EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Experimental–Finite Element Method Confounding in Machine Learning Predictions of Shear Capacity for Reinforced Deep Beams with Web Openings

Hoang Quan Nguyen, Xuan Huy Nguyen, Khuong Le-Nguyen, Dang Dung Le, Quang Si Nguyen

Buildings · 20.11.2026 · 16 (22) · 4630

DOI: 10.3390/buildings16224630 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 20.11.2026. Verfasst von Hoang Quan Nguyen und 4 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Transport and Communications.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning (ML) models trained on pooled experimental and finite element method (FEM) data may achieve high accuracy without reliable generalization to independent experimental studies. This study evaluates the ultimate shear capacity of 498 reinforced concrete deep beams with web openings (201 experimental and 297 FEM specimens) using Monte Carlo validation, SHAP analysis, leave-one-original-study-out (LOSO) validation, and conformal prediction. The baseline models use nine parameters: a/H, ax/a, ay/H, Xo/a, Yo/H, ρsw, ρs, fc′, and fy. The FEM specimens contain square web openings, whereas the experimental dataset includes different opening geometries. Despite high pooled accuracy (R2 ≈ 0.99), substantial differences in geometric scale and response distributions limit its interpretation. In the pooled Random Forest model, the mean absolute SHAP attribution of ρsw was 1234 kN, with opposite mean signed contributions for experimental (−1443 kN) and FEM (+1074 kN) specimens. Sensitivity analyses showed that these attributions depend on model specification and data composition rather than representing direct physical effects. LOSO validation revealed poor cross-study generalization, with median R2 values of −11.503 for Random Forest and −18.233 for tuned XGBoost under pooled training; negative values persisted under experimental-only training. These findings highlight the need for source-specific evaluation, scale-aware modeling, and independent experimental validation before engineering application.

Förderung

  • University of Transport and Communications

Zitieren

APA

Nguyen, H. Q., Nguyen, X. H., Le-Nguyen, K., Le, D. D., & Nguyen, Q. S. (2026). Experimental–Finite Element Method Confounding in Machine Learning Predictions of Shear Capacity for Reinforced Deep Beams with Web Openings. Buildings, 16(22), 4630. https://doi.org/10.3390/buildings16224630

Vancouver

Nguyen HQ, Nguyen XH, Le-Nguyen K, Le DD, Nguyen QS. Experimental–Finite Element Method Confounding in Machine Learning Predictions of Shear Capacity for Reinforced Deep Beams with Web Openings. Buildings. 2026;16(22):4630. doi:10.3390/buildings16224630

BibTeX
@article{Nguyen2026,
  author = {Nguyen, Hoang Quan and Nguyen, Xuan Huy and Le-Nguyen, Khuong and Le, Dang Dung and Nguyen, Quang Si},
  title = {Experimental–Finite Element Method Confounding in Machine Learning Predictions of Shear Capacity for Reinforced Deep Beams with Web Openings},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {22},
  pages = {4630},
  doi = {10.3390/buildings16224630}
}
Kostenlos starten →