A Data-Driven Machine Learning Approach to Predict the Natural Gas Density of Pure and Mixed Hydrocarbons

Natural gas is one of the main fossil energy resources, and its density is an effective thermodynamic property, which is required in almost every pressure–volume–temperature (PVT) calculation. Conventionally, the density of natural gas is determined from the gas deviation (Z-) factor using an equation of states (EOS). Several models have been developed to estimate the Z-factor utilizing the EOS approach, however, most of these models involve complex calculations and require many input parameters. In this study, an improved natural gas density prediction model is presented using robust machine learning techniques such as artificial neural networks and functional networks. A total of 3800 data points were collected from different published sources covering a wide range of input parameters. Moreover, explicit empirical correlations are also derived that can be used explicitly without the need for any machine learning-based software. The proposed correlations are a function of molecular weight (Mw) of natural gas, pseudo-reduced pressure (Ppr), and pseudo-reduced temperature (Tpr). The proposed correlations can be applied for the gases having Mw between 16 and 129.7 g, Ppr range of 0.02–29.3, and Tpr range 0.of 5–2.7. The prediction of the new correlation was compared against the most common methods for determining the natural gas density. The developed correlation showed better estimation than the common prediction models. The estimation error was reduced by 2% on average using the new correlations, and the coefficient of determination (R2) was 0.98 using the developed correlation.

[1]  Zeeshan Tariq,et al.  A Rigorous Data-Driven Approach to Predict Poisson's Ratio of Carbonate Rocks Using a Functional Network , 2018 .

[2]  Anifowose Fatai,et al.  Investigating the effect of training–testing data stratification on the performance of soft computing techniques: an experimental study , 2017, J. Exp. Theor. Artif. Intell..

[3]  S. Alimohammadi,et al.  Estimation of asphaltene precipitation in light, medium and heavy oils: experimental study and neural network modeling , 2017, Neural Computing and Applications.

[4]  Alireza Baghban,et al.  Utilization of LSSVM algorithm for estimating synthetic natural gas density , 2018 .

[5]  Putu D. Raharja,et al.  Estimation of Permeability from Wireline Logs in a Middle Eastern Carbonate Reservoir Using Fuzzy Logic , 2007 .

[6]  A. Abdulraheem,et al.  Applying Artificial Intelligence Techniques to Develop Permeability Predictive Models using Mercury Injection Capillary-Pressure Data , 2013 .

[7]  Tarek Ahmed,et al.  Reservoir Engineering Handbook , 2002 .

[8]  M. A. Abido.  Optimal des'ign of Power System Stabilizers Using Particle Swarm Opt'imization , 2002, IEEE Power Engineering Review.

[9]  Hadi Fattahi,et al.  Estimation of asphaltene precipitation from titration data: a hybrid support vector regression with harmony search , 2014, Neural Computing and Applications.

[10]  Riyaz Kharrat,et al.  Forecasting gas density using artificial intelligence , 2017 .

[11]  Nilanjan Dey,et al.  Particle swarm optimization trained neural network for structural failure prediction of multistoried RC buildings , 2016, Neural Computing and Applications.

[12]  Amin Bemani,et al.  Applying ANFIS-PSO algorithm as a novel accurate approach for prediction of gas density , 2018 .

[13]  Abdolhossein Hemmati-Sarapardeh,et al.  Using an artificial neural network to predict carbon dioxide compressibility factor at high pressure and temperature , 2015, Korean Journal of Chemical Engineering.

[14]  Efficient methods for calculations of compressibility, density and viscosity of natural gases , 2004 .

[15]  Anifowose Fatai,et al.  Recent advances in the application of computational intelligence techniques in oil and gas reservoir characterisation: a comparative study , 2014, J. Exp. Theor. Artif. Intell..

[16]  A. Abdulraheem,et al.  Artificial Intelligence Based Estimation of Water Saturation Using Electrical Measurements Data in a Carbonate Reservoir , 2015 .

[17]  Mohammad Rasheed Khan,et al.  Machine Learning Derived Correlation to Determine Water Saturation in Complex Lithologies , 2018 .

[18]  Syed Masiur Rahman,et al.  Non-linear Heterogeneous Ensemble Model for Permeability Prediction of Oil Reservoirs , 2013 .

[19]  V M F Mendes,et al.  Hybrid Wavelet-PSO-ANFIS Approach for Short-Term Wind Power Forecasting in Portugal , 2011, IEEE Transactions on Sustainable Energy.

[20]  Bo Shen,et al.  Fuzzy-Logic-Based Control, Filtering, and Fault Detection for Networked Systems: A Survey , 2015 .

[21]  Mahmood Bataee,et al.  Neural Networks in BHCP Prediction Performed Much Better Than Mechanistic Models , 2010 .

[22]  M. Mahmoud.  Development of a New Correlation of Gas Compressibility Factor (Z-Factor) for High Pressure Gas Reservoirs , 2014 .

[23]  E. Moiseeva,et al.  Compressibility factor of natural gas determination by means of molecular dynamics simulations , 2019, AIP Advances.

[24]  B. Adeyemi,et al.  Predicting Wax Formation Using Artificial Neural Network , 2012 .

[25]  James P. Brill,et al.  A Study of Two-Phase Flow in Inclined Pipes , 1973 .

[26]  Fred H. Poettman,et al.  The Multiphase Flow of Gas, Oil, and Water Through Vertical Flow Strings with Application to the Design of Gas-lift Installations , 1952 .

[27]  Zhao Hui,et al.  Optimal Design of Power System Stabilizer Using Particle Swarm Optimization , 2006 .

[28]  C. Gokceoğlu,et al.  Models to predict the uniaxial compressive strength and the modulus of elasticity for Ankara Agglomerate , 2004 .

[29]  Reza Shams,et al.  New correlations for predicting pure and impure natural gas viscosity , 2016 .

[30]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[31]  E. Castillo,et al.  Functional Networks: A New Network‐Based Methodology , 2000 .

[32]  Enrique Castillo,et al.  Functional Networks , 1998, Neural Processing Letters.

[33]  Mahmood Farzaneh-Gord,et al.  Developing novel correlations for calculating natural gas thermodynamic properties , 2011 .

[34]  H. M. Maher,et al.  Application of artificial neural networks for response surface modelling in HPLC method development , 2012 .

[35]  Manson Benedict,et al.  An Empirical Equation for Thermodynamic Properties of Light Hydrocarbons and Their Mixtures I. Methane, Ethane, Propane and n‐Butane , 1940 .

[36]  M. Asoodeh.  Prediction of Poisson's Ratio from Conventional Well Log Data: A Committee Machine with Intelligent Systems Approach , 2013 .

[37]  Liangliang Huang,et al.  Natural gas density under extremely high pressure and high temperature: Comparison of molecular dynamics simulation with corresponding state model , 2021, Chinese Journal of Chemical Engineering.

[38]  Daniel L. Gysling,et al.  An aeroelastic model of Coriolis mass and density meters operating on aerated mixtures , 2007 .

[39]  Shunxi Zhang,et al.  A new model for the accurate calculation of natural gas viscosity , 2017 .

[40]  Kenneth R. Hall,et al.  Isothermal PρT measurements on Qatar’s North Field type synthetic natural gas mixtures using a vibrating-tube densimeter , 2012 .

[41]  A. Abdulraheem,et al.  Prediction of Rock Mechanical Parameters for Hydrocarbon Reservoirs Using Different Artificial Intelligence Techniques , 2009 .

[42]  S. Syafiie,et al.  Development of a hybrid PSO–ANN model for estimating glucose and xylose yields for microwave-assisted pretreatment and the enzymatic hydrolysis of lignocellulosic biomass , 2018, Neural Computing and Applications.

[43]  Y. Çengel,et al.  Thermodynamics : An Engineering Approach , 1989 .

[44]  B. Sage,et al.  Phase Equilibria in Hydrocarbon Systems Methane–n-Butane System in the Gaseous and Liquid Regions , 1940 .

[45]  Ebru Akcapinar Sezer,et al.  Modeling of the uniaxial compressive strength of some clay-bearing rocks using neural network , 2011, Appl. Soft Comput..

[46]  Emre Artun.  Characterizing interwell connectivity in waterflooded reservoirs using data-driven and reduced-physics models: a comparative study , 2015, Neural Computing and Applications.

[47]  Marc J. Assael,et al.  Dynamic Viscosity Measurements of Three Natural Gas Mixtures—Comparison against Prediction Models , 2007 .

[48]  David A. Wood,et al.  Transparent machine learning provides insightful estimates of natural gas density based on pressure, temperature and compositional variables , 2020 .

[49]  Dimitrios P. Tassios,et al.  An Equation of State for Associating Fluids , 1996 .

[50]  A. Abdulraheem,et al.  PVT correlations for Pakistani crude oils using artificial neural network , 2017, Journal of Petroleum Exploration and Production Technology.

[51]  Shyamal K. Nath,et al.  Molecular Simulation of Vapor−Liquid Phase Equilibria of Hydrogen Sulfide and Its Mixtures with Alkanes , 2003 .

[52]  David A. Wood,et al.  Performance comparison of bubble point pressure from oil PVT data: Several neurocomputing techniques compared , 2019, Experimental and Computational Multiphase Flow.

[53]  E. M. El-M. Shokir,et al.  Artificial neural networks modeling for hydrocarbon gas viscosity and density estimation , 2011 .

[54]  Yashodhan Keshav Gidh,et al.  Artificial Neural Network Drilling Parameter Optimization System Improves ROP by Predicting/Managing Bit Wear , 2012 .

[55]  Yingjie Yang,et al.  The artificial neural network as a tool for assessing geotechnical properties , 2002 .

[56]  A. Alquraishi,et al.  Viscosity and Density Correlations for Hydrocarbon Gases and Pure and Impure Gas Mixtures , 2009 .

[57]  M. A. Mahmoud.  Development of a New Correlation of Gas Compressibility Factor (Z-Factor) for High Pressure Gas Reservoir , 2013 .

[58]  Mohamed Mahmoud,et al.  Core log integration: a hybrid intelligent data-driven solution to improve elastic parameter prediction , 2019, Neural Computing and Applications.

[59]  Lateef A. Kareem,et al.  New explicit correlation for the compressibility factor of natural gas: linearized z-factor isotherms , 2016, Journal of Petroleum Exploration and Production Technology.

[60]  Md. Rafiul Hassan,et al.  Hydraulic Unit Estimation From Predicted Permeability and Porosity Using Artificial Intelligence Techniques , 2013 .

[61]  M. H. Sefat,et al.  An Artificial Neural Network Approach to Formation Damage Prediction due to Asphaltene Deposition , 2010 .

[62]  Zeeshan Tariq,et al.  New Correlation for the Gas Deviation Factor for High-Temperature and High-Pressure Gas Reservoirs Using Neural Networks , 2019, Energy & Fuels.

[63]  Jane Labadin,et al.  A least-square-driven functional networks type-2 fuzzy logic hybrid model for efficient petroleum reservoir properties prediction , 2012, Neural Computing and Applications.

[64]  E. Vogel,et al.  Viscosity Measurements and Predictions for Natural Gas , 2004 .

[65]  P. M. Dranchuk,et al.  Calculation of Z Factors For Natural Gases Using Equations of State , 1975 .

[66]  T. Blasingame,et al.  Simplified Correlations for Hydrocarbon Gas Viscosity and Gas Density - Validation and Correlation of Behavior Using a Large-Scale Database , 2002 .

[67]  Enrique F. Castillo,et al.  Some Applications of Functional Networks in Statistics and Engineering , 2001, Technometrics.

[68]  M. Michelsen,et al.  Ten Years with the CPA (Cubic-Plus-Association) Equation of State. Part 1. Pure Compounds and Self-Associating Systems , 2006 .

[69]  A. Abdulraheem,et al.  ARTIFICIAL INTELLIGENCE BASED ESTIMATION OF WATER SATURATION IN COMPLEX RESERVOIR SYSTEMS , 2015 .

[70]  Meisam Adibifard,et al.  A stochastic well-test analysis on transient pressure data using iterative ensemble Kalman filter , 2019, Neural Computing and Applications.

[71]  R. P. Sutton,et al.  Fundamental PVT Calculations for Associated and Gas-Condensate Natural Gas Systems , 2005 .

[72]  Sadegh Baziar,et al.  Prediction of water saturation in a tight gas sandstone reservoir by using four intelligent methods: a comparative study , 2016, Neural Computing and Applications.

[73]  A. Khosravi,et al.  Estimation of density and compressibility factor of natural gas using artificial intelligence approach , 2018, Journal of Petroleum Science and Engineering.

[74]  Emad A. El-Sebakhy,et al.  Functional networks as a new data mining predictive paradigm to predict permeability in a carbonate reservoir , 2012, Expert Syst. Appl..

[75]  C. R. Dodson,et al.  Application of Laboratory PVT Data to Reservoir Engineering Problems , 1953 .

[76]  Donald L. Katz,et al.  Density of Natural Gases , 1942 .

[77]  Abouzar Choubineh,et al.  Improved predictions of wellhead choke liquid critical-flow rates: Modelling based on hybrid neural network training learning based optimization , 2017 .

[78]  Judith Gurney.  BP Statistical Review of World Energy , 1985 .

[79]  A. Danesh.  PVT and Phase Behaviour of Petroleum Reservoir Fluids , 1998 .

[80]  Ahmed H. El-Banbi,et al.  PVT Property Correlations: Selection and Estimation , 2018 .

[81]  Jianzhou Wang,et al.  Short-Term Wind Speed Forecasting Using Support Vector Regression Optimized by Cuckoo Optimization Algorithm , 2015 .

[82]  Hossein Jalalifar,et al.  Predicting bottomhole pressure in vertical multiphase flowing wells using artificial neural networks , 2011 .

[83]  S. Moorthi,et al.  Implementation of hybrid ANN-PSO algorithm on FPGA for harmonic estimation , 2012, Eng. Appl. Artif. Intell..