Saturated flow boiling frictional pressure drop inside smooth macro and mini/micro channels: a new predictive tool using CatBoost and XGBoost

Reliable prediction of the saturated boiling frictional pressure drop is fundamental to optimum evaporator design. Hence, frictional pressure drop is a critical parameter for improving the efficiency of the evaporator. The main constraints of the empirical or semi-empirical predictive tools, updated...

Full description

Saved in:
Bibliographic Details
Main Authors: Francisco A. Ramírez-Rivera, Alison E. Sánchez-García, Vrindarani Núñez-Ramírez, Néstor F. Guerrero-Rodríguez
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Case Studies in Thermal Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2214157X25009153
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321126329581568
author Francisco A. Ramírez-Rivera
Alison E. Sánchez-García
Vrindarani Núñez-Ramírez
Néstor F. Guerrero-Rodríguez
author_facet Francisco A. Ramírez-Rivera
Alison E. Sánchez-García
Vrindarani Núñez-Ramírez
Néstor F. Guerrero-Rodríguez
author_sort Francisco A. Ramírez-Rivera
collection DOAJ
description Reliable prediction of the saturated boiling frictional pressure drop is fundamental to optimum evaporator design. Hence, frictional pressure drop is a critical parameter for improving the efficiency of the evaporator. The main constraints of the empirical or semi-empirical predictive tools, updated using non-linear statistical regression techniques, lie in their reduced predictive effectiveness when applied to unseen data. New intelligent tools can contribute to help overcome these constraints by improving accuracy and the generalization capability of the tool. In this study, a new predictive tool for estimating the frictional pressure drop combining XGBoost and CatBoost is built using a database of 6199 high quality points collected from 56 experimental studies reported in the literature. The database involves a wide range of operating conditions, hydraulic diameter from 0.15 to 14 mm, saturation temperature from −40 to 145 °C, heat flux from 3 to 1100 kW/m2, mass velocity from 30 to 1200 kg/m2s, thermophysical properties with 24 fluids, capturing reduced pressure from 0.00060 to 0.70 and incorporating different geometries. A total of 22 input parameters were selected for the training process by performing a comparative analysis between several feature selection techniques. The result indicate that the new predictive tool captures 89.52 % of the points within ±30 % error bands with technical statistical metrics MAE = 1.901, MSE = 11.956, RMSE = 3.458, MAPE = 14.204, R2 = 0.992. The proposed predictive tool demonstrates a powerful high performance and accurately captures the physical trend of frictional pressure drop versus vapor quality.
format Article
id doaj-art-ef44af09da244eac8cfe6113c8261797
institution Kabale University
issn 2214-157X
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Case Studies in Thermal Engineering
spelling doaj-art-ef44af09da244eac8cfe6113c82617972025-08-20T03:49:50ZengElsevierCase Studies in Thermal Engineering2214-157X2025-09-017310665510.1016/j.csite.2025.106655Saturated flow boiling frictional pressure drop inside smooth macro and mini/micro channels: a new predictive tool using CatBoost and XGBoostFrancisco A. Ramírez-Rivera0Alison E. Sánchez-García1Vrindarani Núñez-Ramírez2Néstor F. Guerrero-Rodríguez3Corresponding author.; Engineering Sciences, Pontificia Universidad Católica Madre y Maestra (PUCMM), Av. Abraham Lincoln Esq. Romulo Betancourt, Santo Domingo, 2748, Dominican RepublicEngineering Sciences, Pontificia Universidad Católica Madre y Maestra (PUCMM), Av. Abraham Lincoln Esq. Romulo Betancourt, Santo Domingo, 2748, Dominican RepublicEngineering Sciences, Pontificia Universidad Católica Madre y Maestra (PUCMM), Av. Abraham Lincoln Esq. Romulo Betancourt, Santo Domingo, 2748, Dominican RepublicEngineering Sciences, Pontificia Universidad Católica Madre y Maestra (PUCMM), Av. Abraham Lincoln Esq. Romulo Betancourt, Santo Domingo, 2748, Dominican RepublicReliable prediction of the saturated boiling frictional pressure drop is fundamental to optimum evaporator design. Hence, frictional pressure drop is a critical parameter for improving the efficiency of the evaporator. The main constraints of the empirical or semi-empirical predictive tools, updated using non-linear statistical regression techniques, lie in their reduced predictive effectiveness when applied to unseen data. New intelligent tools can contribute to help overcome these constraints by improving accuracy and the generalization capability of the tool. In this study, a new predictive tool for estimating the frictional pressure drop combining XGBoost and CatBoost is built using a database of 6199 high quality points collected from 56 experimental studies reported in the literature. The database involves a wide range of operating conditions, hydraulic diameter from 0.15 to 14 mm, saturation temperature from −40 to 145 °C, heat flux from 3 to 1100 kW/m2, mass velocity from 30 to 1200 kg/m2s, thermophysical properties with 24 fluids, capturing reduced pressure from 0.00060 to 0.70 and incorporating different geometries. A total of 22 input parameters were selected for the training process by performing a comparative analysis between several feature selection techniques. The result indicate that the new predictive tool captures 89.52 % of the points within ±30 % error bands with technical statistical metrics MAE = 1.901, MSE = 11.956, RMSE = 3.458, MAPE = 14.204, R2 = 0.992. The proposed predictive tool demonstrates a powerful high performance and accurately captures the physical trend of frictional pressure drop versus vapor quality.http://www.sciencedirect.com/science/article/pii/S2214157X25009153EvaporatorsFrictional pressure dropSaturated boilingCatBoostXGBoostConventional tool
spellingShingle Francisco A. Ramírez-Rivera
Alison E. Sánchez-García
Vrindarani Núñez-Ramírez
Néstor F. Guerrero-Rodríguez
Saturated flow boiling frictional pressure drop inside smooth macro and mini/micro channels: a new predictive tool using CatBoost and XGBoost
Case Studies in Thermal Engineering
Evaporators
Frictional pressure drop
Saturated boiling
CatBoost
XGBoost
Conventional tool
title Saturated flow boiling frictional pressure drop inside smooth macro and mini/micro channels: a new predictive tool using CatBoost and XGBoost
title_full Saturated flow boiling frictional pressure drop inside smooth macro and mini/micro channels: a new predictive tool using CatBoost and XGBoost
title_fullStr Saturated flow boiling frictional pressure drop inside smooth macro and mini/micro channels: a new predictive tool using CatBoost and XGBoost
title_full_unstemmed Saturated flow boiling frictional pressure drop inside smooth macro and mini/micro channels: a new predictive tool using CatBoost and XGBoost
title_short Saturated flow boiling frictional pressure drop inside smooth macro and mini/micro channels: a new predictive tool using CatBoost and XGBoost
title_sort saturated flow boiling frictional pressure drop inside smooth macro and mini micro channels a new predictive tool using catboost and xgboost
topic Evaporators
Frictional pressure drop
Saturated boiling
CatBoost
XGBoost
Conventional tool
url http://www.sciencedirect.com/science/article/pii/S2214157X25009153
work_keys_str_mv AT franciscoaramirezrivera saturatedflowboilingfrictionalpressuredropinsidesmoothmacroandminimicrochannelsanewpredictivetoolusingcatboostandxgboost
AT alisonesanchezgarcia saturatedflowboilingfrictionalpressuredropinsidesmoothmacroandminimicrochannelsanewpredictivetoolusingcatboostandxgboost
AT vrindaraninunezramirez saturatedflowboilingfrictionalpressuredropinsidesmoothmacroandminimicrochannelsanewpredictivetoolusingcatboostandxgboost
AT nestorfguerrerorodriguez saturatedflowboilingfrictionalpressuredropinsidesmoothmacroandminimicrochannelsanewpredictivetoolusingcatboostandxgboost