Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.14256/JCE.4344.2025

Flexural capacity prediction of partially encased composite beams using machine learning

Hongxin Liu
Ping Yang
Yaming Li
Shuizhong Jia
Xiaomeng Xie


Puni tekst: hrvatski pdf 2.999 Kb

str. 1-19

preuzimanja: 41

citiraj

Puni tekst: engleski pdf 2.971 Kb

str. 1-19

preuzimanja: 52

citiraj


Sažetak

To address traditional limitations, this study investigated the flexural performance of large-section PEC beams with varied web openings using experiments and machine learning (ML). Four-point bending tests on specimens with different sections and openings demonstrated excellent ductility (coefficient >4.0), although openings slightly reduced yield strength without significantly affecting overall performance. A database of 15 variables was used to train and validate four ML models (RF, CatBoost, KNN, LightGBM). The RF model achieved the highest accuracy (~2.6% MAE). Shapley analysis improved interpretability by identifying key parameters. Integrating explainable ML substantially enhances the prediction accuracy and interpretability of PEC flexural capacity, offering a promising approach for intelligent structural design and assessent.

Ključne riječi

PEC beams; failure mode; flexural capacity; ductility; machine learning

Hrčak ID:

345451

URI

https://hrcak.srce.hr/345451

Datum izdavanja:

2.3.2026.

Podaci na drugim jezicima: hrvatski

Posjeta: 260 *