辽宁工程技术大学学报（自然科学版）2026，Vol.45Issue(2)：185-195,11.DOI:10.11956/j.issn.1008-0562.20250527
基于可解释性机器学习算法的FRP筋UHPC粘结强度预测
Prediction of bond strength between FRP bars and UHPC using explainable machine learning algorithms
摘要
Abstract
In order to explain the bond mechanism of fiber reinforced polymer(FRP)bars and ultra-high performance concrete(UHPC),a sample dataset of 475 bond strength tests results was analyzed.Seven input variables and one output variable(bond strength)were selected to train six machine learning algorithms.Three interpretable techniques were combined for analysis,and compared with the specifications and empirical models.The results show that the extreme gradient boosting(XGBoost)model achieves the best accuracy,with R2 of 0.881,RMSE of 3.700 and MAE of 2.326.The ratio of bond length to reinforcement diameter l/d,steel fiber content ρSF,the ratio of protective layer thickness to reinforcement diameter c/d,FRP bar diameter d,UHPC strength fc are the key factors influencing the bond strength.The results of this study can provide a reference for the prediction of UHPC bond strength of FRP bars.关键词
纤维增强复合材料筋/超高性能混凝土/粘结强度/机器学习/SHAP分析Key words
fiber reinforced polymer(FRP)bars/ultra-high performance concrete(UHPC)/bond strength/machine learning/SHAP analysis分类
建筑与水利引用本文复制引用
李九阳,陈立,吴纪曙,王晓雨..基于可解释性机器学习算法的FRP筋UHPC粘结强度预测[J].辽宁工程技术大学学报（自然科学版）,2026,45(2):185-195,11.基金项目
国家自然科学基金项目(51778063) （51778063）
吉林省科技厅科技发展计划项目(YDZJ202302CXJD052) （YDZJ202302CXJD052）
吉林省自然科学基金项目(YDZJ202401370ZYTS) （YDZJ202401370ZYTS）
