EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable Machine Learning for Flexural Strength Prediction of 3D-Printed Concrete Incorporating Supplementary Cementitious Materials

Fengping Qin, Yangping Chen, Mengdi Hou, Jianbo Huang

Buildings · 08.08.2026 · 16 (16) · 3151

DOI: 10.3390/buildings16163151 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 08.08.2026. Verfasst von Fengping Qin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Flexural strength (FS) governs the structural performance of 3D-printed concrete (3DPC) under bending loads yet remains difficult to predict owing to the coupled influence of binder composition, supplementary cementitious materials, water-to-binder ratio, and fiber reinforcement geometry on interlayer fracture behavior. Much of this compositional diversity stems from supplementary cementitious materials, industrial by-products whose reuse as partial cement replacement lowers the embodied carbon of printable mixes. A machine learning framework was trained on 209 FS records covering OPC- and SAC-based systems (FS: 3.65–45.0 MPa; W/B: 0.15–0.65). Six composite features were constructed from physical principles, two of them specific to bending: Fiber_Pullout_Index encoding post-crack pullout energy and Binder_Efficiency capturing cement quality per unit water content at the fiber–matrix interface; Lasso regularization with the one-standard-error rule reduced the 19-variable space to 14 active predictors. Twenty regression algorithms spanning eight families were benchmarked under 30 independent partitions; the Friedman test rejected equal performance (χ2=337.02, p=4.88×10−60) and all 19 pairwise Wilcoxon comparisons against CatBoost were Holm-significant. CatBoost ranked first (mean rank of 18.17/20; 30-run R2=0.9302±0.0722; seed-42 partition: R2=0.9557; RMSE = 1.761 MPa; MAPE = 11.20%). n(W/B) emerged as the primary driver across SHAP, ALE and LIME, with a monotonic ALE profile spanning 8.99 MPa and no inflection over the full printable window; Binder_Efficiency ranked second (PDP range: 5.21 MPa), isolating cement grade and paste dilution as independent strength levers. Cross-conformal prediction provided finite-sample coverage guarantees without distributional assumptions (empirical coverage: 95.24%; conformity quantile: 3.83 MPa); bootstrap analysis put the epistemic component at a mean predictive SD of 0.946 MPa, a quarter of that quantile. External validation yielded R2=0.769 (Pearson R=0.923, RMSE = 1.91 MPa), with 19 of 20 predictions (95.0%) within Bland–Altman 95% limits of agreement, confirming transfer to a source study withheld from model training. A graphical user interface packaging the 14-feature CatBoost pipeline supports mix design queries without programming.

Zitieren

APA

Qin, F., Chen, Y., Hou, M., & Huang, J. (2026). Interpretable Machine Learning for Flexural Strength Prediction of 3D-Printed Concrete Incorporating Supplementary Cementitious Materials. Buildings, 16(16), 3151. https://doi.org/10.3390/buildings16163151

Vancouver

Qin F, Chen Y, Hou M, Huang J. Interpretable Machine Learning for Flexural Strength Prediction of 3D-Printed Concrete Incorporating Supplementary Cementitious Materials. Buildings. 2026;16(16):3151. doi:10.3390/buildings16163151

BibTeX
@article{Qin2026,
  author = {Qin, Fengping and Chen, Yangping and Hou, Mengdi and Huang, Jianbo},
  title = {Interpretable Machine Learning for Flexural Strength Prediction of 3D-Printed Concrete Incorporating Supplementary Cementitious Materials},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {16},
  pages = {3151},
  doi = {10.3390/buildings16163151}
}
Kostenlos starten →