Comparative machine learning models for predicting the compressive strength of ultra-high-performance concrete
PLOS One · 2026
DOI: 10.1371/journal.pone.0357153 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift PLOS One, 2026. Verfasst von Nguyen Thi Thu Nga und 3 weiteren Autor:innen. Beteiligte Einrichtung: Advanced Materials and Smart Structure for Sustainable System (AMS4), University of Transport Technology, Hanoi, Vietnam. Hauptthemen laut MEDLINE: Compressive Strength, Machine Learning, Construction Materials. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Ultra-high-performance concrete (UHPC) exhibits exceptional mechanical properties and durability. However, its compressive strength is highly dependent on complex mix design parameters. While traditional experimental techniques and regression-based models are commonly used to evaluate UHPC compressive strength, machine learning approaches offer an efficient alternative for capturing complex nonlinear relationships. This study develops a machine learning–based framework to predict the compressive strength of UHPC and compares the predictive performance of five advanced algorithms: Extremely Randomized Trees (ER), Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), CatBoost, and Artificial Neural Network (ANN). A comprehensive experimental database was utilized for training and validation purposes. Among the evaluated models, CatBoost achieved the best predictive performance, with a coefficient of determination (R²) exceeding 0.90, a root mean square error (RMSE) of approximately 4.5 MPa, and a mean absolute error (MAE) of approximately 3.6 MPa. However, subgroup residual analysis showed that the prediction reliability was not uniform across the full strength range. In particular, mixtures with compressive strength ≥180 MPa exhibited larger errors and systematic underprediction, mainly due to the limited number of ultra-high-strength samples in the compiled database. Therefore, the model is more reliable within well-represented strength ranges, while predictions in the ultra-high-strength region should be interpreted with caution. SHAP-based analysis, feature dependency analysis, and both Individual Conditional Expectation (ICE) and Partial Dependence Plots (PDP) were employed. These explainable AI techniques identified key variables and quantified their contributions to the compressive strength of UHPC. The findings demonstrate that interpretable machine learning can support preliminary UHPC mixture assessment by combining predictive performance with physically meaningful insights.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Advanced Materials and Smart Structure for Sustainable System (AMS4), University of Transport Technology, Hanoi, Vietnam.
- Faculty of Civil Engineering, University of Transport Technology, Hanoi, Vietnam.
- School of Information & Communications Technology, Hanoi University of Industry, Hanoi, Vietnam.
- UCT Company, University of Transport and Communication, Hanoi, Vietnam.
ORCID-Profile: Huyen Thi Dang
Zitieren
APA
Nga, N. T. T., Tuan, N. A., Tu, N. T., & Dang, H. T. (2026). Comparative machine learning models for predicting the compressive strength of ultra-high-performance concrete. PLOS One. https://doi.org/10.1371/journal.pone.0357153
Vancouver
Nga NTT, Tuan NA, Tu NT, Dang HT. Comparative machine learning models for predicting the compressive strength of ultra-high-performance concrete. PLOS One. 2026. doi:10.1371/journal.pone.0357153
BibTeX
@article{Nga2026,
author = {Nga, Nguyen Thi Thu and Tuan, Nguyen Anh and Tu, Nguyen Tuan and Dang, Huyen Thi},
title = {Comparative machine learning models for predicting the compressive strength of ultra-high-performance concrete},
journal = {PLOS One},
year = {2026},
doi = {10.1371/journal.pone.0357153}
}
EUVIMED