Image-Based Probabilistic Seismic Damage Assessment of Reinforced Concrete Beam-Column Joints
DOI:
https://doi.org/10.66238/jaeee20Keywords:
Structural Health Monitoring, Computer Vision, Probabilistic Assessment, Reinforced Concrete, Seismic DamageAbstract
The rapid and accurate assessment of seismic damage in reinforced concrete structures is paramount for ensuring public safety and facilitating post-earthquake recovery. Beam-column joints, representing the most critical regions for the lateral load-carrying capacity of structural frames, are particularly vulnerable to complex failure modes such as shear degradation and bond-slip. Traditional inspection methods rely heavily on the subjective judgment of engineers and suffer from significant logistical delays. Recent advancements in computer vision and machine learning offer a promising alternative by enabling automated damage detection from digital images. However, deterministic image-based models often fail to account for the inherent uncertainties present in visual data, such as variable lighting, sensor noise, and the imperfect correlation between surface distress and internal structural integrity. This paper proposes a comprehensive framework for the image-based probabilistic seismic damage assessment of reinforced concrete beam-column joints. By integrating deep learning-based semantic segmentation with Bayesian inference techniques, the proposed methodology quantifies both epistemic and aleatoric uncertainties to deliver reliable damage state classifications. The analytical pipeline extracts critical geometric features, including crack width distributions and spalling areas, and maps these visual indicators to probabilistic fragility functions. Extensive evaluation using a diverse dataset of joint failure images demonstrates that the probabilistic approach significantly outperforms traditional deterministic methods in robustness and reliability. The findings provide a vital step toward the integration of automated, uncertainty-aware health monitoring systems in post-disaster structural evaluation.
References
1. Gu, D., Sun, Y., Hu, J., Lu, R., & Pan, J. (2026). Rheology-and fracture-guided design of lightweight spray-applied engineered cementitious composites achieving structural-grade strength and high tensile ductility. Journal of Building Engineering, 116100.
2. Gu, D., Pan, J., & Luković, M. (2025). Understanding shear-resisting mechanism in reinforced engineered cementitious composite (ECC) beams using distributed strain measurements. Engineering Structures, 327, 119612.
3. Wei, G., Zhang, W., Bi, M., Sun, P., Li, S., Ouyang, X., ... & Tian, X. (2024). Trade-offs and synergies pattern evolution of ecosystem structure-resilience-activity-services (SRAS) in the Belt and Road Initiative region. Resources, Conservation and Recycling, 211, 107883.
4. Anticipation, E. V. A. Self-Regulated Learning for Egocentric Video Activity Anticipation.
5. Li, C., Xu, J., & Xing, J. (2023). A frequency feature extraction method based on convolutional neural network for recognition of incipient fault. IEEE Sensors Journal, 24(1), 564-572.
6. Huang, H., Zhang, J., Yu, L., Zhang, J., Wu, Q., & Xu, C. (2021). TOAN: Target-oriented alignment network for fine-grained image categorization with few labeled samples. IEEE Transactions on Circuits and Systems for Video Technology, 32(2), 853-866.
7. Chen, Q. S., Yu, B., & Li, B. (2021). Probabilistic calibration of strength and strain enhancement models for FRP-confined concrete in circular section. Construction and Building Materials, 304, 124673.
8. Yao, Y., Zhang, W., & Li, M. (2026). Cloud-Edge Federated Incremental Learning Framework for PMSM Efficiency Optimization with Lightweight CNN-LSTM Models and OTA Differential Deployment. Journal of Computer Science and Frontier Technologies, 3(1), 98-111.
9. Yao, Z., Hawi, P., Aitharaju, V., Mahishi, J., & Ghanem, R. (2024, October). Transfer Learning for Multiscale Analysis: Delamination of Carbon-Reinforced Composite Material Exploration. In American Society for Composites (ASC) Annual Technical Conference (pp. 95-112). Cham: Springer Nature Switzerland.
10. Zhang, W., Luo, M., & Chen, Z. (2024, October). Hybrid Forecasting: ML Predictions of Lake-Effect Regional Extreme Precipitations. In 2024 7th International Conference on Universal Village (UV) (pp. 1-11). IEEE.
11. Xing, J., & Xu, J. (2022). An improved convolutional neural network for recognition of incipient faults. IEEE Sensors Journal, 22(16), 16314-16322.
12. Yan, J., Ma, H., Wang, X., Li, H., Li, B., Wei, Q., & Cao, Z. (2025). Direct Measurement of Transverse Compressive Properties of Polyacrylonitrile-Based Single Carbon Fibers. Materials, 18(13), 3018.
13. Yan, Yueru, et al. "Crop yield time-series data prediction based on multiple hybrid machine learning models." arXiv preprint arXiv:2502.10405 (2025).
14. Wang, J. (2023, July). A multi-task learning and transfer learning-based model for crop leaf disease identification. In 2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS) (pp. 348-355). IEEE.
15. Chen, Q., Yu, B., & Li, B. (2025). Quantifying seismic damage in RC walls with image analysis. Journal of Earthquake Engineering, 29(1), 156-179.
16. Gu, D., Zhu, Y., Luković, M., & Pan, J. (2026). Arch action and beam action in reinforced engineered cementitious composite (ECC) beams subjected to shear. Engineering Structures, 357, 122468.
17. Xing, J., & Xu, J. (2022). An improved incipient fault diagnosis method of bearing damage based on hierarchical multi-scale reverse dispersion entropy. Entropy, 24(6), 770.
18. Tahmasebinia, F., Wang, Y., Wu, S., Ho, J., Shen, W., Ma, H., ... & Marroquin, F. A. (2021). Advanced structural analysis of innovative steel–glass structures with respect to the architectural design. Buildings, 11(5), 208.
19. Wei, G., Yang, Y., Li, R., Liu, Y., & He, B. J. (2024). Digital economy exhibits varying degrees of mitigation of air pollution in China: Total cities-economic subdivisions-urban agglomerations. Iscience, 27(6).
20. Lin, J., Jiang, B., Gu, D., Hu, J., He, Q., Xu, L., & Pan, J. (2025). Shear transfer mechanism of headed stud connectors in engineered cementitious composites (ECC): Experimental observation, numerical investigation and analytical model. Journal of Building Engineering, 99, 111565.
21. Hawi, P., Yao, Z., Aitharaju, V., Mahishi, J., & Ghanem, R. (2024, October). Reliability-Based Design and Certification of Hybrid Composites. In American Society for Composites (ASC) Annual Technical Conference (pp. 117-131). Cham: Springer Nature Switzerland.
22. Hawi, P. H. I. L. I. P. P. E., Yao, Z., Aitharaju, V., Mahishi, J., & Ghanem, R. (2023). A framework for design allowables accounting for paucity of data and errors in complex models. In Proceedings of the American society for composites-thirty-eighth technical conference.
23. Wang, Y., Chen, B., Dai, P., Wang, Y., Song, Y., Jiang, K., & Hai, L. (2025). Experimental and numerical study on lateral-torsional buckling of welded QN1803 high-strength stainless steel I-girders. Thin-Walled Structures, 212, 113190.
24. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems.
25. Li, J., Zhao, H., Wang, Y., & Lin, J. (2024, October). Towards photorealistic video colorization via gated color-guided image diffusion models. In Proceedings of the 32nd ACM International Conference on Multimedia (pp. 10891-10900).
26. Huang, J., & Sandeep, H. (2025, October). RESEARCH ON REINFORCEMENT LEARNING FOR TRUSTWORTHY CLIMATE POLICY SIMULATION AND APPLICATION. In The 7th International scientific and practical conference “Development of modern scientific technologies in the era of globalization”(October 14-17, 2025) Berlin, Germany. International Science Group. 2025. 237 p. (p. 32).
27. Wang, S., Sun, P., Sun, F., Jiang, S., Zhang, Z., & Wei, G. (2021). The direct and spillover effect of multi-dimensional urbanization on PM2. 5 concentrations: A case study from the Chengdu-Chongqing urban agglomeration in China. International Journal of Environmental Research and Public Health, 18(20), 10609.
28. Mo, J., Uy, B., Li, D., Thai, H. T., & Wang, Y. (2023). Behaviour and design of composite walls under lateral loading and combined loading. Journal of Constructional Steel Research, 210, 108087.
29. Fan, J., Liang, W., & Zhang, W. Q. (2025). SARNet: A Spike-Aware consecutive validation Framework for Accurate Remaining Useful Life Prediction. arXiv preprint arXiv:2510.22955.
30. Ren, Y., Zeng, C., Fan, D., Liu, L., & Feng, Q. (2018). Multi-state reliability assessment method based on the MDD-GO model. IEEE Access, 6, 5151-5161.
31. Zhou, X., Wang, P., Al-Dhaifallah, M., Rawa, M., & Khadimallah, M. A. (2022). A machine learning-based model for the estimation of the critical thermo-electrical responses of the sandwich structure with magneto-electro-elastic face sheet. Advances in nano research, 12(1), 81-99.
32. Muller, R., Song, R., Wang, C., Zhan, Y., Monteuuis, J. P., Man, Y., ... & Celik, Z. B. (2025, May). Investigating physical latency attacks against camera-based perception. In 2025 IEEE Symposium on Security and Privacy (SP) (pp. 4588-4605). IEEE.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Brooke Dori, Billie Delbert, Bob Desmond
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the Journal of Advanced Electrical and Electronic Engineering (JAEEE) are distributed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). Authors retain copyright of their work while granting the journal the right of first publication.
Under this license, users are permitted to read, download, copy, distribute, print, share, adapt, and reuse published material for both commercial and non-commercial purposes, provided appropriate credit is given to the original author(s), the source of publication is acknowledged, a link to the license is provided, and any changes made are clearly indicated.
The license does not permit users to imply endorsement by the original authors or the journal. No additional restrictions may be imposed that prevent others from exercising the rights granted under CC BY 4.0.
By submitting to the journal, authors confirm that their work is original, does not infringe upon third-party rights, and complies with ethical publishing standards.
