Explainable Data-Driven Modeling for Optimized Mix Design of 3D-Printed Concrete: Interpreting Nonlinear Synergies among Binder Components and Proportions
Open Access
- 1 January 2025
- journal article
- Published by Tech Science Press in Computer Modeling in Engineering & Sciences
- Vol. 145 (2) , 1789-1819
Abstract
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-to-binder 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.Keywords
This publication has 122 references indexed in Scilit:
- A novel compressive strength estimation approach for 3D printed fiber-reinforced concrete: integrating machine learning and gene expression programmingMultiscale and Multidisciplinary Modeling, Experiments and Design, 2024
- Trees2023
- Regularized impurity reduction: accurate decision trees with complexity guaranteesData Mining and Knowledge Discovery, 2022
- Recent advances in decision trees: an updated surveyArtificial Intelligence Review, 2022
- Inter-layer reinforcement of 3D printed concrete elementsAsian Journal of Civil Engineering, 2020
- Mechanical behavior of lightweight concrete structures subjected to 3D coupled static–dynamic loadsActa Mechanica, 2020
- Effects of deposition velocity in the presence/absence of E6-glass fibre on extrusion-based 3D printed mortarAdditive Manufacturing, 2020
- Studying the Printability of Fresh Concrete for Formwork-Free Concrete Onsite 3D Printing Technology (CONPrint3D)2019
- How Many Trees in a Random Forest?2012
- Ensemble Methods in Machine Learning2000