12. Automated detection of concrete spalling in post-earthquake structures using deep learning
DOI:
https://doi.org/10.61591/jslhu.22.662Từ khóa:
Deep Learning; Structural Damage Classification; Spalling Detection; Post-Earthquake Assessment.Tóm tắt
Post-earthquake structural assessment is critical in determining the extent of damage and guiding emergency response efforts. Spalling, characterized by the detachment of concrete layers, serves as a key indicator of seismic damage and can significantly impact structural integrity. This study develops an automated classification model utilizing deep learning to distinguish between spalling and non-spalling cases in concrete structures. The proposed method employs transfer learning with ResNet50 and EfficientNet-B3 to optimize accuracy and inference efficiency. The dataset, collected from real-world post-earthquake reconnaissance, consists of high-resolution images categorized into spalling and non-spalling classes. Key preprocessing techniques, including pixel normalization, data augmentation, and class balancing, were applied to improve model robustness and mitigate class imbalance issues. Performance evaluation showed that ResNet50 outperforms EfficientNet-B3 in overall accuracy (77% vs. 71%), while EfficientNet-B3 achieved higher recall (90% vs. 85%), making it more sensitive to detecting spalling cases. The study highlights the challenges posed by dataset variability and proposes future enhancements such as advanced augmentation, multi-modal data integration, and self-supervised learning. The findings contribute to the advancement of AI-driven structural health monitoring, offering an efficient tool for rapid post-disaster damage assessment.
Tài liệu tham khảo
Kit H. Miyamoto, Giulia Jole Sechi, Guilaine Victor, Beverly St Come, Mark Broughton, 2023, "Haiti Earthquake 2021: Findings from the Repair and Damage Assessment of 179,800 Buildings," International Journal of Disaster Risk Reduction.
M.A. Haroun and H.M. Elsanadedy, 2005, "Seismic Design Guidelines for Squat Composite-Jacketed Circular and Rectangular Reinforced Concrete Columns," Journal of Structural Engineering, American Concrete Institute, Vol. 102, No. 4, pp. 505–514.
F. Kolawole, E.A. Atekwana, D.A. Laó-Dávila, M.G. Abdelsalam, P.R. Chindandali, 2018, "High-resolution electrical resistivity and aeromagnetic imaging reveal the causative fault of the 2009 Mw 6.0 Karonga, Malawi earthquake," Geophysical Journal International.
Erkal, B. G., & Hajjar, J. F. (2017). Laser-based surface damage detection and quantification using predicted surface properties. Automation in Construction, 83, 285-302.
Yin, J. F., Bai, Q., & Zhang, B. (2018). Methods for detection of subsurface damage: a review. Chinese Journal of Mechanical Engineering, 31, 1-14.
Wang, J., & Qiao, P. (2007). Improved damage detection for beam-type structur
Bai, Z., Liu, T., Zou, D., Zhang, M., Hu, Q., & Li, Y. (2024). Multi-scale image-based damage recognition and assessment for reinforced concrete structures in post-earthquake emergency response. Engineering Structures, 314, 118402.
Hui, B., Zhang, Y., Ma, Z., Wang, H., & Yang, X. (2023). Identification and evaluation of spalling aggregate in chip seals in three dimensions. Construction and Building Materials, 364, 129899
Yasmin, T., La, D., La, K., Nguyen, M. T., & La, H. M. (2024). Concrete spalling detection system based on semantic segmentation using deep architectures. Computers & Structures, 300, 107398
Hariri-Ardebili, M. A., & Speicher, M. S. (2025). Reconnaissance-informed post-earthquake functional recovery: Observations and challenges. Earthquake Spectra, 41(1), 88-125.
Sheibani, M., & Ou, G. (2022). Guided post-earthquake reconnaissance surveys considering resource constraints for regional damage inference. Earthquake Spectra, 38(4), 2813-2834.
Al Shafian, S., & Hu, D. (2024). Integrating machine learning and remote sensing in disaster management: A decadal review of post-disaster building damage assessment. Buildings, 14(8), 2344.
