EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Ensemble Machine Learning Models for Bond Strength Prediction at Ultra-High-Performance-to-Normal-Strength-Concrete Interfaces

Sanjog Chhetri Sapkota, Sabin Adhikari, Nisha Panta, Bivek Lekhak, Sandip Pandey, Krishal Karmacharya, Satish Paudel

Buildings · 03.08.2026 · 16 (15) · 3081

DOI: 10.3390/buildings16153081 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 03.08.2026. Verfasst von Sanjog Chhetri Sapkota und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The slant shear bond strength of the UHPC-NSC interface is a key parameter governing load transfer and structural reliability in composite concrete members. However, accurate prediction remains challenging because of strong nonlinear relationships among influencing parameters and the limited availability of experimental data. This study presents an optimized machine learning framework for reliable bond strength prediction by integrating Extra Trees Regressor (ETR) and CatBoost (CATB) with Grasshopper Optimization (GO) and Northern Goshawk Optimization (NG) for hyperparameter optimization. Model performance was evaluated using cross-validation and independent testing to ensure reliable generalization. Among the developed models, the optimized CATB-NG achieved the highest predictive accuracy with an R2 of 0.934, RMSE of 3.081 MPa, and MAE of 2.186 MPa. SHapley Additive exPlanations (SHAP) identified NSC surface treatment and compressive strength as the dominant factors influencing bond strength, while Individual Conditional Expectation (ICE) analysis revealed nonlinear feature interactions and threshold behaviors. To facilitate practical engineering applications, the optimized model was implemented in a graphical user interface (GUI) for real-time prediction with standardized feature encoding. The proposed framework provides an accurate, interpretable, and user-friendly tool for predicting UHPC-NSC interfacial bond strength and supports engineering design and decision making.

Zitieren

APA

Sapkota, S. C., Adhikari, S., Panta, N., Lekhak, B., Pandey, S., Karmacharya, K., & Paudel, S. (2026). Explainable Ensemble Machine Learning Models for Bond Strength Prediction at Ultra-High-Performance-to-Normal-Strength-Concrete Interfaces. Buildings, 16(15), 3081. https://doi.org/10.3390/buildings16153081

Vancouver

Sapkota SC, Adhikari S, Panta N, Lekhak B, Pandey S, Karmacharya K, et al. Explainable Ensemble Machine Learning Models for Bond Strength Prediction at Ultra-High-Performance-to-Normal-Strength-Concrete Interfaces. Buildings. 2026;16(15):3081. doi:10.3390/buildings16153081

BibTeX
@article{Sapkota2026,
  author = {Sapkota, Sanjog Chhetri and Adhikari, Sabin and Panta, Nisha and Lekhak, Bivek and Pandey, Sandip and Karmacharya, Krishal and Paudel, Satish},
  title = {Explainable Ensemble Machine Learning Models for Bond Strength Prediction at Ultra-High-Performance-to-Normal-Strength-Concrete Interfaces},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {3081},
  doi = {10.3390/buildings16153081}
}
Kostenlos starten →