COMPARATIVE ANALYSIS OF NEURAL NETWORK AND NEURO-FUZZY SYSTEM FOR THERMODYNAMIC PROPERTIES OF REFRIGERANTS

Fast and simple determination of the thermodynamic properties of refrigerants is very important for analysis of vapor compression refrigeration systems. Although tables are available for refrigerants, limited data of tables are not useful in the simulation of refrigeration systems. The aim of this study is to determine the thermodynamic properties such as enthalpy, entropy, specific volume of the R413A, R417A, R422D, and R423A by means of the artificial neural networks (ANN) and adaptive neuro-fuzzy (ANFIS) system. The results of the ANN are compared with the ANFIS, in which the same data sets are used. The ANFIS model is slightly better than ANN. Therefore, instead of limited data as found in the literature, thermodynamic properties for every temperature and pressure value with the ANFIS are easily estimated.

[1]  Chitralekha Mahanta,et al.  A novel approach for ANFIS modelling based on full factorial design , 2008, Appl. Soft Comput..

[2]  Reşat Selbaş,et al.  Prediction of thermophysical properties of mixed refrigerants using artificial neural network , 2011 .

[3]  L. P. J. Veelenturf,et al.  Analysis and applications of artificial neural networks , 1995 .

[4]  Adnan Sözen,et al.  Derivation of empirical equations for thermodynamic properties of a ozone safe refrigerant (R404a) using artificial neural network , 2010, Expert Syst. Appl..

[5]  Engin Avci,et al.  Comparison of wavelet families for texture classification by using wavelet packet entropy adaptive network based fuzzy inference system , 2008, Appl. Soft Comput..

[6]  Adnan Sözen,et al.  Calculation for the thermodynamic properties of an alternative refrigerant (R508b) using artificial neural network , 2007 .

[7]  Erol Arcaklioğlu,et al.  Thermodynamic analyses of refrigerant mixtures using artificial neural networks , 2004 .

[8]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[9]  Servet Soyguder,et al.  An expert system for the humidity and temperature control in HVAC systems using ANFIS and optimization with Fuzzy Modeling Approach , 2009 .

[10]  S. M. Hosseini,et al.  Estimation of thermophysical properties of dimethyl ether as a commercial refrigerant based on artificial neural networks , 2010, Expert Syst. Appl..

[11]  A. Şencan,et al.  Prediction of Liquid and Vapor Enthalpies of Ammonia-water Mixture , 2011 .

[12]  Lotfi A. Zadeh,et al.  Fuzzy Logic Toolbox User''''s Guide , 1995 .

[13]  Mustafa Inalli,et al.  Modelling a ground-coupled heat pump system using adaptive neuro-fuzzy inference systems , 2008 .

[14]  S. Kalogirou,et al.  A new approach using artificial neural networks for determination of the thermodynamic properties of fluid couples , 2005 .

[15]  Adnan Sözen,et al.  Determination of thermodynamic properties of an alternative refrigerant (R407c) using artificial neural network , 2009, Expert Syst. Appl..

[16]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[17]  Li-Chih Ying,et al.  Using adaptive network based fuzzy inference system to forecast regional electricity loads , 2008 .

[18]  Sami Ekici,et al.  An adaptive neuro-fuzzy inference system (ANFIS) model for wire-EDM , 2009, Expert Syst. Appl..

[19]  Behdad Moghtaderi,et al.  A neuro–fuzzy model for prediction of the indoor temperature in typical Australian residential buildings , 2009 .

[20]  Reşat Selbaş,et al.  Prediction of thermodynamic properties of refrigerants using data mining , 2011 .

[21]  Arzu Şencan,et al.  Modeling of thermodynamic properties of refrigerant/absorbent couples using data mining process , 2007 .

[22]  LiMin Fu,et al.  Neural networks in computer intelligence , 1994 .