<p>A mathematical model of the vapor compression refrigeration cycle for different operating conditions (different evaporator and condenser temperatures, different superheat and supercooling temperatures) is established in the present study. Instead of R134a, mixtures of R134a and R1234yf with lower global warming potential values are evaluated as the working fluid in the vapor compression refrigeration cycle. The energy and exergy performances of these refrigerant mixtures were estimated by machine learning algorithms. Seven different machine learning algorithms have been used. These are support vector regression, random forest, extreme gradient boosting regressor (XGBR), CatBoost, light gradient boosting machine, adaptive boosting, and decision tree. The XGBR algorithm provided higher accuracy in the energy efficiency results of both refrigerants, with the best performance of the CatBoost algorithm in terms of exergy efficiency. For the blend of R134a/R1234yf (10/90), taking the evaporator temperatures as − 25&#xa0;°C, − 20&#xa0;°C, − 15&#xa0;°C, − 10&#xa0;°C, − 5&#xa0;°C, and 0&#xa0;°C, the condenser temperature as 35&#xa0;°C and both superheating and subcooling temperatures as 7&#xa0;°C, COP values vary between 2.6723 and 5.7909 and <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="10973_2025_14547_Article_IEq1.gif" Format="GIF" Height="13" Rendition="HTML" Resolution="72" Type="Linedraw" Width="20" /> </InlineMediaObject> <EquationSource Format="TEX">\({\upeta }_{\text{II}}\)</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi mathvariant="normal">η</mi> <mtext>II</mtext> </msub> </math></EquationSource> </InlineEquation> vary between 0.6461 and 0.7420. At the same operating conditions, the COP values for the R134a/R1234yf (15/85) blend vary between 2.6731 and 5.7861, and the second law efficiencies <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="10973_2025_14547_Article_IEq1.gif" Format="GIF" Height="13" Rendition="HTML" Resolution="72" Type="Linedraw" Width="20" /> </InlineMediaObject> <EquationSource Format="TEX">\({\upeta }_{\text{II}}\)</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi mathvariant="normal">η</mi> <mtext>II</mtext> </msub> </math></EquationSource> </InlineEquation> vary between 0.6463 and 0.7414. The R<sup>2</sup> values obtained as the result of the comparison of the actual and predicted values in the energy and exergy analyses for the R134a/R1234yf (10/90) mixture have been found as 0.9887 (energy efficiency) and 0.9810 (exergy efficiency), respectively. For the R134a/R1234yf (15/85) blend, R<sup>2</sup> values were 0.9881 (energy efficiency) and 0.9819 (exergy efficiency), respectively. This shows that machine learning algorithms can predict both energy and exergy analyses of R134a/R1234yf blend with high accuracy.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Machine learning models for high-accuracy energy and exergy prediction of low-GWP R134a/R1234yf blends

  • Ragıp Yıldırım

摘要

A mathematical model of the vapor compression refrigeration cycle for different operating conditions (different evaporator and condenser temperatures, different superheat and supercooling temperatures) is established in the present study. Instead of R134a, mixtures of R134a and R1234yf with lower global warming potential values are evaluated as the working fluid in the vapor compression refrigeration cycle. The energy and exergy performances of these refrigerant mixtures were estimated by machine learning algorithms. Seven different machine learning algorithms have been used. These are support vector regression, random forest, extreme gradient boosting regressor (XGBR), CatBoost, light gradient boosting machine, adaptive boosting, and decision tree. The XGBR algorithm provided higher accuracy in the energy efficiency results of both refrigerants, with the best performance of the CatBoost algorithm in terms of exergy efficiency. For the blend of R134a/R1234yf (10/90), taking the evaporator temperatures as − 25 °C, − 20 °C, − 15 °C, − 10 °C, − 5 °C, and 0 °C, the condenser temperature as 35 °C and both superheating and subcooling temperatures as 7 °C, COP values vary between 2.6723 and 5.7909 and \({\upeta }_{\text{II}}\) η II vary between 0.6461 and 0.7420. At the same operating conditions, the COP values for the R134a/R1234yf (15/85) blend vary between 2.6731 and 5.7861, and the second law efficiencies \({\upeta }_{\text{II}}\) η II vary between 0.6463 and 0.7414. The R2 values obtained as the result of the comparison of the actual and predicted values in the energy and exergy analyses for the R134a/R1234yf (10/90) mixture have been found as 0.9887 (energy efficiency) and 0.9810 (exergy efficiency), respectively. For the R134a/R1234yf (15/85) blend, R2 values were 0.9881 (energy efficiency) and 0.9819 (exergy efficiency), respectively. This shows that machine learning algorithms can predict both energy and exergy analyses of R134a/R1234yf blend with high accuracy.