NEURAL NETWORK PREDICTION OF REFRIGERANTS PROPERTIES: REVIEW

Authors

  • С.В. Артеменко Odessa National Academy of Food Technologies, Educational and Research Institute of Refrigeration, cryotechnology and Ecoenergetics n.a. V.S. Martynovskiy, 1/3 Dvoryanskaya str., Odessa, 65082, Ukraine

DOI:

https://doi.org/10.15673/0453-8307.6/2014.30992

Keywords:

Artificial neural network – Properties of refrigerant – Phase equilibria

Abstract

The review of recent papers related to modeling of refrigerant properties using artificial neural networks as an alternative to conventional thermodynamic approach for modeling prediction of thermodynamic properties of refrigerants has been given in the paper. The study also discusses efficiency, adequacy and limitation of this approach.

References

REFERENCES

Zhang G. et al. Forecasting with artificial neural networks // The state of the art. International Journal of forecasting. – 1998. – 14. – pp.35 – 62.

Tayagarajan T. et al. Artificial neural networks: Principles and application to model based control of drying systems – a review // Drying Technology. – 1998. – 16. – pp.931 –966. DOI: 10.1080/07373939808917449

Gardner M.W., Dorling S.R. Artificial neural net-works (the multilayer perceptron) – a review of applications in the atmospheric sciences // Atmospheric Environment. – 1998. – 32. – pp. 2627 – 2636. DOI: 10.1016/S1352-2310(97)00447-0

Mellit A. et al. Artificial intelligence techniques for sizing photovoltaic systems: a review // Renewable and Sustainable Energy Reviews. – 2009. – 13. – p.406 – 419. DOI: 10.1016/j.rser.2008.01.006

Kalogirou S. Applications of artificial neural net-works in energy systems: a review // Energy Conver-sion and Management. – 1999. – 40. – pp. 1073–1087. DOI: 10.1016/S0140-6701(00)94999-3

Kalogirou S. Applications of artificial neural net-works for energy systems // Applied Energy. – 2000. – 67. – pp.17–35.

DOI: 10.1016/B978-0-08-043877-1.50005-X

Kalogirou S. Artificial neural networks in renew-able energy systems applications: a review // Renew-able and Sustainable Energy Reviews. – 2001. – 5. – pp. 373–401. DOI:10.1016/S1364-0321(01)00006-5

Михайленко В.С., Харченко Р.Ю. Определе-ние параметров математических моделей энерго-блоков ТЭС на основе аппарата гибридных сетей // Информатика и математические методы в моделировании. – 2012. – 2(3). – с. 286-292

Hebb D.O. The Organization of Behavior. - New York: Wiley, 1949

Rosenblatt F. Principles of Neurodynamics, Washington D.C.: Spartan Press, 1961

Davies M., Jones J. // Trans. Faraday Soc. – 1954. – 50. – p. 1042

Rumelhart D. E., Hinton G. E., Williams R. J. Learning internal representations by error propagation // Parallel Data Processing.-1986.- Vol.1.- p. 318-362 DOI: 10.1016/B978-1-4832-1446-7.50035-2

Moller M.F. A scaled conjugate gradient algo-rithm for fast supervised learning // Neural Networks. - 1993.- Vol. 6.  p. 525-533 DOI: 10.1016/S0893-6080(05)80056-5

Menhaj M. Training feedforward networks with the Marquardt algorithm // IEEE Transactions on Neural Networks.-1994.  Vol. 5(6).  p. 989-993. DOI: 10.1109/72.329697

Battiti R. First and second order methods for learning: Between steepest descent and Newton's method // Neural Computation. – 1992. – Vol. 4(2). – p. 141-166. DOI:10.1162/neco.1992.4.2.141

Riedmiller M., Braun H. A direct adaptive meth-od for faster backpropagation learning: The RPROP algorithm // Proceedings of the IEEE International Conference on Neural Networks.  1993.

DOI: 10.1109/ICNN.1993.298623

Nguyen D., Widrow B. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights // Proceedings of the International Joint Conference on Neural Networks.-1990.- Vol 3.- p.21-26.

DOI: 10.1109/IJCNN.1990.137819

Chen S., Cowan С., Grant P. Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks // IEEE Transactions on Neural Networks. – 1991. – vol.2(2). – P. 302-309.

DOI: 10.1109/72.80341

Elman J. Finding structure in time // Cognitive Science. – 1990. – vol.14. – P.179-211.

DOI: 10.1207/s15516709cog1402_1

Kohonen T. Self-Organization and Associative Memory.- 2nd Edition, Berlin: Springer-Verlag, 1987

Sozen A, Ozalp M, Arcaklioglu E. Calculation for the thermodynamic properties of an alternative refrig-erant (R508B) using artificial neural network // Ap-plied Thermal Engineering. – 2007. – 27. – pp.551 – 559. DOI: 10.1016/j.applthermaleng.2006.06.003

Sozen A, et al. Determination of thermodynamic properties of an alternative refrigerant (R407C) using artificial neural network. // Expert Systems with Ap-plications. – 2009. – 36. – pp.:4346–4356.

DOI:10.1016/j.eswa.2008.05.023

Sozen A, Arcaklioglu E, Menlik T. Derivation of empirical equations for thermodynamic properties of a ozone safe refrigerant (R404A) using artificial neural network // Expert Systems with Applications. – 2010. – 37. – pp. 1158–1168.

DOI: 10.1016/j.eswa.2009.06.016

Scalabrin G, Cristofoli G. The viscosity surfaces of R152a in the form of multilayer feed forward neu-ral networks // International Journal of Refrigeration. – 2003. – 26. – pp. 302–314. DOI: 10.1016/S0140-7007(02)00113-5

Mohebbi A, Taheri M, Soltani A. A neural net-work for predicting saturated liquid density using ge-netic algorithm for pure and mixed refrigerants. Inter-national // Journal of Refrigeration. – 2008. – 31. – pp.:1317–1327. DOI: 10.1016/j.ijrefrig.2008.04.008

Sencan A, Kose II, Selbas R. Prediction of thermophysical properties of mixed refrigerants using artificial neural network // Energy Conversion and Management. - 2011. – 52. – pp.:958–974.

DOI: 10.1016/j.enconman.2010.08.024

Moghadassi A.R., Nikkholgh M.R., Parvizian F., Hosseini S.M. Estimation of thermophysical properties of dimethyl ether as a commercial refrigerant based on artificial neural networks // Expert Systems with Applications. – 2010. – 37.– pp.7755–7761. DOI: 10.1016/j.eswa.2010.04.065

Kurt H., Kayfeci M., Prediction of thermal con-ductivity of ethylene glycol–water solutions by using artificial neural networks // Applied Energy. – 2009. – 86. – pp.2244–2248.

DOI: 10.1016/j.apenergy.2008.12.020

Eslamloueyan R., Khademi M.H. Estimation of thermal conductivity of pure gases by using artificial neural networks.//International Journal of Thermal Sciences. – 2009. – 48. – pp.1094-1101.

DOI: 10.1016/j.ijthermalsci.2008.08.013

Sozen A., Ozalp M., Arcaklioglu E. Investigation of thermodynamic properties of refrigerant/absorbent couples using artificial neural networks. Chemical Engineering and Processing 2004;43:1253–1264. DOI: 10.1016/S0140-6701(05)80375-3

Sozen A., Arcaklioglu E., Ozalp M. Formulation based on artificial neural network of thermodynamic properties of ozone friendly refrigerant/absorbent cou-ples. Applied Thermal Engineering 2005;25:1808–1820. DOI: 10.1016/j.applthermaleng.2004.11.003

Sencan A., Yakut K.A., Kalogirou S.A. Thermo-dynamic analysis of absorption systems using artifi-cial neural network. Renewable Energy 2006;31:29–43. DOI: 10.1016/j.renene.2005.03.011

Urata S. et al. Prediction of vapor–liquid equilib-rium for binary systems containing HFEs by using artificial neural network // Fluid Phase Equilibria. – 2002. – 199. – pp. 63–78.

DOI: 10.1016/S0378-3812(01)00814-7

Artemenko S., Mazur V. Azeotropy in the natural and synthetic refrigerant mixtures // International Journal of Refrigeration. – 2007. – 30(5). – pp. 831-839. DOI: 10.1016/j.ijrefrig.2006.11.010

Mohanty S. Estimation of vapour liquid equilibria for the system carbon dioxide–difluoromethane using artificial neural networks. // International Journal of Refrigeration. – 2006. – 29. – pp.243–249. DOI: 10.1016/j.ijrefrig.2005.05.007

carbon dioxide–difluoromethane using artificial neural networks. // International Journal of Refrigeration. – 2006. – 29. – pp.243–249.

Published

2015-01-16

Issue

Section

Refrigerating and accompanying technologies