EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Innovative Machine Learning Techniques for Sustainable Compressive Strength Estimation of Ultrahigh‐Performance Concrete

Guangcheng Diao, Alireza Baghban

Advances in Civil Engineering · 2026-01 · 2026 (1)

DOI: 10.1155/adce/2499864 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advances in Civil Engineering, online erschienen am 29.06.2026. Verfasst von Guangcheng Diao und 1 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this work, the compressive strength of high‐performance concrete (HPC) mixtures was estimated by four various machine learning methods based on Gaussian process regression (GPR). For this purpose, kernel functions including exponential, Matern, rational quadratic, and squared exponential were employed in modeling. Also, a dataset with a number of 1030 points was collected so that its features were fine aggregate, blast furnace slag, coarse aggregate, water, superplasticizer, cement, age, and fly ash. According to mathematical and visual investigations, the GPR method including Matern kernel function is the best calculator for the determination of compressive strength. The R‐squared values in training, validation, and testing steps were determined to be 0.9863, 0.9214, and 0.9655, respectively, and these values confirmed the mentioned claim. In addition, the outlier detection process was conducted on the databank, and the reliability of available data points was confirmed. Also, the sensitivity analysis explained the effect of different inputs on the compressive strength was assessed, and it was obtained that age is the most effective parameter on the target.

Zitieren

APA

Diao, G., & Baghban, A. (2026). Innovative Machine Learning Techniques for Sustainable Compressive Strength Estimation of Ultrahigh‐Performance Concrete. Advances in Civil Engineering, 2026(1). https://doi.org/10.1155/adce/2499864

Vancouver

Diao G, Baghban A. Innovative Machine Learning Techniques for Sustainable Compressive Strength Estimation of Ultrahigh‐Performance Concrete. Advances in Civil Engineering. 2026;2026(1). doi:10.1155/adce/2499864

BibTeX
@article{Diao2026,
  author = {Diao, Guangcheng and Baghban, Alireza},
  title = {Innovative Machine Learning Techniques for Sustainable Compressive Strength Estimation of Ultrahigh‐Performance Concrete},
  journal = {Advances in Civil Engineering},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/adce/2499864}
}
Kostenlos starten →