节能2025，Vol.44Issue(12)：27-31,5.DOI:10.3969/j.issn.1004-7948.2025.12.007
基于机器学习算法的纳米流体强化型深井地源热泵的性能预测
Performance prediction of nanofluid-enhanced deep well ground source heat pump based on machine learning algorithms
摘要
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.关键词
机器学习/纳米流体/深井地源热泵/性能预测Key words
machine learning/nanofluid/deep well ground source heat pump/performance prediction分类
信息技术与安全科学引用本文复制引用
任彦洁,任国杰,王日藩,辛齐,马玖辰..基于机器学习算法的纳米流体强化型深井地源热泵的性能预测[J].节能,2025,44(12):27-31,5.基金项目
天津市自然科学基金企业科技特派员项目(项目编号:19JCTPJC48100) （项目编号:19JCTPJC48100）
中铁建设集团有限公司科研计划课题项目(项目编号:LX24-33C) （项目编号:LX24-33C）
中铁建设集团有限公司科研计划课题华北-天津项目(项目编号:7287QT2024003) （项目编号:7287QT2024003）
