Analysis of COP stability in a refrigeration system using artificial neural networks

This paper presents the application of an artificial neural network to perform an analysis of the Coefficient of Performance for a compression vapor system operating with R1234yf. A testing facility was built to measure several parameters at the input and at the output of the refrigeration system. These parameters were: the compressor rotation speed, the temperature, and the volumetric flow in the secondary fluids. An artificial neural network was trained to model the behavior of the refrigeration system. A random variable with a uniform distribution was applied to one input of the artificial neural network to measure the effect of this parameter on the Coefficient of Performance. Color plots were built to show the efficiency of the systems under different working conditions. Computer simulations using artificial neural networks were used to analyze the refrigeration system, and observe the best performance of this system. In the same way, these simulations were used to identify which parameter affect the most the coefficient of performance of the installation.

[1]  Sergio E. Ledesma-Orozco,et al.  Analysis of a variable speed vapor compression system using artificial neural networks , 2013, Expert Syst. Appl..

[2]  Lei Zhao,et al.  Neural modeling of vapor compression refrigeration cycle with extreme learning machine , 2014, Neurocomputing.

[3]  Bijan Samali,et al.  A comparative study on the effect of different strategies for energy saving of air-cooled vapor compression air conditioning systems , 2014 .

[4]  K. Sopian,et al.  Artificial neural network analysis of liquid desiccant regenerator performance in a solar hybrid air-conditioning system , 2013 .

[5]  F. Liu,et al.  Performance prediction for a parallel flow condenser based on artificial neural network , 2014 .

[6]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[7]  K. Pearson.  Contributions to the Mathematical Theory of Evolution. II. Skew Variation in Homogeneous Material , 1895 .

[8]  M. Hosoz,et al.  Artificial neural network analysis of an automobile air conditioning system , 2006 .

[9]  Xianbiao Bu,et al.  Performance characteristics of R1234yf ejector-expansion refrigeration cycle , 2014 .

[10]  Jui-Sheng Chou,et al.  Smart meter monitoring and data mining techniques for predicting refrigeration system performance , 2014, Expert Syst. Appl..

[11]  Martin T. Hagan,et al.  Enhanced recurrent network training , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[12]  Mustafa Inalli,et al.  Performance prediction of a ground-coupled heat pump system using artificial neural networks , 2008, Expert Syst. Appl..

[13]  W. Ramsey,et al.  The Cambridge Handbook of Artificial Intelligence , 2014 .

[14]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[15]  A. Ravishankara,et al.  CF3CF=CH2 and (Z)-CF3CF=CHF: temperature dependent OH rate coefficients and global warming potentials. , 2008, Physical chemistry chemical physics : PCCP.

[16]  Haslinda Mohamed Kamar,et al.  Artificial neural networks for automotive air-conditioning systems performance prediction , 2013 .

[17]  H. Metin Ertunç,et al.  An adaptive neuro-fuzzy inference system model for predicting the performance of a refrigeration system with a cooling tower , 2011, Expert Syst. Appl..

[18]  Barbara H. Minor,et al.  Flammability characteristics of HFO‐1234yf , 2010 .

[19]  J. E. Glynn,et al.  Numerical Recipes: The Art of Scientific Computing , 1989 .

[20]  Mustafa Inalli,et al.  Modeling a ground-coupled heat pump system by a support vector machine , 2008 .

[21]  O. Nielsen,et al.  Atmospheric chemistry of CF3CFCH2: Kinetics and mechanisms of gas-phase reactions with Cl atoms, OH radicals, and O3 , 2007 .

[22]  Honghyun Cho,et al.  Performance characteristics of an automobile air conditioning system with internal heat exchanger using refrigerant R1234yf , 2013 .

[23]  Ozgur Solmaz,et al.  Hourly cooling load prediction of a vehicle in the southern region of Turkey by Artificial Neural Network , 2014 .

[24]  M. Mohanraj,et al.  Applications of artificial neural networks for refrigeration, air-conditioning and heat pump systems—A review , 2012, Renewable and Sustainable Energy Reviews.

[25]  Joaquín Navarro-Esbrí,et al.  Comparative study of transcritical vapor compression configurations using CO2 as refrigeration mode base on simulation , 2013 .

[26]  Sad Jarall,et al.  Study of refrigeration system with HFO-1234yf as a working fluid , 2012 .

[27]  J. Navarro-Esbrí,et al.  Experimental analysis of R1234yf as a drop-in replacement for R134a in a vapor compression system , 2013 .

[28]  Önder Kizilkan,et al.  Thermodynamic analysis of variable speed refrigeration system using artificial neural networks , 2011, Expert Syst. Appl..