EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Explainable Ensemble Learning for Web‐Crippling Resistance of Sigma Cold‐Formed Steel Sections under Interior–Two–Flange Loading

Lenganji Simwanda, Thushanthan Kannan, Kajaharan Thirunavukkarasu, Mohamed Sifan, Keerthan Poologanathan, Kajeenthan Kamalaseelan, Jeyasutha Lingaretnam, Sunday Popo‐Ola

ce/papers · 2026-09 · 9 (2-3) · 566-571

DOI: 10.1002/cepa.70752 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ce/papers, online erschienen am 14.09.2026. Verfasst von Lenganji Simwanda und 7 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cold‐formed steel (CFS) sigma sections are common in floors and purlins but are prone to web crippling under interior‐two‐flange (ITF) bearing. Equations in AISI S100, EN 1993‐1‐3 and related standards were mainly calibrated for channel sections and give poor, highly scattered predictions for sigma profiles. This study develops explainable machine‐learning (ML) surrogates for ITF web‐crippling capacity. A validated finite‐element (FE) database of 648 cases was created, spanning practical ranges of thickness, bearing length, yield strength and geometry. Code equations and recent proposals showed large bias (often negative R 2 ), whereas boosted trees (CatBoost, XGBoost, LightGBM, GBRT) and kernel methods (SVR, GPR) achieved near‐perfect accuracy (R 2 ≥ 0.99; RMSE ≈ 0.20–0.25 kN). SHAP analysis identifies thickness and yield strength as the dominant drivers, followed by section depth and bearing length, consistent with mechanics. Reliability calibration using the AISI S100 framework provides design‐ready factors for top models (φ ≈ 0.90, Ω ≈ 1.78). Interpretable ML surrogates thus enable accurate, reliability‐aligned design of sigma sections under ITF loading.

Zitieren

APA

Simwanda, L., Kannan, T., Thirunavukkarasu, K., Sifan, M., Poologanathan, K., Kamalaseelan, K., Lingaretnam, J., & Popo‐Ola, S. (2026). Explainable Ensemble Learning for Web‐Crippling Resistance of Sigma Cold‐Formed Steel Sections under Interior–Two–Flange Loading. ce/papers, 9(2-3), 566-571. https://doi.org/10.1002/cepa.70752

Vancouver

Simwanda L, Kannan T, Thirunavukkarasu K, Sifan M, Poologanathan K, Kamalaseelan K, et al. Explainable Ensemble Learning for Web‐Crippling Resistance of Sigma Cold‐Formed Steel Sections under Interior–Two–Flange Loading. ce/papers. 2026;9(2-3):566-571. doi:10.1002/cepa.70752

BibTeX
@article{Simwanda2026,
  author = {Simwanda, Lenganji and Kannan, Thushanthan and Thirunavukkarasu, Kajaharan and Sifan, Mohamed and Poologanathan, Keerthan and Kamalaseelan, Kajeenthan and Lingaretnam, Jeyasutha and Popo‐Ola, Sunday},
  title = {Explainable Ensemble Learning for Web‐Crippling Resistance of Sigma Cold‐Formed Steel Sections under Interior–Two–Flange Loading},
  journal = {ce/papers},
  year = {2026},
  volume = {9},
  number = {2-3},
  pages = {566--571},
  doi = {10.1002/cepa.70752}
}
Kostenlos starten →