.png){kind=icon}
.png){kind=icon}
Return
Experimental analysis and explainable machine learning modeling of heat and mass transfer in an ionic-liquid-based adiabatic dehumidification system
.png){kind=icon}
OA
AI
J
Y
Y
DOI：10.1016/j.tsep.2026.104810.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Novel ionic liquid system achieves an optimal EF of 3.42 kg/kWh. • Reducing airflow rate improves system energy factor by 70.1%. • CatBoost model predicts Nu and Sh with high accuracy (R2 > 0.97) • Boosting algorithms outperform traditional LSM in nonlinear modeling. • SHAP analysis identifies Reynolds number as the key transfer driver.
Keywords:
Ionic-liquid dehumidification
Heat and mass transfer
Machine learning (ML) regression
SHAP analysis
Energy efficiency
Counterflow
Journal
IF:
5.4
Papers:
4.4K
Citations:
1.1W
Organization
Cited Papers