Article
Geosciences, Multidisciplinary
Maryam Sadi, Abbas Shahrabadi
Summary: In this study, experimental measurements and modeling investigations were conducted to predict crude oil viscosity under various conditions. Three advanced intelligent models were developed to estimate saturated and under-saturated oil viscosity using input parameters such as crude oil API, solution gas oil ratio, bubble point pressure, molecular weight, specific gravity of C12+ fraction, mole percent of C?11components, temperature, and pressure. The results showed that the Gaussian process regression model had the best performance in viscosity prediction, with average absolute relative errors of 0.18% and 0.07% for saturated and under-saturated oil, respectively. The findings of the Leverage technique and sensitivity analysis further supported the reliability and importance of the study.
NATURAL RESOURCES RESEARCH
(2023)
Article
Chemistry, Multidisciplinary
Aydin Larestani, Abdolhossein Hemmati-Sarapardeh, Zahra Samari, Mehdi Ostadhassan
Summary: This study focuses on developing reliable and accurate compositional oil formation volume factor (B-o) models using advanced machine learning models. The results show that tree-based models, especially the ET model, outperform other models and can be reliably applied for estimating B-o. Furthermore, machine learning models provide more accurate predictions compared to equations of state.
Article
Multidisciplinary Sciences
Kiana Peiro Ahmady Langeroudy, Parsa Kharazi Esfahani, Mohammad Reza Khorsand Movaghar
Summary: Oil viscosity is crucial in petroleum engineering, and experimental methods and compositional methods can accurately estimate it. However, experimental data is difficult to obtain, so there is a need for convenient and fast methods to predict viscosity. This study uses machine learning methods (XGBoost, CatBoost, and GradientBoosting) based on gradient boosting decision tree to reduce the prediction error of viscosity by considering dissolved gas content, temperature, pressure, and API gravity. XGBoost outperforms other methods with higher precision and lower error, showing the effectiveness of the approach.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Artificial Intelligence
Mohammad Soleimani Lashkenari, Mohammad Bagheri, Afshin Tatar, Hadi Rezazadeh, Mustafa Inc
Summary: A robust radial basis function neural network (RBF-NN) is developed to predict the viscosity of Iranian crude oil accurately. The model utilizes temperature, pressure, and PVT analysis parameters as independent variables. The RBF-NN model is evaluated and compared with previous studies using experimental data and sensitivity analyses. The results demonstrate that the proposed RBF-NN model outperforms other methods in predicting crude oil viscosity in different pressure regions.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Multidisciplinary Sciences
Daihong Li, Xiaoyu Zhang, Qian Kang
Summary: This study applies multiple models to predict the viscosity of heavy crude oil and correlates it to reservoir conditions using computational modeling techniques. Decision Tree, Multi-Layer Perceptron (MLP), and Generalized Radial Basis Function Neural Network (GRNN) models were utilized to estimate the viscosity of heavy crude oil samples from Middle Eastern oil fields. The firefly algorithm was used to optimize the hyperparameters of the machine learning models. The final models of DT, MLP, and GRNN have RMSE error rates of 40.52, 25.08, and 30.83, respectively, and R-2 scores of 0.921, 0.978, and 0.933 respectively. Based on various criteria, MLP is chosen as the best model for estimating crude oil viscosity in this study.
Article
Electrochemistry
Fadhel Azeez, Abdelrahman Refaie
Summary: This study successfully predicts the viscosity of salt-free solvent mixtures and relative viscosity of Li-ion electrolyte solutions using a semi-empirical model and artificial neural network. The results show high accuracy in viscosity prediction by the models.
JOURNAL OF THE ELECTROCHEMICAL SOCIETY
(2022)
Article
Thermodynamics
Hiyam Abdulrahim, Safiya Mukhtar Alshibani, Omer Ibrahim Osman Ibrahim, Azhari A. Elhag
Summary: This paper compares the performance of multi-layer perceptron and decision tree models in predicting OPIC crude oil production, and evaluates their accuracy using various error assessment metrics. It also presents the OPIC crude oil output using descriptive scales and graphs, and compares the results with previous studies.
Article
Chemistry, Multidisciplinary
Haijun Luo, Jiangbo Wen, Rong Jiang, Qianqian Shao, Zhihua Wang
Summary: This study investigates the influence of water cut on the viscosity characteristics of crude oil emulsion and establishes a prediction model for the phase inversion point. The results show that the viscosity of stable W/O emulsion decreases with increasing shear rate and temperature while increasing with the water cut. The viscosity of unstable O/W emulsion decreases with increasing shear rate, water cut, and temperature. The prediction model based on crude oil physical properties achieves a mean relative deviation of 2.9%.
Article
Environmental Studies
Zilin Xu, Muhammad Mohsin, Kaleem Ullah, Xiaoyu Ma
Summary: The volatility of the crude oil market and its effects on the global economy have raised concerns among individual investors, governments, and corporations. Predicting crude oil prices is difficult due to its complex, nonlinear, and chaotic nature. Multiple variables influence crude oil prices, such as economic history, economic cycle, international relations, and geopolitics.
Article
Thermodynamics
Naman Parashar, Navid Aslfattahi, Syed Mohd. Yahya, R. Saidur
Summary: The dynamic viscosity of MXene-palm oil nanofluid was investigated, showing a strong dependence on temperature and decreasing with increasing temperature. The effect of MXene nanoflakes concentration on dynamic viscosity was more pronounced at lower temperatures.
JOURNAL OF THERMAL ANALYSIS AND CALORIMETRY
(2021)
Article
Chemistry, Physical
Fujun Sheng, Jie Zhang, Shuang Yang, Guangyu Sun, Chuanxian Li, Fei Yang, Bo Yao, Xiaobin Jiang, Yangyang Zhou
Summary: In this study, the effects of crude oil viscosity and wax precipitation on foaming characteristics were investigated using the depressurization method. The results showed that the foamability of crude oil tends to decrease with increasing temperature below the wax appearance temperature (WAT). However, above the WAT, the foamability weakens drastically and remains relatively constant with temperature. The dominant factor affecting foamability was found to be the temperature-induced change in oil phase viscosity. Additionally, the foam stability decreased significantly with increasing temperature, which was attributed to the decrease in interfacial dilational modulus and the weakened film strength at the crude oil-CO2 interface.
COLLOIDS AND SURFACES A-PHYSICOCHEMICAL AND ENGINEERING ASPECTS
(2023)
Article
Energy & Fuels
Witold Orzeszko
Summary: The study found strong bidirectional causal relations between crude oil prices and EUR/USD, GBP/USD, and weaker relations with JPY/USD. The significance of these relations has changed in recent years, and Support Vector Regression (SVR) was used for forecasting crude oil prices and exchange rates.
Article
Engineering, Environmental
Francisca M. Santos, Alvaro Gomez-Losada, Jose C. M. Pires
Summary: This study utilized machine learning to generate O-3 isopleths in urban and suburban environments, demonstrating the powerful fitting performance of ANN models in describing complex relationships between O-3 and its precursors. The findings provide valuable insights for defining mitigation strategies to reduce O-3 concentrations.
JOURNAL OF HAZARDOUS MATERIALS
(2021)
Article
Energy & Fuels
Xiaodong Gao, Pingchuan Dong, Jiawei Cui, Qichao Gao
Summary: This study aims to develop a more accurate viscosity model of diluted heavy crude based on machine learning techniques. By using a multilayer neural network to predict the viscosity of heavy oil diluted with lighter oil, it was found that the new model can predict the viscosity of diluted heavy oil with higher accuracy and outperforms other models.
Article
Economics
Zhifeng Dai, Jie Kang
Summary: The study shows that using long-term government bond yield, corporate bond yields spread, and Treasury bill rate can effectively predict WTI and Brent spot prices. These variables have substantial explanatory power on oil returns and there are significant Granger causality relationships between them. Additionally, the predictive abilities of bond yield variables can be significantly enhanced with multivariate prediction methods, partially due to their ability to capture oil market sentiment.
Article
Energy & Fuels
Dicho Stratiev, Ivelina Shishkova, Rosen Dinkov, Svetoslav Nenov, Sotir Sotirov, Evdokia Sotirova, Iliyan Kolev, Vitaly Ivanov, Simeon Ribagin, Krassimir Atanassov, Danail Stratiev, Dobromir Yordanov, Dimitar Nedanovski
Summary: This study predicts the viscosity of 165 crude oils with varying viscosity, density, and molecular weight, using eight existing models and three new models developed in this study. The results show that the artificial neural network (ANN) model performs better than the empirical correlations. Additionally, the study examines the viscosity prediction of 93 crude oils with varying viscosity, density, molecular weight, and SARA composition using existing empirical correlations and a new empirical correlation that also considers the crude oil saturate content. The results indicate that the model developed in this study, incorporating the saturate content, has the highest prediction accuracy.
Article
Engineering, Chemical
Dicho Stratiev, Sotir Sotirov, Evdokia Sotirova, Svetoslav Nenov, Rosen Dinkov, Ivelina Shishkova, Iliyan Venkov Kolev, Dobromir Yordanov, Svetlin Vasilev, Krassimir Atanassov, Stanislav Simeonov, Georgi Nikolov Palichev
Summary: The precision of petroleum engineering calculations and process design can be affected by the accuracy of petroleum fluid molecular weight correlations. Some methods used in commercial software process simulators for predicting petroleum fluid molecular weight are not significantly better than the Lee-Kesler and Twu correlations, which are the most commonly used in petroleum engineering. In this study, 430 data points for boiling point, specific gravity, and molecular weight of petroleum fluids and individual hydrocarbons were analyzed to determine the most appropriate correlations for petroleum fluids with molecular weight variation. The artificial neural network (ANN) model showed the highest accuracy of prediction, followed by the newly developed nonlinear regression correlation.
Article
Engineering, Chemical
Dicho Stratiev, Rosen Dinkov, Mariana Tavlieva, Ivelina Shishkova, Georgi Nikolov Palichev, Simeon Ribagin, Krassimir Atanassov, Danail D. Stratiev, Svetoslav Nenov, Dimitar Pilev, Sotir Sotirov, Evdokia Sotirova, Stanislav Simeonov, Viktoria Boyadzhieva
Summary: This study characterized 48 crude oils using HTSD, TBP, and SARA analyses. A modified SARA analysis for petroleum was proposed, a procedure to simulate petroleum TBP curves from HTSD data was developed, and a new correlation to predict petroleum saturate content was established. Intercriteria analysis was used to evaluate the relations between different petroleum properties and the similarity between crude oils.
Article
Mathematics
Krassimir Atanassov, Sotir Sotirov, Tania Pencheva
Summary: This paper introduces the concept of an intuitionistic fuzzy deep neural network (IFDNN), which combines artificial neural networks and intuitionistic fuzzy sets to leverage the advantages of both methods. The study methodologically presents the entire development process of IFDNN, starting from the simplest form of an intuitionistic fuzzy neural network (IFNN) with one layer and a single-input neuron, and progressing to more complex structures with multi-input neurons. The formulas for estimating NN parameters, represented as intuitionistic fuzzy pairs, are provided for each of the presented IFNNs. An example of using IFDNN for biomedical data is also presented to demonstrate its feasibility.
Article
Engineering, Chemical
Iliyan Kolev, Dicho Stratiev, Ivelina Shishkova, Krassimir Atanassov, Simeon Ribagin, Sotir Sotirov, Evdokia Sotirova, Danail D. Stratiev
Summary: The properties of hydrocracked vacuum residue and cutter stocks have an impact on the density, sediment content, and viscosity of the obtained fuel oil. Different crude oil blends and cutter stocks interact with each other in different ways, resulting in varying values of these properties. The density of the blends deviates from regular solution behavior due to attractive and repulsive forces between the molecules. The viscosity of hydrocracked vacuum residue is linearly dependent on the viscosity of the vacuum residue feed blend. Equations used to predict viscosity show good prediction ability with an average deviation of 8.8%, while predicting sediment content remains challenging.
Article
Engineering, Chemical
Jeramie J. Adams, Joseph F. Rovani, Jean-Pascal Planche, Jenny Loveridge, Alex Literati, Ivelina Shishkova, Georgi Palichev, Iliyan Kolev, Krassimir Atanassov, Svetoslav Nenov, Simeon Ribagin, Danail Stratiev, Dobromir Yordanov, Jianqiang Huo
Summary: Model compounds were used to define the chemical properties of different fractions in the SAR-AD(TM) characterization method for heavy oils. The study found that the Saturates fraction mainly consists of linear and cyclic alkanes, while the Aro-1 fraction is composed of molecules with a single aromatic ring. Additionally, the Aro-2 fraction consists of fused aromatic molecules, including pyrene, and the Aro-3 fraction contains larger linear and catacondensed aromatics.
Article
Engineering, Chemical
A. Qubian, A. S. Abbas, N. Al-Khedhair, J. F. Peres, D. Stratiev, I. Shishkova, R. Nikolova, V. Toteva, M. R. Riazi
Summary: The formation of asphaltene and waxes occurs due to changes in crude oil characteristics. Mitigating deposit formation is crucial due to the high costs associated with equipment cleaning and profit loss. A laboratory analysis of a crude sample with asphaltene deposition problem was conducted, and various chemical inhibitors were screened for their effectiveness in inhibiting precipitation.
Article
Mathematics
Krassimir Atanassov
Summary: This paper introduces a set SET(n) generated by an arbitrary natural number n, and defines some arithmetic functions and operators of a modal type on the elements of SET(n) as described in [3] and [4]. Additionally, it defines arithmetic operators of a topological type on the elements of SET(n) and studies some of their basic properties. Perspectives for future research are also discussed.
NOTES ON NUMBER THEORY AND DISCRETE MATHEMATICS
(2023)
Article
Mathematics
Jozsef Sandor, Krassimir T. Atanassov
Summary: New results on the maximum and minimum exponents in integer factorization have been achieved, alongside the introduction of related functions and generalized arithmetical functions.
NOTES ON NUMBER THEORY AND DISCRETE MATHEMATICS
(2023)
Article
Mathematics, Applied
Krassimir Atanassov
Summary: In this paper, four different intuitionistic fuzzy temporal topological structures are introduced and their properties are discussed. These structures are extensions of the existing intuitionistic fuzzy topological structures and will serve as the foundation for a new type of topological structures.
Article
Mathematics, Applied
Krassimir Atanassov, Nora Angelova, Tania Pencheva
Summary: The concept of an Intuitionistic Fuzzy Modal Topological Structure (IFMTS) was introduced, and some of its properties were studied. Two new IFMTSs were developed based on new intuitionistic fuzzy topological operators and the two standard intuitionistic fuzzy modal operators ?. The basic properties of the new IFMTSs were discussed, and ideas for future development and open problems were presented.
Article
Medicine, General & Internal
Daniel Zhelev, Stoyan Hristov, Ivan Zderic, Stoyan Ivanov, Luke Visscher, Asen Baltov, Simeon Ribagin, Karl Stoffel, Franz Kralinger, Joerg Winkler, R. Geoff Richards, Peter Varga, Boyko Gueorguiev
Summary: This study confirmed that the new technique of using polymethylmethacrylate bone cement augmentation can significantly enhance fixation stability and reduce the risk of postoperative complications in the treatment of unstable proximal humerus fractures.
MEDICINA-LITHUANIA
(2023)