Data-Driven Prediction of Crack Evolution in Regional Concrete Bridges: Comparison of Multiple Machine Learning Models
Infrastructures · 18.11.2026 · 11 (11) · 427
DOI: 10.3390/infrastructures11110427 ↗Kurz gefasst
Fachartikel in der Zeitschrift Infrastructures, online erschienen am 18.11.2026. Verfasst von Ning Liang und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hebei Expressway Group Research and Innovation Project, National Natural Science Foundation of China.
Abstract (Originalsprache)
The maximum crack width of the main girder of concrete girder bridges is one of the key indicators for evaluating bridge service performance and formulating maintenance decisions. At present, crack information in engineering practice is obtained mainly through manual inspection, which involves a certain lag and makes it difficult to meet the requirements of modern bridges for preventive and predictive maintenance. This study compared 12 regression models with GridSearch and with the Tree-structured Parzen Estimator (TPE) in Optuna, producing 24 model-optimization combinations. The dataset contains 669 bridge inspection records of 170 expressway bridges from 2019 to 2022, covering 12 structural, environmental, traffic, and maintenance features. Before preprocessing, the records were assigned to a training set and a test set containing 535 and 134 samples, respectively. Both optimization strategies used the same bridge-grouped five-fold cross-validation split and maximized the mean validation R2, with preprocessing fitted independently within each training fold. CatBoost–Optuna achieved the highest observed test R2 of 0.9208, with RMSE = 0.0484 and MAE = 0.0387 on the standardized MCW scale. Gradient boosting models performed best in this comparison. SHapley Additive exPlanations (SHAP) further identified bridge age, heavy-vehicle traffic, and cumulative vehicle load as the main contributors to the model predictions. The results provide a regional benchmark for MCW estimation. In future work, covariate scenarios can be supplied to the model to explore maintenance demand.
Förderung
- Hebei Expressway Group Research and Innovation Project
- National Natural Science Foundation of China
Zitieren
APA
Liang, N., Zhang, Z., Shen, D., Liang, D., Huang, H., & Shi, J. (2026). Data-Driven Prediction of Crack Evolution in Regional Concrete Bridges: Comparison of Multiple Machine Learning Models. Infrastructures, 11(11), 427. https://doi.org/10.3390/infrastructures11110427
Vancouver
Liang N, Zhang Z, Shen D, Liang D, Huang H, Shi J. Data-Driven Prediction of Crack Evolution in Regional Concrete Bridges: Comparison of Multiple Machine Learning Models. Infrastructures. 2026;11(11):427. doi:10.3390/infrastructures11110427
BibTeX
@article{Liang2026,
author = {Liang, Ning and Zhang, Zhi-Yi and Shen, Ding-Yu and Liang, Dong and Huang, Hai-Bin and Shi, Jing},
title = {Data-Driven Prediction of Crack Evolution in Regional Concrete Bridges: Comparison of Multiple Machine Learning Models},
journal = {Infrastructures},
year = {2026},
volume = {11},
number = {11},
pages = {427},
doi = {10.3390/infrastructures11110427}
}
EUVIMED