservoir. Mobilization of trapped oil in a reservoir after primary and secondary recovery schemes, as part of a tertiary oil recovery, requires a true and accurate understanding of interfacial interactions between oil, brine and reservoir rock. This study presents an investigation of temperature, pressure and synthetic formation water salinity effects on interfacial tension of two carbonate oil reservoirs. A pendant drop instrument was used to perform the measurements. In addition, Least Square Support Vector Machine (LS-SVM) in combination with Coupled Simulated Annealing (CSA) was used to model the values of IFT. Results show that the IFT of reservoir A increases with increasing temperature, pressure and salinity of synthetic formation water and the IFT data for reservoir B increases with increasing pressure and salinity of synthetic formation water but decreases with increasing pressure. The results of modeling studies show that the developed model is accurate for prediction of experimental IFT data.
Chapter
The study and modeling of physical properties such as surface tension and interfacial tension are important factors in the formation and stability of fluid systems such as emulsions. The present work shows the experimental results for surface tension and interfacial tension measurements in water and/or oils systems in the presence of surfactants, using the pendant drop technique. Distilled water and straight-chain alkanes such as hexane, dodecane and hexadecane were used. The surfactants employed were sodium dodecyl sulphate (SDS) and sorbitan monooleate (SPAN 80), which are hydrophilic and lipophilic surfactants respectively. Some results show the dependence of surface tension or interfacial tension with respect to the surfactant concentration, other results were obtained by varying the temperature in a range from 20 to \(60\,{}^{\circ }\mathrm{{C}}\).
Article
Reliable measurement and prediction of phase behaviour and properties of petroleum reservoir fluids are essential in designing optimum recovery processes and enhancing hydrocarbon production. This book explains relevant fundamentals and presents practical methods of determining required properties for engineering applications, through reviewing established practices and recent events. Although the emphasis is on the application of PVT and phase behaviour data to engineering problems, experimental methods are reviewed and their limitations are identified. The material in the book is divided into nine chapters, comprising the following; phase behaviour fundamentals; PVT tests and correlations; phase equilibria; equations of state; phase behaviour calculations; fluid characterization; gas injection; interfacial tension; and application in reservoir simulation.
Article
Interfacial tension is one of the very important parameters in pharmacology science, chemical engineering and petroleum engineering. The interfacial tension between pure hydrocarbons and water is widely used in chemical and petroleum engineering and so that it is highly desirable to find its accurate values. In this study a new unique correlation has been developed based on a comprehensive database of pure hydrocarbons-water interfacial tension values which contained both aliphatic and aromatic compounds (32 different hydrocarbons) with pressure ranges of 0.1-300MPa and temperature ranges of 252.44-550K. The proposed correlation uses the density difference between pure hydrocarbon and water, system temperature and critical temperature of hydrocarbon to estimate the interfacial tension value. The accuracy and estimation efficiency of the proposed model has been checked by comparing the model estimated values with the corresponding experimental values. Also, they have been compared to the estimated values using the other common correlations which showed the superiority of the proposed model. Also the trend estimation capability test against pressure and temperature changes has been conducted and compared for the proposed model and other common correlations which showed that the proposed model is more efficient in estimating interfacial tension between pure hydrocarbons and water.
Article
Tensidfluten gehört zu einem der aussichtsreichsten Verfahren zur Erhöhung der Erdölausbeute (EOR/IOR). Der Großteil aller Tensidflut-Verfahren scheitert an der richtigen Auswahl grenzflächenaktiver Substanzen, insbesondere für Lagerstätten mit hochsalinaren Lagerstättenwässern und höheren Temperaturen. Bei selektiven Untersuchungen von ca. 1200 Tensiden konnten sich nur sehr wenige Produktklassen qualifizieren. Unter Berücksichtigung geringer Adsorption, ultra-niedriger Grenzflächenspannung gegenüber aromatischen, paraffinischen und naphthenischen Ölen, thermischer Stabilität sowie hoher Salzverträglichkeit konnten letztendlich nur Ethercarboxylate und Ethersulfonate als geeignet eingestuft werden. Hierbei handelt es sich um spezifisch - über EO-Gruppen - "zuschneidbare" Gemische aus anionaktiven und nichtionogenen Tensiden, die in umfangreichen Labor-Flutversuchen erfolgreich geprüft wurden. First introduction of new tailor-made surfactant types (Polyethercarboxylates and Polyethersulfonates)
Article
Interfacial tension between crude oil and water plays a significant role in enhanced oil recovery. Many researchers seek surfactants to reduce the interfacial tension of crude oil and water that can be applicable in reservoir conditions of high salinity and temperature. The current study introduces the results of using two different families of ionic liquids (ILs) including imidazolium (1-dodecyl-3-methylimidazolium chloride ([C(12)mim][Cl]) and 1-octyl-3-methylimidazolium chloride ([C(8)mim][Cl])) and pyridinium (1-dodecyl pyridinium chloride ([C12Py][Cl]) and 1-octyl pyridinium chloride ([C8Py][Cl])) for this purpose. Measured IFT values between solutions of Is and a southern Iranian crude oil reveal that these ILs are successful in reducing the IFT. Unlike traditional surfactants, these ILs are more effective as the salinity increases. Also the measurements revealed that there is a correlation of the IFT of the solutions with salinity and temperature.
Article
This paper addresses the problem of improving the accuracy of an hypothesis output by a learning algorithm in the distribution-free (PAC) learning model. A concept class is learnable (or strongly learnable) if, given access to a source of examples of the unknown concept, the learner with high probability is able to output an hypothesis that is correct on all but an arbitrarily small fraction of the instances. The concept class is weakly learnable if the learner can produce an hypothesis that performs only slightly better than random guessing. In this paper, it is shown that these two notions of learnability are equivalent. A method is described for converting a weak learning algorithm into one that achieves arbitrarily high accuracy. This construction may have practical applications as a tool for efficiently converting a mediocre learning algorithm into one that performs extremely well. In addition, the construction has some interesting theoretical consequences, including a set of general upper bounds on the complexity of any strong learning algorithm as a function of the allowed error ∈.
Article
Interfacial tension plays a major role in many disciplines of science and engineering. Complex nature of this property has restricted most of the previous theoretical studies on thermophysical properties to bulk properties measured far from the interface. Considering the drawbacks and deficiencies of preexisting models, there is yet a huge interest in accurate determination of this property using a rather simple and more comprehensive modeling approach. In recent years, inductive machine learning algorithms have widely been applied in solving a variety of engineering problems. This study introduces Least-Square Support Vector Machines (LS-SVM) approach as a viable and powerful tool for predicting the interfacial tension between pure hydrocarbon and water. Comparing the model to experimental data, an excellent agreement was observed yielding the overall squared correlation coefficient (R2) of 0.993. Proposed model was also found to outperform when compared to some previously presented multiple regression models. An outlier detection method was also introduced to determine the model applicability domain and diagnose the outliers in the gathered dataset. Results of this study indicate that the model can be applied in systems over temperature ranges of 454.40–890 (oR) and pressure ranges of 0.1–300 (MPa).
Article
The QR decomposition is one of the most basic tools for statistical computation, yet it is also one of the most versatile and powerful. The chapter discusses the problem of perfect or nearly perfect linear dependencies, the complex QR decomposition, the QR decomposition in regression, the essential properties of the QR decomposition, and the use of Householder transformations to compute the QR decomposition. A classical alternative to the Householder QR algorithm is the Gram–Schmidt method. Least-squares regression estimates can also be found using either the Cholesky factorization or the singular value decomposition. The QR decomposition approach has been observed to offer excellent numerical properties at reasonable computational cost, while providing factors, Q and R, which are quite generally useful. Although the QR decomposition is a long established technique, it is not in stasis. The QR decomposition is a key to stable and efficient solutions to many least-squares problems. A diverse collection of examples in statistics is given in the chapter and it is certain that there are many more problems for which orthogonalization algorithms can be exploited. In addition, the QR decomposition provides ready insight into the statistical properties of regression estimates.
Book
A strong foundation in reservoir rock and fluid properties is the backbone of almost all the activities in the petroleum industry. Suitable for undergraduate students in petroleum engineering, Petroleum Reservoir Rock and Fluid Properties, Second Edition offers a well-balanced, in-depth treatment of the fundamental concepts and practical aspects that encompass this vast discipline. New to the Second Edition & Introductions to Stone II three-phase relative permeability model and unconventional oil and gas resources & Discussions on low salinity water injection, saturated reservoirs and production trends of five reservoir fluids, impact of mud filtrate invasion and heavy organics on samples, and flow assurance problems due to solid components of petroleum & Better plots for determining oil and water Corey exponents from relative permeability data & Inclusion of Rachford-Rice flash function, Plateau equation, and skin effect & Improved introduction to reservoir rock and fluid properties & Practice problems covering porosity, combined matrix-channel and matrix-fracture permeability, radial flow equations, drilling muds on fluid saturation, wettability concepts, three-phase oil relative permeability, petroleum reservoir fluids, various phase behavior concepts, phase behavior of five reservoir fluids, and recombined fluid composition & Detailed solved examples on absolute permeability, live reservoir fluid composition, true boiling point extended plus fractions properties, viscosity based on compositional data, and gas-liquid surface tension Accessible to anyone with an engineering background, the text reveals the importance of understanding rock and fluid properties in petroleum engineering. Key literature references, mathematical expressions, and laboratory measurement techniques illustrate the correlations and influence between the various properties. Explaining how to acquire accurate and reliable data, the author describes coring and fluid sampling methods, issues related to handling samples for core analyses, and PVT studies. He also highlights core and phase behavior analysis using laboratory tests and calculations to elucidate a wide range of properties.
Article
In the present paper the effect of salinity and different surfactants on interfacial tension (IFT) between crude oil and water has been investigated. Three different types of surfactants like anionic (sodium lauryl sulfate [SLS]), cationic (hexadecyltrimethylammonium bromide [HTAB]), and nonionic surfactants such as Tergitol 15-S-7, Tergitol 15-S-9, and Tergitol 15-S-12, respectively, have been used in this study. Improved efficiency of IFT reduction using a salt and surfactant mixture has been verified by measuring the IFT between oil and water. The synergism of salt and surfactant mixture on the reduction of IFT has been observed. A series of flooding experiments have been conducted to justify the effects of lowering interfacial tension and adsorption behavior of surfactants on additional oil recovery. It has been found that the additional oil recovery increases up to 24 % of the original oil in place (OOIP) when a surfactant and salt mixture has been used as the displacing fluid.
Article
The effect of the surfactant, NaOH, and polymer and the interactions between them on the heavy oil/water interface are unveiled by studying the dynamic interfacial tension (IFT), minimal transient IFT, and total organic carbon (TOC) and analyzing the phenomenon during the measurement of IFT of heavy oil/different alkaline systems, including alkaline (A), alkaline–surfactant (AS), alkaline–polymer (AP), and alkaline–surfactant–polymer (ASP). The results show that there exists a minimum transient IFT. There is an optimal composition to achieve the minimal IFT with varying NaOH concentrations in 0.018–0.8 wt %. For different chemical solutions, the optimal composition is different. Adding polymer affects the IFT by influencing the diffusion of species to or from the interface. Despite polymer addition, adding surfactant will increase the IFT at a lower alkaline concentration because of its competitive adsorption with OH– and reduce the IFT at a higher alkaline concentration because of its synergistic effect. The synergy between the surfactant and alkaline is turned out as follows: NaOH reacts with the polar components in the oil phase to produce ionized surface-active species; then the IFT is reduced; and the oil drop is prolonged. Surfactant accelerates the diffusion of ionized species from the interface to the bulk phase, and then the polar components underneath it are exposed to NaOH; therefore, the reaction between NaOH and polar oil components can proceed to further reduce the IFT. The contraction of the oil drop after surface-active species departed can be explained reasonably by considering the influence of the composition and structure of heavy oil.
Article
Spontaneous imbibition controls many processes of practical importance. The subject is undergoing rapid growth in terms of the number of publications. This paper is a selective review of the literature which concentrates on the last ten years or so but also highlights, as necessary, earlier work. Insight into the mechanism of spontaneous imbibition is provided through consideration of the behavior of strongly wetted uniform tubes of any cross-section. The significance of cross-flow on the mechanism of advance of interfaces in tubes is related to imbibition in much more complex pore spaces. Details of the mechanism of imbibition by rocks and correlation of data for very strongly wetted conditions are discussed with respect to the numerous variables. Correlation of spontaneous imbibition data for a wide range of viscosity ratios demonstrates unequivocally that the operative relative permeabilities during counter current imbibition are not unique as is commonly assumed. They depend on viscosity ratio. This dependence points to the limitations of analytic models of spontaneous imbibition that also include the choice of specific boundary conditions at the open face.
Article
The temperature dependence of interface tension in a water-n-hexane system without additives and after addition of stearic acid was experimentally studied at four different concentrations. A method for determining the excess surface chemical potential from experimental data on the temperature dependence of interfacial or surface tension is proposed for a diluted solution of surface-active impurity. The excess surface chemical potential of stearic acid at the interface of a water-n-hexane binary mixture is determined.
Article
A quantitative structure property relationship approach was performed to find the relation between the surfactant structure and its effect on water–oil interfacial tension. As a result, a new database has been developed measuring the interfacial tension between n-decane as the model oil and different aqueous solutions of some ionic compounds. In spite of other reports we selected surfactants by a scientific method that covers all structural information. Twenty four different compounds were selected by the principle component analysis method and their interfacial tensions were measured at their critical micelle concentrations. The geometrical optimization of surfactants was performed at the B3LYP/6-311G** level and quantum chemical and structural descriptors were calculated using relevant computer software programs. The best fitted descriptors were selected using the variable selection of the genetic algorithm (GA-MLR). The predictive test was performed for an external prediction set of 6 compounds, chosen out of 24 compounds. The resulted GA-MLR model can reasonably predict the interfacial tension using only three selected descriptors. The deviation between predicted and measured values was found to be <7%.
Article
It is estimated that two-thirds of crude oil remains in the oil reservoirs after primary and secondary (water flooding) recovery stages. The extent of residual oil trapped in the reservoir pore structure is dominated by capillary and interfacial forces. The residual oil will be mobilized if the capillary forces are reduced because of interfacial tension (IFT) reduction during surface active agents flooding into the oil reservoir. In this work, 1-dodecyl-3-methylimidazolium chloride ([C12mim] [Cl]) is proposed as the IFT reducing agent and its dynamic IFT with one of the Iranian crude oil under different conditions were examined. The obtained results revealed that the critical micelle concentration (CMC) between the crude oil and formation brine was obtained at a very low concentration of 100 ppm. Unlike to the traditional surfactants, this ionic liquid based surfactant found to be more effective for higher saline formation water. In addition, several core flooding experiments were performed to find both, tertiary oil recovery efficiency and IL adsorption on the rock surfaces which indicated promising results.
Article
An equation for prediction of liquid–liquid interfacial tension (IFT) in multi-component systems has been developed using the lattice theory and the regular solution assumptions. The equation does not include any empirical parameter and there is no limitation on the number of components comprising the system. The reliability of the equation has been evaluated by comparing its prediction with experimental data and other methods.
Article
The interfacial tension of hydrocarbon + water/brine systems is one of the basic physical properties required for performing process calculations in petroleum, natural gas, and petrochemical industries. Interfacial tensions of 10 normal alkane + water/brine and hydrocarbon mixture + water/brine systems were measured by using a pendent drop instrument. The temperature and pressure ranges of measurements are (25 to 80) C and (1 to 300) bar, respectively. The effects of temperature, pressure, and salt content have been studied. It was found that the interfacial tension is sensitive to temperature and salt concentration but weakly dependent on pressure and salt species.
Article
An apparatus was constructed for the measurement of interfacial tensions over a range of temperatures and pressures. This apparatus utilized the pendent drop method, and resembles in construction similar apparatus recently described in the literature and in use in some petroleum research laboratories. The interfacial tensions of benzene, propane, n-pentane, n-hexane, n-octane, and iso-octane against water were measured at temperatures ranging from 26? to 82? C and at pressures ranging from 1 to 204 atm. Values of interfacial tensions for the benzene-water system and their variations with temperature and pressure are generally in good agreement with values of previous investigations. The data in all cases showed a slight decrease of interfacial tension with pressure at constant temperature in the range studied. The effect of pressure became less as the pressure was increased, with an indication of a reversal of the effect at higher pressures. There was a decrease of interfacial tension with temperature at constant pressure in all cases, as would normally be expected. This rate of decrease became greater the higher the temperature. A general equation is presented for the interfacial tensions as a function of pressure and temperature over the range studied, and the constants calculated for each system. A definite trend was found in the effect of molecular weight on the interfacial tension at a given temperature and pressure, for the homologous series from propane to n-octane. Data for n-decane from the literature fitted well into this trend. Introduction It has been recognized for many years that surface forces play an active part in the production history of an oil reservoir as well as in determining the amount of unrecoverable oil. The magnitudes of these forces are governed by the values of the interfacial tensions. These vary greatly with composition, pressure, and temperature. The effect of composition is greater than that of pressure and temperature over the ranges normally encountered. In fact, because of the variety of compounds present in a crude, no attempt has yet been made to correlate crude composition with its surface tension or with its interfacial tension against water. The amount of dissolved methane greatly affects the surface properties of an oil, and there are "surface-active" compounds in crudes which have a much greater effect on boundary tensions than do equal amounts of hydrocarbons.
Article
The surface tension that exists between hydrocarbon and water systems is an important property within the petroleum industry. Uses of this property range from quantifying its effects on capillary pressure which governs the vertical saturation distribution of hydrocarbons in a reservoir to determining liquid droplet size for multiphase flow calculations. A general correlation for estimating water-hydrocarbon surface tension has been developed. Prior generalized methods presented in the literature were found to be in error for gases other than methane and did not adequately characterize the change in surface tension with temperature. A large database consisting of 1902 data points was created as part of the development of the correlation. Pure hydrocarbon component surface tension measurements against pure water provide the basis for this database. Data ranging from methane through hexadecane as well as benzene and toluene were included in the main database. Pure water data at vapor pressure equilibrium was also included in the analysis to ensure that changes in surface tension with temperature were modeled accurately. In addition, natural gas, natural gas-carbon dioxide and natural gas-nitrogen mixtures with pure water were tested with the new correlation to ensure realistic scenarios could be accurately modeled. Pressure data covered the range from 14.7 to 43,526 psia while temperature ranged 33-500 °F which ensures that both conventional and HPHT conditions can be modeled. Real hydrocarbon-water systems usually contain dissolved salts in the water; therefore, a salinity correction must be applied to account for the increase in surface tension. Available data from the literature was examined and a suitable correction is proposed. This paper presents the analysis of an exhaustive database and proposes a new correlation to model water-hydrocarbon surface tension with significantly higher accuracy.
Article
Interfacial tension between crude oil and brine is an important variable in water/oil and water/oil/gas displacements. Interfacial tension influences capillary pressure, capillary number, adhesion tension, and the dimensionless time for imbibition. Despite its importance, there is little data available for crude oils and even less data that can be related to key crude oil chemical properties such as acid and base number. We present the results of a study of interfacial tensions for well-characterized stock-tank crude oil samples. Transient tensions measured by the pendant drop technique were monitored as a function of time. The effects of salinity and pH have been investigated and correlations observed between interfacial tension and an oil's acid number, base number, amount of asphaltenes, and viscosity. This data set can be used to compare capillary pressures measured with different fluid pairs or to design core floods with model fluids, among many other applications. It can also be used to examine mechanistic explanations for the magnitude of interfacial tension between a crude oil and brine. © 2007 Society of Petrophysicists and Well Log Analysts. All rights reserved.
Article
The changes of thermodynamic quantities associated with the interface formation are evaluated by the use of thermodynamic relations, when the interfacial tension of organic solutions against water is measured as a function of all the permissible thermodynamic variables. They are important to make clear the behavior of the molecules at organic liquid/water interfaces.
Article
A series of interfacial tension (IFT) measurements versus temperature were carried our at a constant pressure using the Pendent Drop apparatus. The study was conducted with seven different samples of viscous crude oil using as the aqueous phases a source water for water injection, distilled water, and heavy water. The temperatures investigated ranged from ambient 10 160 °C. For two heavy oils if was found that the IFT initially decreased then increased with temperature and for one oil there was only an increase. For all other systems IFT either remained constant or decreased with increasing temperature. To investigate this apparent anomaly of increasing IFT with increasing temperature, a series of experiments were conducted to examine the effect of oxidation of the bitumen and also the effect of intermediate or light-end hydrocarbons which may hare been lost from the heavy crude oil system during the driving process. No just explanation for the increasing IFT was established. In a system where the density difference between the oil and the aqueous phase was from 0.01 to 0.002 gcm3, the Pendent Drop maintains its integrity. However it was found that the drop does not have the necessary shape to permit the determination of an accurate tension. Consequently for the heavier crude oils, modified procedures for measuring IFT were examined and are described. To overcome this problem the density difference between the two phases was increased by using heavy water as the aqueous phase. Introduction The interfacial tension between heavy crude oil and injection water under reservoir conditions plays a significant mechanistic role in the process of enhanced oil recovery. This interaction between the oil and water phases in steam flood recovery schemes is a function of temperature, pressure, and composition of both the hydrocarbon and aqueous phases. With highly viscous crude oils, increasing the temperature of the formation is the most significant factor in mobilizing the oil. However, to improve the efficiency of this process, the use of additives such as solvents, high pH control chemicals, or surfactants co-injected with steam, has been shown to enhance the oil recovery. The dominant mechanism in these cases, is a reduction in IFT at the oil/water interface resulting in the mobilization of oil by in-situ emulsification. Both an increase in temperature and the use of certain additives are expected to cause a decrease in the IFT. The purpose of this study was to investigate this expectation for some heavy oils and waters. This study involved the examination of the effect of temperature on the IFT of a number of heavy crude oil and water systems using the Pendent Drop technique. This quantification of the IFT/temperature relationship is important in a number of areas including:the assessment of the application of chemicals in low- and high-temperature enhanced recovery processes.the study of the effect of IFT as it relates to emulsification of oil-in-water or water-in-oil.the establishment of high-temperature IFT relationships associated with thermal recovery mechanisms.
Article
The reduction of interfacial tension between acidic oils and floodwater is one of the most important mechanisms of enhanced oil recovery. An experimental study was conducted to elucidate the mechanisms of the interfacial tension behavior arising from the interaction between an acidified oil and a pure surfactant. A model oil system was used to examine the influence of acid and surfactant concentrations on interfacial tension. With sodium dodecyl sulfate as the added surfactant, the interfacial tension was lower than with either surfactant alone or acid alone and no minimum in interfacial tension was observed.
Article
It was proposed that negative interfacial tension due to high film pressure is responsible for the formation of micro emulsions. It now appears that the initial, negative interfacial tension γφ in mixed films of soap and long-chain alcohols is the result not so much of a high initial film pressure as of a large depression of the interfacial tension (γo/w)a between the water and the oil phase with its adsorbed alcohol monolayer in accordance with the equation γφ  (γo/w)a  π. This depression is brought about by the spontaneous distribution of alcohol between the interface and the oil phase. It is pointed out that this distribution is dependent upon the initial chemical potential of the particular alcohol in the given oil and that it may vary within wide limits. The fraction of the alcohol that remains in the oil phase is available to depress the oil/water interfacial tension while the remainder of it forms a mixed film with emulsifier adsorbed from the water phase. It is submitted that the interaction of coulombic, hydrogen bonding and van der Waals forces among the heads and tails of the tenants of this film develops an initial pressure gradient across the flat interface which generates the initial film pressure . Three stages of pressure development are postulated, the maximum pressure corresponding to an intermediate concentration of alcohol. Hypothetical plots of (γo/w)a and as ordinates versus concentration of alcohol as abscissa provide a graphical characterization of the process of microemulsification.
Article
The variation in interfacial tension in acidic oil-alkaline solution systems has been modeled previously. These existing models account for the adsorption of acid, in situ generated surfactant and the added surfactant at the oil-water interface. However, these models do not account for the interactions that exist between these surfactants in the adsorbed layer. An existing model for the formation of non-ideal mixed micelles has been modified and extended to a three component mixture to quantify these interactions. The model is applied to an experimental system consisting of an acidic oil in contact with an alkaline solution containing surfactant. Such systems are encountered in the process of chemical enhanced oil recovery. A good agreement is observed between the experimentally measured interfacial tensions and the values predicted by the present model. The best fit estimates of the monolayer interaction parameters between the acid, surfactant and ionized acid are reported.
Article
This study is aimed at developing an alkaline/surfactant-enhanced oil recovery process for heavy oil reservoirs with oil viscosities ranging from 1000 to 10,000mPas, through the mechanism of interfacial instability. Instead of the oil viscosity being reduced, as in thermal and solvent/gas injection processes, oil is dispersed into and transported through the water phase to production wells.Extensive emulsification tests and oil/water interfacial tension measurements were conducted to screen alkali and surfactant for the oil and the brine samples collected from Brintnell reservoir. The heavy oil/water interfacial tension could be reduced to about 7×10−2dyn/cm with the addition of a mixture of Na2CO3 and NaOH in the formation brine without evident dynamic effect. The oil/water interfacial tension could be further reduced to 1×10−2dyn/cm when a very low surfactant concentration (0.005–0.03wt%) was applied to the above alkaline solution. Emulsification tests showed that in situ self-dispersion of the heavy oil into the water phase occurred when a carefully designed chemical solution was applied.A series of 21 flood tests were conducted in sandpacks to evaluate the chemical formulas obtained from screening tests for the oil. Tertiary oil recoveries of about 22–23% IOIP (32–35% ROIP) were obtained for the tests using 0.6wt% alkaline (weight ratio of Na2CO3 to NaOH=2:1) and 0.045wt% surfactant solution in the formation brine. The sandpack flood results obtained in this project showed that a synergistic enhancement among the chemicals did occur in the tertiary recovery process through the interfacial instability mechanism.
Article
An equation relating the free energies of cohesion of separate phases to the free energy of adhesion, and hence the surface tensions to the interfacial tensions, is proposed: -[ΔF aba/(ΔF a°ΔF b°) 1/2] = [(γ a + γ b - γ ab)/2(γ aγ b)1/2] = Φ. The relations developed are confronted with experimental data on interfacial tensions.
Article
Time-dependent interfacial tension (IFT) has been investigated for an interfacially reactive immiscible system composed of model-acidified oil and alkaline water. The acidified oil was composed of either lauric acid or linoleic acid dissolved in n-dodecane. Drop volume tensiometry was employed to measure the interfacial tension between the two phases. In the case of lauric acid, the IFT value was found to decrease sharply with increasing alkali concentration, even at low drop formation times. In the case of linoleic acid, the IFT decrease with the drop formation time was more gradual, especially at low alkali concentration. The rate of formation of the interfacial area was also found to be dependent on alkali concentration.