Prediction of Ultra-High-Performance Concrete (UHPC) Compressive Strength Based on Convolutional Neural Networks
Materials · 17.06.2025 · 18 (12) · 2851
DOI: 10.3390/ma18122851 ↗Kurz gefasst
Fachartikel in der Zeitschrift Materials, online erschienen am 17.06.2025. Verfasst von Li Xu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Jiangsu Vocational College of Business, Nantong 226000, China. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Nantong City Social Livelihood Science and Technology Projec, Nantong City Social Livelihood Science and Technology Project.
Abstract (Originalsprache)
This paper investigates the potential of deep learning in predicting the compressive strength of ultra-high-performance concrete (UHPC) by developing a convolutional neural network (CNN) model with two convolutional layers. The proposed CNN architecture demonstrates capability in accurately predicting UHPC compressive strength from tabular data encompassing various material compositions. Ten input variables were selected, including the cement content, water content, silica fume content, silica powder content, silica sand content, superplasticizer content, and curing parameters. The model was trained and tested on a dataset comprising 219 samples. Experimental results indicated excellent predictive performance, with the CNN achieving a coefficient of determination (R2) of 0.959 on the test set and a mean absolute percentage error (MAPE) of 5.55%, demonstrating both accuracy and stability. Comparative analysis revealed that the CNN’s performance was comparable to established machine learning methods like XGBoost (R2 = 0.961), which are typically more suited for tabular data. Furthermore, SHAP (SHapley Additive exPlanations) analysis confirmed the model’s interpretability. These findings collectively suggest that the CNN-based approach shows considerable promise for predicting compressive strength across diverse UHPC formulations.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Jiangsu Vocational College of Business, Nantong 226000, China.
- School of Transportation and Civil Engineering, Nantong University, Nantong 226000, China.
- Nantong Vocational University, Nantong 226000, China.
ORCID-Profile: Jie Yang
Förderung
- National Natural Science Foundation of China
- Nantong City Social Livelihood Science and Technology Projec
- Nantong City Social Livelihood Science and Technology Project
Zitieren
APA
Xu, L., Yu, X., Zhu, C., Wang, L., & Yang, J. (2025). Prediction of Ultra-High-Performance Concrete (UHPC) Compressive Strength Based on Convolutional Neural Networks. Materials, 18(12), 2851. https://doi.org/10.3390/ma18122851
Vancouver
Xu L, Yu X, Zhu C, Wang L, Yang J. Prediction of Ultra-High-Performance Concrete (UHPC) Compressive Strength Based on Convolutional Neural Networks. Materials. 2025;18(12):2851. doi:10.3390/ma18122851
BibTeX
@article{Xu2025,
author = {Xu, Li and Yu, Xiaochun and Zhu, Chenhui and Wang, Ling and Yang, Jie},
title = {Prediction of Ultra-High-Performance Concrete (UHPC) Compressive Strength Based on Convolutional Neural Networks},
journal = {Materials},
year = {2025},
volume = {18},
number = {12},
pages = {2851},
doi = {10.3390/ma18122851}
}
EUVIMED