scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Prediction of Bubble Point Pressure Using New Hybrid Computationail Intelligence Models

TL;DR: The outcomes of the study show the models developed are capable of predicting BPP with promising performance, where the best result was achieved for DWKNN-ICA and the performance comparison of the developed hybrid models with some previously developed models revealed that the DWKnn-ICA outperforms the former empirical models with respect to perdition accuracy.
Abstract: Determining BPP is one of the critical parameters for the development of oil and gas reservoirs and have this parameter requires a lot of time and money. As a result, this study aims to develop a new predictive model for BPP that uses some available input variables such as solution oil ratio (Rs), gas specific gravity (γg), API Gravity (API). In this study, two innovatively combined hybrid algorithms, DWKNN-GSA and DWKNN-ICA, are developed to predict BPP. The outcomes of the study show the models developed are capable of predicting BPP with promising performance, where the best result was achieved for DWKNN-ICA (RMSE = 0.90276 psi and R2 = 1.000 for the test dataset). Moreover, the performance comparison of the developed hybrid models with some previously developed models revealed that the DWKNN-ICA outperforms the former empirical models with respect to perdition accuracy. In addition to presenting new techniques in the present study, the effect of each of the input parameters on BPP was evaluated using Spearman's correlation coefficient, where the API and Rs have the lowest and the highest impact on the BPP.

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI
TL;DR: Analysis indicates that the MELM-PSO model provides the highest μc prediction accuracy achieving a root mean squared error (RMSE) of 0.0035 cP and a coefficient of determination (R2) for a dataset of 2269 data records compiled from gas-condensate fields around the world.

24 citations

Journal ArticleDOI
TL;DR: In this paper , empirical equations along with machine learning methods, namely random forest algorithm, support vector regression (SVR), artificial neural network (ANN) algorithm, and decision tree (DT) algorithm were employed for PP prediction applying well log data.

16 citations

Journal ArticleDOI
TL;DR: In this article , the authors applied a robust machine-learning forecasting model to predict permeability (K) for heterogeneous carbonate gas condensate reservoirs, where the input variables considered are porosity (Φ, %), specific surface area (Sp, 1/cm) and irreducible water saturation (Swir, %).

15 citations

Journal ArticleDOI
TL;DR: In this article, a CNN model was developed to predict the flow rate through orifice plate (Qo) from seven input variables, including fluid temperature (Tf), upstream pressure (Pu), root differential pressure (√ΔP), percentage of base sediment and water (BS&W), oil specific gravity (SG), kinematic viscosity (ν), and beta ratio (β, the ratio of pipe diameter to orifice diameter).

14 citations

Journal ArticleDOI
TL;DR: In this article , the authors used hybrid machine learning (HML) and deep learning (DL) algorithms for predicting shear wave velocity (V S ) from sedimentary rock sequences.
Abstract: Abstract Shear wave velocity ( V S ) data from sedimentary rock sequences is a prerequisite for implementing most mathematical models of petroleum engineering geomechanics. Extracting such data by analyzing finite reservoir rock cores is very costly and limited. The high cost of sonic dipole advanced wellbore logging service and its implementation in a few wells of a field has placed many limitations on geomechanical modeling. On the other hand, shear wave velocity V S tends to be nonlinearly related to many of its influencing variables, making empirical correlations unreliable for its prediction. Hybrid machine learning (HML) algorithms are well suited to improving predictions of such variables. Recent advances in deep learning (DL) algorithms suggest that they too should be useful for predicting V S for large gas and oil field datasets but this has yet to be verified. In this study, 6622 data records from two wells in the giant Iranian Marun oil field (MN#163 and MN#225) are used to train HML and DL algorithms. 2072 independent data records from another well (MN#179) are used to verify the V S prediction performance based on eight well-log-derived influencing variables. Input variables are standard full-set recorded parameters in conventional oil and gas well logging data available in most older wells. DL predicts V S for the supervised validation subset with a root mean squared error (RMSE) of 0.055 km/s and coefficient of determination (R 2 ) of 0.9729. It achieves similar prediction accuracy when applied to an unseen dataset. By comparing the V S prediction performance results, it is apparent that the DL convolutional neural network model slightly outperforms the HML algorithms tested. Both DL and HLM models substantially outperform five commonly used empirical relationships for calculating V S from V p relationships when applied to the Marun Field dataset. Concerns regarding the model's integrity and reproducibility were also addressed by evaluating it on data from another well in the field. The findings of this study can lead to the development of knowledge of production patterns and sustainability of oil reservoirs and the prevention of enormous damage related to geomechanics through a better understanding of wellbore instability and casing collapse problems. Graphical abstract

13 citations

References
More filters
Journal ArticleDOI
TL;DR: A new optimization algorithm based on the law of gravity and mass interactions is introduced and the obtained results confirm the high performance of the proposed method in solving various nonlinear functions.

5,501 citations

Book
07 May 1998
TL;DR: In this paper, the phase behavior of reservoir fluids is analyzed and a model for phase behavior in real reservoir fluid simulations is presented. But the model is not suitable for the simulation of real reservoir fluids.
Abstract: Preface. Nomenclature. Phase Behaviour Fundamentals. Reservoir Fluid Composition. Phase Behaviour. Pure compound. Corresponding states. Multicomponent mixture. Classification of Reservoir Fluids. Dry gas. Wet gas. Gas condensate. Volatile oil. Black oil. References. Exercises. PVT Tests and Correlations. Fluid Sampling. Well preparation. Sample collection. PVT Tests 38. Dry gas. Wet gas. Black oil. Gas condensate. Volatile oil. Emperical Correlations. Black oil. (Bubble point pressure. Gas in solution. Oil formation volume factor. Total formation volume factor. Oil density. Oil viscosity). Natural gas. (Volumetric data. Gas viscosity). Formation water. (Water content of hydrocarbon phase. Hydrocarbon solubility in water. Water formation volume factor. Compressibility of water. Water density. Water viscosity). References. Exercises. Phase Equilibria. Criteria for Equilibrium. Chemical potential. Fugacity. Activity. Equilibrium Ratio. Raoult's law. Henry's law. Emperical correlations. References. Exercises. Equations of State. Viral EOS and its Modifications. Starling-Benedict-Webb-Rubin EOS. Cubic Equations of State. Two-parameter EOS. (Soave-Redlich-Kwong EOS. Peng-Robinson EOS. Volume shift). Three-parameter EOS. (Schmidt-Wenzel EOS, Patel-Teja EOS). Attracting term temperature dependency. Mixing Rules. Random mixing rules. Non-random mixing rules. References. Exercises. Phase Behaviour Calculations. Vapour-Liquid Equilibrium Calculations. Root selection. Rapid flash calculations. Stability Analysis. Stability limit. Critical Point Calculations. Compositional Grading. Equilibrium assumption. Non-equilibrium fluids. Heat of transport. Significance. References. Exercises. Fluid Characterisation. Experimental Methods. Distillation. Gas chromatography. Critical properties. Lee-Kesler correlations. Riazi-Daubert correlations. Perturbation expansion correlations. Description of Fluid Heavy End. Single carbon number function. Continuous description. Direct application. References. Exercises. Gas Injection. Miscibility Concepts. Miscibility in Real Reservoir Fluids. Experimental Studies. Slim tube. Rising bubble apparatus. Contact experiments. Prediction of Miscibility Conditions. First contact miscibility. Vaporising gas drive. Condensing-vaporising gas drive. References. Exercises. Interfacial Tension. Measurement Methods. Prediction of Interfacial Tension. Parachor method. Corresponding states correlation. Comparison of predictive methods. Water-Hydrocarbon Interfacial Tension. References. Exercises. Application in Reservoir Simulation. Grouping. Group selection. Group properties. Composition retrieval. Comparison of EOS. Phase composition. Saturation pressure. Density. Gas and liquid volumes. Robustness. Tuning of EOS. Fluid characterisation. Selection of EOS. Experimental data. Selection of regression variables. Limits of tuned parameters. Methodology. Dynamic Validation of Model. Relative permeability function. Viscosity prediction.

583 citations


"Prediction of Bubble Point Pressure..." refers methods in this paper

  • ...This property can be obtained in two ways: a) using experiments and sampling from bottom hole b) or through experimental equations where the information related to these equations is gathered from field data [7]....

    [...]

Journal ArticleDOI
Oistein Glaso1

379 citations


"Prediction of Bubble Point Pressure..." refers methods in this paper

  • ...Then, in 1980 Glaso (1980) [35] used 45 oil samples from the North Sea region to predict correlations to determine BPP and several other parameters (OFVF, Rs, and dead oil viscosity (μOD)) where an average error of 20....

    [...]

  • ...Then, in 1980 Glaso (1980) [35] used 45 oil samples from the North Sea region to predict correlations to determine BPP and several other parameters (OFVF, Rs, and dead oil viscosity (µOD)) where an average error of 20.43% was reported for BPP prediction....

    [...]

  • ..., (2003) [35] using 92, 282 and 160 data for predicted BPP using artificial neural network (ANN) model was used where the error rate of APD% = 645, -0....

    [...]

Journal ArticleDOI
TL;DR: This review summarizes the different properties of gas hydrates as well as their formation and dissociation kinetics and then reviews the fast-growing literature reporting their role and applications in the aforementioned fields, mainly concentrating on advances during the last decade.
Abstract: Gas hydrates have received considerable attention due to their important role in flow assurance for the oil and gas industry, their extensive natural occurrence on Earth and extraterrestrial planets, and their significant applications in sustainable technologies including but not limited to gas and energy storage, gas separation, and water desalination Given not only their inherent structural flexibility depending on the type of guest gas molecules and formation conditions, but also the synthetic effects of a wide range of chemical additives on their properties, these variabilities could be exploited to optimise the role of gas hydrates This includes increasing their industrial applications, understanding and utilising their role in Nature, identifying potential methods for safely extracting natural gases stored in naturally occurring hydrates within the Earth, and for developing green technologies This review summarizes the different properties of gas hydrates as well as their formation and dissociation kinetics and then reviews the fast-growing literature reporting their role and applications in the aforementioned fields, mainly concentrating on advances during the last decade Challenges, limitations, and future perspectives of each field are briefly discussed The overall objective of this review is to provide readers with an extensive overview of gas hydrates that we hope will stimulate further work on this riveting field

349 citations

Journal Article

276 citations


"Prediction of Bubble Point Pressure..." refers methods in this paper

  • ...First in 1947, Standing (1947) [34] established two correlations to predict oil formation volume factor (OFVF) and BPP with input data parameters temperature (T), solution gas-oil ratio (Rs), gas specific gravity (γg) and oil density (API) which were obtained using the laboratory analyzes carried…...

    [...]