The rapid advancement of three-dimensional printed concrete(3DPC)requires intelligent and interpretable frameworks to optimize mixture design for strength,printability,and sustainability.While machine learning(ML)mode...The rapid advancement of three-dimensional printed concrete(3DPC)requires intelligent and interpretable frameworks to optimize mixture design for strength,printability,and sustainability.While machine learning(ML)models have improved predictive accuracy,their limited transparency has hindered their widespread adoption in materials engineering.To overcome this barrier,this study introduces a Random Forests ensemble learning model integrated with SHapley Additive exPlanations(SHAP)and Partial Dependence Plots(PDPs)to model and explain the compressive strength behavior of 3DPC mixtures.Unlike conventional“black-box”models,SHAP quantifies each variable’s contribution to predictions based on cooperative game theory,which enables causal interpretability,whereas PDP visualizes nonlinear and interactive effects between features that offer practical mix design insights.A systematically optimized random forest model achieved strong generalization(R2=0.978 for training,0.834 for validation,and 0.868 for testing).The analysis identified curing age,Portland cement,silica fume,and the water-tobinder ratio as dominant predictors,with curing age exerting the highest positive influence on strength development.The integrated SHAP-PDP framework revealed synergistic interactions among binder constituents and curing parameters,which established transparent,data-driven guidelines for performance optimization.Theoretically,the study advances explainable artificial intelligence in cementitious material science by linking microstructural mechanisms to model-based reasoning,thereby enhancing both the interpretability and applicability of ML-driven mix design for next-generation 3DPC systems.展开更多
This research explored the application potential of PUM thin-overlay technology on airport rapid maintenance.The rapid curing process of polyurethane binder determines the limited time window for mixing and constructi...This research explored the application potential of PUM thin-overlay technology on airport rapid maintenance.The rapid curing process of polyurethane binder determines the limited time window for mixing and construction of polyurethane-bonded mixture(PUM),which presents significant difference with hot-mix asphalt(HMA)technology.Therefore,this research investigated and optimized the mix design of PUM for airport thin-overlay technology based on its thermosetting characteristics.First,limestone and basalt were comprehensively compared as an aggregate for PUM.Then,the effects of molding and curing conditions were studied in terms of mixing time,molding method,molding parameters and curing temperature.Statistical analysis was also conducted to evaluate the effects of gradation and particle size on PUM performances based on gray relational analysis(GRA),thus determining the key particle size to control PUM performances.Finally,the internal structural details of PUM were captured by X-ray CT scan test.The results demonstrated that it only took 12 hours to reach 75%of maximum strength at a curing temperature of 50°C,indicating an efficient curing process and in turn allowing short traffic delay.The internal structural details of PUM presented distribution of tiny pores with few connective voids,guaranteeing waterproof property and high strength.展开更多
基金supported by the Ongoing Research Funding Program(Grant No.ORFFT-2025-025-4)at King Saud University,Riyadh,Saudi Arabia.The grant was awarded to Yassir M.Abbas。
文摘The rapid advancement of three-dimensional printed concrete(3DPC)requires intelligent and interpretable frameworks to optimize mixture design for strength,printability,and sustainability.While machine learning(ML)models have improved predictive accuracy,their limited transparency has hindered their widespread adoption in materials engineering.To overcome this barrier,this study introduces a Random Forests ensemble learning model integrated with SHapley Additive exPlanations(SHAP)and Partial Dependence Plots(PDPs)to model and explain the compressive strength behavior of 3DPC mixtures.Unlike conventional“black-box”models,SHAP quantifies each variable’s contribution to predictions based on cooperative game theory,which enables causal interpretability,whereas PDP visualizes nonlinear and interactive effects between features that offer practical mix design insights.A systematically optimized random forest model achieved strong generalization(R2=0.978 for training,0.834 for validation,and 0.868 for testing).The analysis identified curing age,Portland cement,silica fume,and the water-tobinder ratio as dominant predictors,with curing age exerting the highest positive influence on strength development.The integrated SHAP-PDP framework revealed synergistic interactions among binder constituents and curing parameters,which established transparent,data-driven guidelines for performance optimization.Theoretically,the study advances explainable artificial intelligence in cementitious material science by linking microstructural mechanisms to model-based reasoning,thereby enhancing both the interpretability and applicability of ML-driven mix design for next-generation 3DPC systems.
基金This study was supported by the National Natural Science Foundation of China under Grant number of 51861145402.
文摘This research explored the application potential of PUM thin-overlay technology on airport rapid maintenance.The rapid curing process of polyurethane binder determines the limited time window for mixing and construction of polyurethane-bonded mixture(PUM),which presents significant difference with hot-mix asphalt(HMA)technology.Therefore,this research investigated and optimized the mix design of PUM for airport thin-overlay technology based on its thermosetting characteristics.First,limestone and basalt were comprehensively compared as an aggregate for PUM.Then,the effects of molding and curing conditions were studied in terms of mixing time,molding method,molding parameters and curing temperature.Statistical analysis was also conducted to evaluate the effects of gradation and particle size on PUM performances based on gray relational analysis(GRA),thus determining the key particle size to control PUM performances.Finally,the internal structural details of PUM were captured by X-ray CT scan test.The results demonstrated that it only took 12 hours to reach 75%of maximum strength at a curing temperature of 50°C,indicating an efficient curing process and in turn allowing short traffic delay.The internal structural details of PUM presented distribution of tiny pores with few connective voids,guaranteeing waterproof property and high strength.
