GA-RBF model for prediction of dew point pressure in gas condensate reservoirs

Najafi‐Marghmaleki, Adel; Tatar, Afshin; Barati-Harooni, Ali; Choobineh, Mohammad-Javad; Mohammadi, Amir H.

doi:10.1016/j.molliq.2016.08.087

Cited by 21 publications

(14 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For small and reliable datasets, SVM framework is preferred while for larger data sets, neural network models perform better. The accuracy of predictions of each algorithm used in this study can be improved by incorporating optimization techniques such as genetic algorithm [20,21], swarm algorithm [16,28] and fuzzy logic [17].…”

Section: Resultsmentioning

confidence: 99%

“…This limits the accuracy of empirical correlations especially when estimating dewpoint pressure at elevated temperature conditions. Many researchers have explored the potential of applying artificially intelligent tools and other robust techniques such as; artificial neural networks (ANNs) [10, [17][18][19], support vector machine (SVM) [16,20], genetic algorithm (GA) [21,22], multi-gene genetic programming approach Hossein [23] and swarm particle optimization (SPO) [16] to predict dewpoint pressure of gas condensate reservoirs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance evaluation of machine learning algorithms in predicting dew point pressure of gas condensate reservoirs

et al. 2020

View full text Add to dashboard Cite

Accurate knowledge of the dew point pressure for a gas condensate reservoir is necessary for optimizing mitigation operations during field development plan. This study explores the use of machine learning models in predicting the dew point pressure of gas condensate reservoirs. 535 experimental dew point pressure data-points with maximum temperature and pressure of 304 °F and 10,500 psi were used for this analysis. First, a standard multiple linear regression (MLR) was used as a benchmark for comparing the performance of the machine learning models. Multilayer perceptron Neural Networks (MLP) [optimized for the number of neurons and hidden layers], Support Vector Machine (SVM) [using radial basis function kernel] and Decision Tree [Gradient boost Method (GBM) and XG Boost (XGB)] algorithms were used to predict the dew point pressure. The performance of these algorithms was then compared with results obtained from published machine learning models. The input parameters for the model include; gas composition, specific gravity, the molecular weight of the heavier component and compressibility factor. The performances of these algorithms were analysed using root mean square error (RMSE), absolute average relative deviation percentage (AARD %) and coefficient of determination (R 2).

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Performance evaluation of machine learning algorithms in predicting dew point pressure of gas condensate reservoirs

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This situation may seriously affect the learning efficiency, so the GA is introduced to obtain the initial weights in this article, which improves the training efficiency and prediction accuracy of the neural network. [26][27][28] RBF neural network. The structure of the RBF network is a three-layer forward network similar to that of the multilayer forward network.…”

Section: Optimal Trajectory Of the Manipulator Solved By The Ga-rbf Mmentioning

confidence: 99%

Optimal control research on a manipulator’s combined feedback device by the variational method genetic algorithm radial basis function method

Wang

Zhaoyang

2019

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This article aims to improve the accuracy of each joint in a manipulator and to ensure the high-speed and real-time requirements. A method called the variational method genetic algorithm radial basis function, which is based on a combination feedback controller, is proposed to solve the optimal control problem. It is proposed a combined feedback with a linear part and a nonlinear part. We reconstruct the manipulator's kinematics and dynamics models with a feedback control. In this model, the optimal trajectory, which was solved by the variation method, is regarded as the desired output. The other one is also established an improved genetic algorithm radial basis function neural network model. The optimal trajectory is rapidly solved by using the desired output and the improved genetic algorithm radial basis function neural network. This method can greatly improve the speed of the calculation and guarantee real-time performance while simultaneously ensuring accuracy.

show abstract

“…In these reservoirs, the process of condensate production is based on certain thermodynamic behavior, in which the reverse behavior occurs by decreasing the pressure, rather than expanding the gas or liquid evaporation (Ahmed 2006;Mohammadi et al, 2012). The drop, in production pressure around the well in this type of reservoir, causes a two-phase flow due to the fluidization of a portion of the gas in this area (Arabloo et al 2013;Kamari et al 2016;Najafi-Marghmaleki et al 2016. This twophase flow grows by moving the pressure profile toward the center of the produced well.…”

Section: Introductionmentioning

confidence: 99%

Wettability alteration and enhanced gas condensate recovery by treatment of carbonate reservoir rock using supercritical R134A and R404A gases

Nowrouzi

Manshad

Mohammadi

2020

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

The pressure drop around the well in the production from a gas condensate reservoir causes the formation of condensate in the area before it reaches the well and surface space. This condensate and occasionally water in the porous medium can block the well and create an additional pressure drop. Studies show that the chemical treatment of this area eliminates the problem by altering the reservoir rock wettability toward a moderate and strong gasphilicity. For this purpose, fluoropolymers-, fluorosurfactants-, and fluorochemicals-coated nanoparticles can be used. In this work, we have studied two types of fluoride gas namely R134A and R404A, which are widely used in refrigeration industry as refrigerant gases, perfumery, and industrial detergents. The basis of this study was the aging of rock samples in thin sections and plugs in these two gases at different pressures above the critical pressures of them at 70 °C at different times and then conducting the contact angle experiments by placing the drop of water and condensate on the cross sections and then performing imbibition tests using plugs. The results show that in addition to the efficiency of both gases in wettability alteration to gasphilic, the gasphilic intensity obtained at constant temperature depends on the pressure and the aging time of the samples.

show abstract

GA-RBF model for prediction of dew point pressure in gas condensate reservoirs

Cited by 21 publications

References 22 publications

Performance evaluation of machine learning algorithms in predicting dew point pressure of gas condensate reservoirs

Performance evaluation of machine learning algorithms in predicting dew point pressure of gas condensate reservoirs

Optimal control research on a manipulator’s combined feedback device by the variational method genetic algorithm radial basis function method

Wettability alteration and enhanced gas condensate recovery by treatment of carbonate reservoir rock using supercritical R134A and R404A gases

Contact Info

Product

Resources

About