EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Driven Strength Prediction and Sustainability Analysis of Ultra-High-Performance Concrete

Hongliang Rong, Wangwen Sun iD, Haoran Ma, Muhan Luo iD, Zhenghua You, Guobin Zhang, Pengcheng Zhu, Zhuangzhuang Liu, Lauren Y Gómez-Zamorano iD

Materials · 11.11.2025 · 18 (22) · 5116

DOI: 10.3390/ma18225116 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 11.11.2025. Verfasst von Hongliang Rong und 8 weiteren Autor:innen. Beteiligte Einrichtung: Xinjiang Jiaotou Construction Management Co., Ltd., Urumchi 830000, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Science and Technology Research and Development Project of Xinjiang Transportation In-vestment (Group) Co., Ltd. (Project No. XJJTZKX-FWCG-202411-0736) on…, the project "Application Technology Guidelines for Deicing and Anti-Icing Liquids (Agents) for Airport Runways and Taxiways" (Project No. JC2025005)..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ultra-high-performance concrete (UHPC) is recognized for its exceptional strength and durability. However, the adoption of UHPC frequently leads to higher material and environmental costs. Accurate prediction of compressive strength is crucial for optimizing material design and reducing construction costs. In this study, a dataset of 800 samples was compiled from published articles. Four models, including random forest (RF), Gaussian Process Regression (GPR), Gradient Boosting (GB) and Artificial Neural Network (ANN), were applied. Results show that ANN and GPR achieved the best accuracy and stability. GB also performed well with good adaptability. RF captured general trends but produced larger errors in the high-strength range. Feature importance analysis highlighted curing age and cement content as the most influential factors, with a combined contribution above 65%. The water-to-binder ratio also affected strength through matrix densification. Extended evaluation with regression error characteristic (REC) curves and environmental impact index (EII) revealed the balance between performance and environmental impact. Higher compressive strength often required higher energy, CO2, and resource use. The range of 150–250 MPa showed a better balance between performance and sustainability. This study confirms the robustness of machine learning models for strength prediction and provides guidance for green and low-carbon ultra-high-performance concrete design.

Schlagwörter

Stichwörter der Autor:innen

compressive strength predictionenvironmental impactmachine learning modelssustainability assessmentultra-high-performance concrete

Autor:innen und Institutionen

  • Xinjiang Jiaotou Construction Management Co., Ltd., Urumchi 830000, China.
  • School of Highway, Chang'an University, Xi'an 710064, China.
  • Key Laboratory of Special Area Highway Engineering, Ministry of Education, Xi'an 710064, China.
  • International Joint Laboratory for Sustainable Development of Highway Infrastructures in Special Regions, Xi'an 710064, China.
  • Programa Doctoral en Ingeniería de Materiales, Facultad de Ingeniería Mecánica y Eléctrica, Universidad Autónoma de Nuevo León, Ave. Universidad s/n, Ciudad Universitaria, San Nicolás de los Garza 66455, Nuevo León, Mex…

ORCID-Profile: Wangwen Sun, Muhan Luo, Lauren Y Gómez-Zamorano

Förderung

  • the Science and Technology Research and Development Project of Xinjiang Transportation In-vestment (Group) Co., Ltd. (Project No. XJJTZKX-FWCG-202411-0736) on…
  • the project "Application Technology Guidelines for Deicing and Anti-Icing Liquids (Agents) for Airport Runways and Taxiways" (Project No. JC2025005).

Zitieren

APA

Rong, H., Sun, W., Ma, H., Luo, M., You, Z., Zhang, G., Zhu, P., Liu, Z., & Gómez-Zamorano, L. Y. (2025). Machine Learning-Driven Strength Prediction and Sustainability Analysis of Ultra-High-Performance Concrete. Materials, 18(22), 5116. https://doi.org/10.3390/ma18225116

Vancouver

Rong H, Sun W, Ma H, Luo M, You Z, Zhang G, et al. Machine Learning-Driven Strength Prediction and Sustainability Analysis of Ultra-High-Performance Concrete. Materials. 2025;18(22):5116. doi:10.3390/ma18225116

BibTeX
@article{Rong2025,
  author = {Rong, Hongliang and Sun, Wangwen and Ma, Haoran and Luo, Muhan and You, Zhenghua and Zhang, Guobin and Zhu, Pengcheng and Liu, Zhuangzhuang and Gómez-Zamorano, Lauren Y},
  title = {Machine Learning-Driven Strength Prediction and Sustainability Analysis of Ultra-High-Performance Concrete},
  journal = {Materials},
  year = {2025},
  volume = {18},
  number = {22},
  pages = {5116},
  doi = {10.3390/ma18225116}
}
Kostenlos starten →