Document Type : Full length


Department of Chemical Engineering, Faculty of Engineering, University of Kurdistan, Sanandaj, Iran


The artificial neural network (ANN) approach was applied to develop simple correlations for predicting the thermal conductivity of nitrogen-methane and carbon dioxide-methane mixtures. The genetic algorithm method was used to obtain global optimum parameters (weights and biases) of the ANNs. The methane mole fraction, temperature, pressure, and density as effective parameters on thermal conductivity were network input variables. 171 and 180 data points related to the nitrogen-methane and carbon dioxide-methane gas mixtures, respectively, divided to test and train datasets. Simple correlations were obtained due to the small number of optimal neurons in the ANN structures. The mean relative errors of 0.206% and 0.199% for the testing dataset indicate the high accuracy and validation of the correlations. The work indicates that artificial intelligence approaches are very useful for thermal conductivity modeling in natural gases. A sensitivity analysis was performed on all input variables that indicates that the gas mixture density has the greatest impact on the thermal conductivity.


[1]      Bergles, A. E., “The implications and challenges of enhanced heat transfer for the chemical process industries”, Chem. Eng. Res. Des., 79 (4), 437 (2001).
[2]      Beigzadeh, R., Parvareh, A. and Rahimi, M., “Experimental and CFD study of the tube configuration effect on the shell-side thermal performance in a shell and helically coiled tube heat exchanger”, Iranian Journal of Chemical Engineering (IJChE), 12 (2), 13 (2015).
[3]      Pátek, J., Klomfar, J., Čapla, L. and Buryan, P., “Thermal conductivity of carbon dioxide-methane mixtures at temperatures between 300 and 425 K and at pressures up to 12 MPa”, Int. J. Thermophys., 26 (3), 577 (2005).
[4]      Schreiber, M., Vesovic, V. and Wakeham, W. A., “Thermal conductivity of multicomponent polyatomic dilute gas mixtures”, Int. J. Thermophys., 18 (4), 925 (1997).
[5]      Pátek, J., Klomfar, J., Čapla, L. and Buryan, P., “Thermal conductivity of nitrogen-methane mixtures at temperatures between 300 and 425 K and at pressures up to 16 MPa”, Int. J. Thermophys., 24 (4), 923 (2003).
[6]      Pátek, J. and Klomfar, J., “Measurement of the thermal conductivity of argon and methane: A test of a transient hot-wire apparatus”, Fluid Phase Equilib., 198 (1), 147 (2002).
[7]      Panerati, J., Schnellmann, M. A., Patience, C., Beltrame, G. and Patience, G. S., “Experimental methods in chemical engineering: Artificial neural networks-ANNs”, Can. J. Chem. Eng., 97 (9), 2372 (2019).
[8]      Pirdashti, M., Curteanu, S., Kamangar, M. H., Hassim, M. H. and Khatami, M. A., “Artificial neural networks: Applications in chemical engineering”, Rev. Chem. Eng., 29 (4), 205 (2013).
[9]      Beigzadeh, R., Rahimi, M. and Shabanian, S. R., “Developing a feed forward neural network multilayer model for prediction of binary diffusion coefficient in liquids”, Fluid Phase Equilib., 331, 48 (2012).
[10]  Eslamloueyan, R. and Khademi, M. H., “A neural network-based method for estimation of binary gas diffusivity”, Chemom. Intell. Lab. Syst., 104 (2),195 (2010).
[11]  Etebarian, M., “Prediction of true critical temperature and pressure of binary hydrocarbon mixtures: A comparison between the artificial neural networks and the support vector machine”, Iranian Journal of Chemical Engineering (IJChE), 16 (2), 14 (2019).
[12]  Ghaderi, F., Ghaderi, A. H., Najafi, B. and Ghaderi, N., “Viscosity prediction by computational method and artificial neural network approach: The case of six refrigerants”, J. Supercrit. Fluids, 81, 67 (2013).
[13]  Fazlali, A., Koranian, P., Beigzadeh, R. and Rahimi, M., “Application of artificial neural network for vapor liquid equilibrium calculation of ternary system including ionic liquid: Water, ethanol and 1-butyl-3-methylimidazolium acetate”, Korean. J. Chem. Eng., 30 (9), 1681 (2013).
[14]  Eslamloueyan, R. and Khademi, M. H., “Estimation of thermal conductivity of pure gases by using artificial neural networks”, Int. J. Therm. Sci., 48 (6), 1094 (2009).
[15]  Kumar, M., Husain, M., Upreti, N. and Gupta, D. “Genetic algorithm: Review and application”, International Journal of Information Technology and Knowledge Management, 2 (2), 451 (2010).
[16]  Beigzadeh, R. and Eiamsa-Ard, S., “Genetic algorithm multiobjective optimization of a thermal system with three heat transfer enhancement characteristics”, J. Enhanc. Heat Transf., 27 (2), 123 (2020).
[17]  Gopan, V., Wins, K. L. D. and Surendran, A., “Integrated ANN-GA approach for predictive modeling and optimization of grinding parameters with surface roughness as the response”, Mater. Today. Proc., 5 (5), 12133 (2018).
[18]  Beigzadeh, R., Rahimi, M., Jafari, O. and Alsairafi, A. A., “Computational fluid dynamics assists the artificial neural network and genetic algorithm approaches for thermal and flow modeling of air-forced convection on interrupted plate fins”, Numer. Heat Transf. Part A Appl., 70 (5), 546 (2016).
[19]  Kumar, V., Kumar, A., Chhabra, D. and Shukla, P., “Improved biobleaching of mixed hardwood pulp and process optimization using novel GA-ANN and GA-ANFIS hybrid statistical tools”, Bioresour. Technol., 271, 274 (2019).
[20]  Hussain, M. A., “Review of the applications of neural networks in chemical process control-simulation and online implementation”, Artif. Intell. Eng., 13 (1), 55 (1999).
[21]  Safamirzaei, M. and Modarress, H., “Modeling and predicting solubility of n-alkanes in water”, Fluid Phase Equilib., 309 (1), 53 (2011).
[22]  Beigzadeh, R., Rahimi, M., Parvizi, M. and Eiamsa-Ard, S., “Application of ann and ga for the prediction and optimization of thermal and flow characteristics in a rectangular channel fitted with twisted tape vortex generators”, Numer. Heat Transf. Part A Appl., 65 (2), 186 (2014).
[23]  Ghritlahre, H. K. and Prasad, R. K., “Prediction of heat transfer of two different types of roughened solar air heater using artificial neural network technique”, Therm. Sci. Eng. Prog., 8, 145 (2018).
[24]  Xi, L., Muzhou, H., Lee, M. H., Li, J., Wei, D., Hai, H. and Wu, Y., “A new constructive neural network method for noise processing and its application on stock market prediction”, Appl. Soft. Comput., 15, 57 (2014).
[25]  Hagan, M. T. and Menhaj, M. B., “Training feedforward networks with the Marquardt algorithm”, IEEE Trans. Neural Networks, 5 (6), 989 (1994).
[26]  Chang, Y. T., Lin, J., Shieh, J. S. and Abbod, M. F., “Optimization the initial weights of artificial neural networks via genetic algorithm applied to hip bone fracture prediction”, Adv. Fuzzy Syst., 2012 (9), (2012).
[27]  Karimi, H. and Yousefi, F., “Application of artificial neural network-genetic algorithm (ANN-GA) to correlation of density in nanofluids”, Fluid Phase Equilib., 336, 79 (2012).
[28]  Gupta, S. K. and Ramteke, M., Applications of genetic algorithms in chemical engineering I: Methodology, Applications of metaheuristics in process engineering, Springer, p. 39 (2014).
[29]  Vesovic, V. and Wakeham, W. A., “Prediction of the thermal conductivity of fluid mixtures over wide ranges of temperature and pressure”, High Temp. High Press., 23 (2), 179 (1991).
[30]  Jarrahian, A. and Heidaryan, E., “A simple correlation to estimate natural gas thermal conductivity”, J. Nat. Gas. Sci. Eng., 18, 446 (2014).
[31]  Garson, G. D., “Interpreting neural network connection weights”, AI Expert, 6 (4), 47 (1991).