TY  - EJOU
AU  - Chen, Jia 
AU  - Liao, Zhicheng 
AU  - Hou, Mengdi 
AU  - Huang, Jianbo 

TI  - Machine Learning for Compressive Strength Prediction of 3D-Printed Concrete: Feature Engineering, Statistically Validated Model Selection, and Applicability Boundaries
T2  - Computer Modeling in Engineering \& Sciences

PY  - 2026
VL  - 148
IS  - 2
SN  - 1526-1506

AB  - Extrusion-based 3D-printed concrete (3DPC) imposes a dual constraint on mix design: fresh-state printability and hardened compressive strength must both be maintained within a narrow water-to-binder window, making data-driven prediction tools essential for reducing experimental iteration. This study evaluates 20 regression algorithms on 254 experimental records spanning plain printable mortars to high-fibre reinforced composites (CS: 11.1–189.0 MPa). Four physically motivated composite variables encoding cement blend potency, cumulative supplementary cementitious material (SCM) substitution, fibre volumetric stiffness, and water-to-sand ratio are constructed; Boruta-based selection retains 11 of 17 candidate features. CatBoost achieves the highest 30-run mean performance (<math id="mml-ieqn-1"><msup><mi>R</mi><mn>2</mn></msup><mo>=</mo><mn>0.8968</mn><mo>±</mo><mn>0.0505</mn></math>; single-run metrics on the seed-42 partition: RMSE = 8.82 MPa, MAPE = 9.68%) under frequentist Bonferroni correction (<math id="mml-ieqn-2"><msup><mi>α</mi><mo>∗</mo></msup><mo>=</mo><mn>0.0026</mn></math>) and Bayesian Savage-Dickey comparison; XGBoost is the only alternative not statistically separated from CatBoost after correction (<math id="mml-ieqn-3"><mi>p</mi><mo>=</mo><mn>0.085</mn></math>; <math id="mml-ieqn-4"><msub><mrow><mi mathvariant="normal">B</mi><mi mathvariant="normal">F</mi></mrow><mrow><mn>10</mn></mrow></msub><mo>=</mo><mn>9.23</mn></math> indicates only moderate evidence for a small advantage). Multi-method interpretability analysis identifies the water-to-binder ratio as the dominant predictor with an ALE effect range of 57.57 MPa; local interpretable model-agnostic explanations reveal a sign reversal of this effect across the strength spectrum, capturing the printability–strength coupling specific to layer-by-layer deposition. For practical mix design, W/B <math id="mml-ieqn-5"><mo>≤</mo><mn>0.28</mn></math> consistently projects CS above 80 MPa within the compiled dataset; the 95% prediction interval half-width of 12 MPa is recommended as a design safety margin. Trained model is well-calibrated for OPC/SAC-based 3DPC within the compiled W/B window (0.15–0.65), achieving MAPE <math id="mml-ieqn-6"><mo>≤</mo><mn>9.68</mn></math>%. Cross-system transfer to 262 ECC/SHCC specimens yields a 12.0 MPa systematic overestimation attributable to material-system differences rather than model overfitting, delineating the applicability boundary for deployment. A graphical user interface implementing the optimized model is released to support mix design without programming expertise. Source codes are publicly available at <a href="https://github.com/lucassivan/ML-3DPC" target="_blank">https://github.com/lucassivan/ML-3DPC</a>.
KW  - 3D-printed concrete; machine learning; compressive strength prediction; feature engineering; uncertainty quantification; external validation; interpretability

DO  - 10.32604/cmes.2026.085729