![](https://iifiir-uploads.s3.fr-par.scw.cloud/periodic/492/image/small-f8051aef4e1d31c9f3e5d83ac19adca2.png)
Summary
Condensation on surfaces in the presence of non-condensable gas (NCG) is a ubiquitous and critical phenomenon in many industrial fields. However, current empirical correlations for predicting condensation heat transfer coefficients in the presence of NCG may exhibit significant deviations from reality. Machine learning algorithms are now being dedicated to this field, but the models developed can only predict the condensation heat transfer coefficients of steam or vapor of a non-aqueous working fluid with similar physical properties to water in the presence of NCG. In the present study, a comprehensive theoretical analysis was conducted to investigate the total condensation heat transfer coefficients with NCG, and 16 dimensionless numbers were identified as input variables for machine learning models. Based on a filtered database consisting of 4377 data points extracted from 37 papers, the Spearman correlation coefficients were calculated to evaluate the relationship between the total heat transfer coefficients and the input variables, indicating the magnitude of the impact of the 16 dimensionless variables. Four machine learning models, namely Gradient Boosting Regression (GBR), Extreme Gradient Boosting (XGBoost), Random Forest Regression (RFR), and Multilayer Perceptron (MLP), were developed to predict the total heat transfer coefficients for water and non-aqueous working fluids. The mean absolute percentage errors for the four models were 1.38%, 1.63%, 3.00%, and 4.42%, respectively, with the GBR model exhibiting the highest degree of accuracy. The determination of the application scope of these models was conducted by analyzing the value ranges for each dimensionless parameter and its corresponding frequency distribution.
Available documents
Format PDF
Pages: 215-233
Available
Public price
20 €
Member price*
Free
* Best rate depending on membership category (see the detailed benefits of individual and corporate memberships).
Details
- Original title: Machine-learning algorithms for predicting condensation heat transfer coefficients in the presence of non-condensable gases.
- Record ID : 30032343
- Languages: English
- Subject: Technology
- Source: International Journal of Refrigeration - Revue Internationale du Froid - vol. 162
- Publication date: 2024/06
- DOI: http://dx.doi.org/10.1016/j.ijrefrig.2024.04.007
Links
See other articles in this issue (20)
See the source
-
Forecasting of saturated boiling heat transfer ...
- Author(s) : MORADKHANI M. A., HOSSEINI S. H., KARAMI M.
- Date : 2022/11
- Languages : English
- Source: International Journal of Refrigeration - Revue Internationale du Froid - vol. 143
- Formats : PDF
View record
-
Evaluating the generality of machine learning-b...
- Author(s) : SHOUREHDELI S. A., GHOLIPOUR H.
- Date : 2024/03
- Languages : English
- Source: International Journal of Refrigeration - Revue Internationale du Froid - vol. 159
- Formats : PDF
View record
-
HORIZONTAL TUBE EVAPORATORS. 1. THEORETICALLY-B...
- Author(s) : KOCAMUSTAFAOGULLARI G., CHEN I. Y.
- Date : 1989
- Languages : English
- Source: Int. Commun. Heat Mass Transf. - vol. 16 - n. 4
View record
-
Computer vision and machine learning methods fo...
- Author(s) : YANG B., ZHU X., WEI B., LIU M., LI Y., LV Z., WANG F.
- Date : 2023/02
- Languages : English
- Source: Energies - vol. 16 - 3
- Formats : PDF
View record
-
Estimation of Ranque-Hilsch vortex tube perform...
- Author(s) : DOGAN A., KORKMAZ M., KIRMACI V.
- Date : 2023/06
- Languages : English
- Source: International Journal of Refrigeration - Revue Internationale du Froid - vol. 150
- Formats : PDF
View record