Statistical analysis of the energy performance of a refrigeration system working with R1234yf using artificial neural networks
This paper presents the application of an artificial neural network to carry out a statistical analysis of the energy performance for a compression vapor system operating with R1234yf as working fluid. The main contribution of this work is the creation of 3D plots for visualization of energy perform...
Saved in:
Published in | Applied thermal engineering Vol. 82; pp. 8 - 17 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Elsevier Ltd
05.05.2015
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | This paper presents the application of an artificial neural network to carry out a statistical analysis of the energy performance for a compression vapor system operating with R1234yf as working fluid. The main contribution of this work is the creation of 3D plots for visualization of energy performance and its variability when changes in the input operating parameters are present. These parameters are: compressor rotation speed, the temperature and volumetric flow of the secondary fluids.
Furthermore, frequency histograms to represent the variability of the energy performance of the refrigeration system were estimated and analyzed. Computer simulations employing neural networks were used to understand the energy performance behavior, and observe the best performance of the installation. In the same way, these simulations were used to statistically analyze the variability of the energy performance.
•An artificial neural network was designed to model a vapor compression system.•A statistical analysis computing the histograms of input and output parameters in this system was perform.•3D color plots were used to display the mean and variance of the COP.•Histograms were computed to analyze the variability of the COP under different operating conditions. |
---|---|
Bibliography: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ISSN: | 1359-4311 |
DOI: | 10.1016/j.applthermaleng.2015.02.061 |