基于GPR模型的多孔沥青混合料空隙率预估  

作　　者：马志鹏 章启月 张泽霖 肖一帆 邓学耀 刘祥[1] 

机构地区：[1]昆明理工大学,昆明650504

出　　处：《科技创新与应用》2024年第30期52-54,59,共4页Technology Innovation and Application

基　　金：云南省大学生创新创业训练计划项目(S202210674133);云南省教育厅科学研究基金项目(2023J0132)。

摘　　要：多孔沥青混合料空隙率是影响其排水功能和路用性能的关键指标之一。为实现多孔沥青混合料空隙率的快速判别,该研究以混合料级配不同筛孔尺寸通过率、油石比为自变量,通过相关性分析提取特征参数,进而基于高斯过程回归(GPR)模型建立PAC-13多孔沥青混合料空隙率预估模型,并对比分析GPR模型与多元线性回归、AdaBoost和随机森林法对多孔沥青混合料空隙率的预估准确性。结果表明,以4.75、2.36、1.18、0.6、0.3、0.15和0.075 mm的筛孔通过率,以及油石比作为模型参数的多孔沥青混合料空隙率GPR预估模型具有较好的准确性,线性拟合系数达到0.95;相比多元线性回归、AdaBoost和随机森林法,GPR模型对于多孔沥青混合料空隙率预估的适用性相对更优。The void content of porous asphalt mixture is one of the key indicators that affect its drainage function and road performance.In order to quickly determine the void content of porous asphalt mixtures,this study took the passage rate of different sieve size and oil-stone ratio of the mixture gradation as independent variables,extracted characteristic parameters through correlation analysis,and then established the PAC-13 porous asphalt mixture void content prediction model based on the Gaussian Process Regression(GPR)model,and compared and analyzed the accuracy of the GPR model with multiple linear regression,AdaBoost and random forest methods in predicting the void content of porous asphalt mixtures.The results show that the GPR model for predicting the porosity of porous asphalt mixtures using the sieve passage rates of 4.75 mm,2.36 mm,1.18 mm,0.6 mm,0.3 mm,0.15 mm and 0.075 mm and oil-to-stone ratio as model parameters has good accuracy,with a linear fitting coefficient of 0.95;compared with multiple linear regression,AdaBoost and random forest methods,the GPR model is relatively more applicable to predicting the porosity of porous asphalt mixtures.

关 键 词：道路工程 多孔沥青混合料 空隙率 高斯过程回归 预估模型 

分 类 号：U416.2[交通运输工程—道路与铁道工程]