Machine learning to estimate the bond strength of the corroded steel bar‐concrete
Structural Concrete · 2024-02 · 25 (1) · 696-715
DOI: 10.1002/suco.202300401 ↗Kurz gefasst
Fachartikel in der Zeitschrift Structural Concrete, online erschienen am 28.12.2023. Verfasst von Kai‐Lai Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Steel bar corrosion is prone to serious degeneration of the bond strength ( τ BS ) of reinforced concrete, which leads to structural failure. There are many factors affecting the τ BS ; thus, the assessment of the τ BS of corroded steel bar‐concrete becomes very complicated. In this research, a τ BS evolution database of 430 samples containing 14 important factors, such as concrete compressive strength, yield strength and corrosion rate of steel bar, was established. Six machine learning algorithms were employed for comparative study to achieve optimal prediction results. The results showed that random forest and extreme random trees models have the best performance with coefficient of determination ( R 2 ) of 0.83 and 0.82, mean square error (MSE) of 13.59 and 13.98, root mean square error of 3.68 and 3.74, mean absolute error values of 2.35 and 2.31, and a20 values of 0.62 and 0.70, respectively. In addition, both models demonstrated shorter training times compared to the others. The running times are 589.75 and 418.31 ms, respectively. The superior feasibility and reliability of the machine learning algorithm were validated by contrasting with the computation of the empirical formulas. The empirical formulas exhibited higher error values, with the majority of MSE indicators exceeding 50 and the lowest R 2 value even presenting negative values. Furthermore, feature importance calculations were used to understand the ability of the machine learning models to perceive each influencing factor. Among them, the corrosion rate, the yield strength of the longitudinal bar, and the stirrup emerged as the three most important influential factors.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wang, K., Li, J., Li, L., Deng, E., Zhang, Y., & Li, Z. (2024). Machine learning to estimate the bond strength of the corroded steel bar‐concrete. Structural Concrete, 25(1), 696-715. https://doi.org/10.1002/suco.202300401
Vancouver
Wang K, Li J, Li L, Deng E, Zhang Y, Li Z. Machine learning to estimate the bond strength of the corroded steel bar‐concrete. Structural Concrete. 2024;25(1):696-715. doi:10.1002/suco.202300401
BibTeX
@article{Wang2024,
author = {Wang, Kai‐Lai and Li, Jingyi and Li, Li and Deng, E. and Zhang, Yang and Li, Zongli},
title = {Machine learning to estimate the bond strength of the corroded steel bar‐concrete},
journal = {Structural Concrete},
year = {2024},
volume = {25},
number = {1},
pages = {696--715},
doi = {10.1002/suco.202300401}
}
EUVIMED