Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Using ANNs to approach to the energy performance for a small refrigeration system working with R134a and two alternative lower GWP mixtures
KTH, School of Industrial Engineering and Management (ITM), Energy Technology, Applied Thermodynamics and Refrigeration.
2017 (English)In: Applied Thermal Engineering, ISSN 1359-4311, E-ISSN 1873-5606, Vol. 127, 996-1004 p.Article in journal (Refereed) Published
Abstract [en]

In this paper, an artificial neural network application to model a small refrigeration system is presented. The main objective of this study is an energy comparison of three refrigerants: R134a, R450A and R513A. The application of the artificial neural network was designed to model individually three typical energy parameters: the cooling capacity, the power consumption and the coefficient of performance, as a function of the evaporating temperature and the condensing temperature. Each model was validated using a technique called cross-validation, producing minimum relative errors of 0.15 for the cooling capacity and the coefficient of performance, while 0.05 for the power consumption. Based on the appropriate validation results, computer simulations were performed to build 3D color surfaces. After inspecting these 3D color surfaces, it was concluded that R450A presented a slightly lower cooling capacity than R134a, actually a 10% reduction in the cooling capacity was estimated. Similar results were observed for the power consumption, that is, R450A had about 10% less power consumption than the other two refrigerants. On the other hand, it was observed that R134a and R513A presented very similar energy behaviors. With respect the COP, it was concluded that all three refrigerants showed a very similar behavior. After the analysis performed with the artificial neural networks and the use of 3D surface color, it was concluded that R450A and R513A are appropriate refrigerants to replace R134a in the short term in applications at medium evaporating temperature.

Place, publisher, year, edition, pages
Elsevier Ltd , 2017. Vol. 127, 996-1004 p.
Keyword [en]
Artificial neural network, Cross-validation, Energy performance, R450A, R513A, Vapor compression system
National Category
Energy Engineering
Identifiers
URN: urn:nbn:se:kth:diva-218604DOI: 10.1016/j.applthermaleng.2017.08.108Scopus ID: 2-s2.0-85028443623OAI: oai:DiVA.org:kth-218604DiVA: diva2:1161474
Note

QC 20171130

Available from: 2017-11-30 Created: 2017-11-30 Last updated: 2017-11-30Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Authority records BETA

Makhnatch, Pavel

Search in DiVA

By author/editor
Makhnatch, Pavel
By organisation
Applied Thermodynamics and Refrigeration
In the same journal
Applied Thermal Engineering
Energy Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 7 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf