Performance prediction of nanofluid-enhanced deep well ground source heat pump based on machine learning algorithms
REN Yanjie
REN Guojie
WANG Rifan
XIN Qi
MA Jiuchen
Abstract：To explore the applicability of different machine learning algorithms in the performance prediction of deep well ground source heat pumps with enhanced heat transfer using nano-fluids as circulating fluids,the operation data of the heat pump system using 2%Al2O3 nano-fluids are monitored and collected in real time,and then a database is constructed.And calculation and analysis are carried out respectively by using algorithms such as support vector machine(SVM),particle swarm optimization-support vector machine(PSO-SVM),and extreme gradient boost(XGBoost).The results show that the XGBoost algorithm has excellent predictive performance.Its prediction of system coefficient of performance(COP)and heat supply(Q)has a fitting degree of 100%within an error range of±5%.This result fully demonstrates that the algorithm has high fitting accuracy and no obvious overfitting phenomenon occurs.
Keywords：machine learningnanofluiddeep well ground source heat pumpperformance prediction
Publication Date：2025-12-25
Online Publishing Date：2026-01-26(First online date of this platform, not the publication date of the document)
Pages：5( 27-31 )