EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction of Concrete Abrasion Depth in Hydraulic Structures Using an Interpretable Hybrid Ensemble Model Based on Meta-Heuristic Algorithms

Changhai He, Xiaodong Liu, Ao Xu, Qingfu Li, Xiang Wang, Xiyu Ma

Buildings · 13.11.2025 · 15 (22) · 4086

DOI: 10.3390/buildings15224086 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 13.11.2025. Verfasst von Changhai He und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The concrete protective layer in hydraulic tunnels is prone to abrasion by high-velocity sand-laden water, reducing structural durability. Accurate prediction of abrasion depth is key to rational hydraulic structure design. Existing studies have limitations: classical empirical models consider only a single factor, while early machine learning models fail to cover two core abrasion mechanisms (friction and impact) and lack meta-heuristic algorithm-based parameter optimization, leading to insufficient generalization and stability. This study aims to (1) establish a multi-source database with 690 cases (463 friction-dominated, 227 impact-dominated) covering multiple test standards (ASTM C944, ASTM C779, BIS: 1237-1980, ASTM C1138); (2) optimize hyperparameters of LightGBM, XGBoost, and CatBoost using Genghis Khan Shark Optimizer (GKSO) to build a hybrid ensemble model; (3) verify model performance and identify key factors via SHAP analysis. After preprocessing, input features were simplified to five: water–cement ratio, FA/CA (fine aggregate/coarse aggregate), age, T/V (test duration/velocity), and WRA content. Results show that GKSO-CatBoost performed best (test set R2 = 0.982, RMSE = 0.1231 mm). SHAP analysis identified T/V and the water–cement ratio as key influencing features, providing clear directions for optimizing concrete mix proportions under different standard scenarios. This study provides a new method for hydraulic concrete abrasion prediction and a scientific basis for durability design oriented to specific test standards.

Zitieren

APA

He, C., Liu, X., Xu, A., Li, Q., Wang, X., & Ma, X. (2025). Prediction of Concrete Abrasion Depth in Hydraulic Structures Using an Interpretable Hybrid Ensemble Model Based on Meta-Heuristic Algorithms. Buildings, 15(22), 4086. https://doi.org/10.3390/buildings15224086

Vancouver

He C, Liu X, Xu A, Li Q, Wang X, Ma X. Prediction of Concrete Abrasion Depth in Hydraulic Structures Using an Interpretable Hybrid Ensemble Model Based on Meta-Heuristic Algorithms. Buildings. 2025;15(22):4086. doi:10.3390/buildings15224086

BibTeX
@article{He2025,
  author = {He, Changhai and Liu, Xiaodong and Xu, Ao and Li, Qingfu and Wang, Xiang and Ma, Xiyu},
  title = {Prediction of Concrete Abrasion Depth in Hydraulic Structures Using an Interpretable Hybrid Ensemble Model Based on Meta-Heuristic Algorithms},
  journal = {Buildings},
  year = {2025},
  volume = {15},
  number = {22},
  pages = {4086},
  doi = {10.3390/buildings15224086}
}
Kostenlos starten →