Call For Paper - Upcoming Conferences
Research Article | Open Access | Download PDF
Volume 13 | Issue 4 | Year 2026 | Article Id. IJCE-V13I4P123 | DOI : https://doi.org/10.14445/23488352/IJCE-V13I4P123

Deep Learning-Based Damage Detection and Prognosis in Civil Structures using Seismic Vibration Data

Sneha Hirekhan, Rajesh Bhagat, Abhay Hirekhan, Manisha Ingle, Humera Khanum

Received Revised Accepted Published
17 Jan 2026 19 Feb 2026 24 Mar 2026 28 Apr 2026

Citation :

Sneha Hirekhan, Rajesh Bhagat, Abhay Hirekhan, Manisha Ingle, Humera Khanum, "Deep Learning-Based Damage Detection and Prognosis in Civil Structures using Seismic Vibration Data," International Journal of Civil Engineering, vol. 13, no. 4, pp. 380-395, 2026. Crossref, https://doi.org/10.14445/23488352/IJCE-V13I4P123

Abstract

Detection and prognosis of damage in civil structures during an earthquake event are imperative for the safety of the public and judicious maintenance strategies. Almost all existing methods based on traditional signal processing techniques or standalone deep learning models suffer from many disadvantages, including lagging adaptability, high false positives, and limited interpretability. To counter this, we proposed a new deep learning framework with a hybrid CNN-RNN architecture, Random Forest feature selection, real-time adaptation via Deep Q-Network-based methods, transfer learning, and Explainable AI (XAI) methods. Our framework reduces dimensions using dimensionality reduction via Random Forest; it enhances the spatial features extracted by CNN and temporal sequence modeling by RNN to achieve 93% classification accuracy and 12% reduced false positives. Real-time optimization of model parameters by DQN for seismic events improves the detection accuracy up to 15% and decreases the timestamp of response to 20%. Domain adaptation with transfer learning is tuning the generalization of a pre-trained autoencoder, resulting in 30% training timestamp decrease and the availability of 10% sparse seismic data. SHAP-based explainable AI explanations for over 85% of decisions and uncertainty quantification by BNNs with 95% confidence interval led to a 25% improvement in prognosis reliability. This integrated approach enhances both the accuracy and real-time capability of seismic damage detection systems; an improvement in the model performance will be substantial with the help of adaptability and interpretability because it allows for real-world applications where data may be noisy, along with high structural variability in the process.

Keywords

Seismic Damage Detection, Hybrid CNN-RNN, Real-Time Adaptation, Explainable AI, Bayesian Neural Networks.

References

  1. Ali Zar et al., “Towards Vibration-based Damage Detection of Civil Engineering Structures: Overview, Challenges, and Future Prospects,” International Journal of Mechanics and Materials in Design, vol. 20, no. 3, pp. 591-662, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  2. Xi Song, Dan Li, and Chunhee Cho, “Image-based Machine Learning Approach for Structural Damage Detection Through Wavelet Transforms,” Urban Lifeline, vol. 2, no. 1, pp. 1-18, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  3. Getachew Ambaye, Enkhsaikhan Boldsaikhan, and Krishna Krishnan, “Robot Arm Damage Detection using Vibration Data and Deep Learning,” Neural Computing and Applications, vol. 36, no. 4, pp. 1727-1739, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  4. Lechen Li, and Raimondo Betti, “A Machine Learning-based Data Augmentation Strategy for Structural Damage Classification in Civil Infrastructure System,” Journal of Civil Structural Health Monitoring, vol. 13, no. 6-7, pp. 1265-1285, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  5. Viet-Hung Dang, and Huan X. Nguyen, “Multi-task Framework for Vibration-based Structural Damage Detection of Spatial Truss Structure using Graph Learning,” Journal of Vibration Engineering and Technologies, vol. 12, no. 7, pp. 7763-7779, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  6. Shree Harsha et al., “Machine Learning Models for Damage Detection in Steel Beams,” International Journal of System Assurance Engineering and Management, vol. 14, no. 5, pp. 1898-1911, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  7. Willy Aulia Akbar Kustiana et al., “Bridge Damage Detection with Support Vector Machine in Accelerometer-based Wireless Sensor Network,” Journal of Vibration Engineering and Technologies, vol. 12, no. S1, pp. 21-40, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  8. Berhanu Tefera, Adil Zekaria, and Abrham Gebre, “Challenges in Applying Vibration-based Damage Detection to Highway Bridge Structures,” Asian Journal of Civil Engineering, vol. 24, no. 6, pp. 1875-1894, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  9. Mohammadmahdi Abedi, Javad Shayanfar, and Khalifa Al-Jabri, “Infrastructure Damage Assessment Via Machine Learning Approaches: A Systematic Review,” Asian Journal of Civil Engineering, vol. 24, no. 8, pp. 3823-3852, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  10. Burcu Gunes, “Localizing Structural Damage based on Auto-Regressive with Exogenous Input Model Parameters and Residuals using a Support Vector Machine based Learning Approach,” Frontiers of Structural and Civil Engineering, vol. 18, no. 10, pp. 1492-1506, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  11. Soyeon Park, and Sunjoong Kim, “Enhancing Vibration-based Damage Assessment with 1D-CNN: Parametric Studies and Field Applications,” KSCE Journal of Civil Engineering, vol. 28, no. 7, pp. 2934-2951, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  12. Ronny Francis Ribeiro Junior, and Guilherme Ferreira Gomes, “On the use of Machine Learning for Damage Assessment in Composite Structures: A Review,” Applied Composite Materials, vol. 31, no. 1, pp. 1-37, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  13. Gaurav Kumar, Vivek Pratap Singh, and Saurabh Kumar Pandey, “Assessing Gas Leakage Detection Performance using Machine Learning with Different Modalities,” Transactions on Electrical and Electronic Materials, vol. 25, no. 5, pp. 653-664, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  14. Quyet Huu Nguyen et al., “A Prospective Technique for Damage Detection in Truss Structures using the Fusion of DNN with AVOA,” KSCE Journal of Civil Engineering, vol. 28, no. 7, pp. 2920-2933, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  15. Flavio Dipietrangelo, Francesco Nicassio, and Gennaro Scarselli, “SHM Implementation on a RPV Airplane Model based on Machine Learning for Impact Detection,” Aerotecnica Missili and Spazio, vol. 103, no. 4, pp. 363-375, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  16. Pei Yi Siow et al., “Noise Robustness of an Operational Modal-based Structural Damage-Detection Scheme using Impact-Synchronous Modal Analysis,” Journal of Zhejiang University-SCIENCE A, vol. 24, no. 9, pp. 782-800, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  17. Prashant Kumar, and Solomon Raju Kota, “Machine Learning Models in Structural Engineering Research and a Secured Framework for Structural Health Monitoring,” Multimedia Tools and Applications, vol. 83, no. 3, pp. 7721-7759, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  18. Anup Chitkeshwar, “Revolutionizing Structural Engineering: Applications of Machine Learning for Enhanced Performance and Safety,” Archives of Computational Methods in Engineering, vol. 31, no. 8, pp. 4617-4632, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  19. Zhang Lingxin, Shen Junkai, and Zhu Baijie, “A Review of the Research and Application of Deep Learning-based Computer Vision in Structural Damage Detection,” Earthquake Engineering and Engineering Vibration, vol. 21, no. 1, pp. 1-21, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  20. Hassan Sarmadi et al., “Partially Online Damage Detection using Long-Term Modal Data Under Severe Environmental Effects by Unsupervised Feature Selection and Local Metric Learning,” Journal of Civil Structural Health Monitoring, vol. 12, no. 5, pp. 1043-1066, 2022. [CrossRef] [Google Scholar] [Publisher Link]
  21. Ali Anaissi, Basem Suleiman, and Widad Alyassine, “Personalised Federated Learning Framework for Damage Detection in Structural Health Monitoring,” Journal of Civil Structural Health Monitoring, vol. 13, no. 2-3, pp. 295-308, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  22. Daniele Kauctz Monteiro et al., “Whale Optimization Algorithm for Structural Damage Detection, Localization, and Quantification,” Discover Civil Engineering, vol. 1, no. 1, pp. 1-22, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  23. Pouria Hamidian, Yasaman J. Soofi, and Maryam Bitaraf, “A Comparative Machine Learning Approach for Entropy-based Damage Detection using Output-Only Correlation Signal,” Journal of Civil Structural Health Monitoring, vol. 12, no. 5, pp 975-990, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  24. Chandesh Palsara et al., “Structural Health Monitoring of ASCE Benchmark Building using Machine Learning Algorithms,” Asian Journal of Civil Engineering, vol. 25, no. 1, pp. 303-316, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  25. Junchen Ye et al., “Investigation on Identification of Structural Anomalies from Polluted Data Sets using an Unsupervised Learning Method,” Frontiers of Structural and Civil Engineering, vol. 18, no. 10, pp. 1479-1491, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  26. Yingying He et al., “A Framework of Structural Damage Detection for Civil Structures using a Combined Multi-Scale Convolutional Neural Network and Echo State Network,” Engineering with Computers, vol. 39, no. 3, pp. 1771-1789, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  27. Yantao Zhu et al., “Damage Assessment and Diagnosis of Hydraulic Concrete Structures using Optimization-based Machine Learning Technology,” Frontiers of Structural and Civil Engineering, vol. 17, no. 8, pp. 1281-1294, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  28. Shuming Zhou, Donghuang Yan, and Yu He, “Interpretable Capacity Prediction of RC Bridges based on Genetic Algorithm-Enhanced Support Vector Machine Learning,” KSCE Journal of Civil Engineering, vol. 28, no. 10, pp. 4559-4574, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  29. T. Jothi Saravanan et al., “Internet of Things (IoT)-based Structural Health Monitoring of Laboratory-Scale Civil Engineering Structures,” Innovative Infrastructure Solutions, vol. 9, no. 4, pp. 1-15, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  30. Wenzhi Yuan, and Qun Yang, “A Novel Method for Pavement Transverse Crack Detection based on 2D Reconstruction of Vehicle Vibration Signal,” KSCE Journal of Civil Engineering, vol. 27, no. 7, pp. 2868-2881, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  31. Caiwei Liu et al., “Research on Damage Identification of Large-Span Spatial Structures based on Deep Learning,” Journal of Civil Structural Health Monitoring, vol. 14, no. 4, pp. 1035-1058, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  32. Ali Zar et al., “Vibration-based Damage Detection of Arch Dams using Least-Square Support Vector Machines and Salp Swarm Algorithms,” Iranian Journal of Science and Technology, Transactions of Civil Engineering, vol. 46, no. 6, pp. 4441-4462, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  33. Amanda Aryda Silva Rodrigues de Sousa et al., “Multiclass Supervised Machine Learning Algorithms Applied to Damage and Assessment using Beam Dynamic Response,” Journal of Vibration Engineering and Technologies, vol. 11, no. 6, pp. 2709-2731, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  34. Furkan Luleci, F. Necati Catbas, and Onur Avci, “Generative Adversarial Networks for Labeled Acceleration Data Augmentation for Structural Damage Detection,” Journal of Civil Structural Health Monitoring, vol. 13, no. 1, pp. 181-198, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  35. Burcu Gunes, “One-Class Machine Learning Approach for Localized Damage Detection,” Journal of Civil Structural Health Monitoring, vol. 12, no. 5, pp. 1115-1131, 2022.
    [    CrossRef] [Google Scholar] [Publisher Link]
  36. Zahir Malik et al., “A Review on Vision-based Deep Learning Techniques for Damage Detection in Bolted Joints,” Asian Journal of Civil Engineering, vol. 25, no. 8, pp. 5697-5707, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  37. Mohammad Hossein Afsharmovahed, Gholamreza Ghodrati Amiri, and Ehsan Darvishan, “A Novel Damage Detection Approach based on Feature Extraction and Selection using Machine Learning Without Signal Processing: A Case Study on the Tianjin Yonghe Bridge,” Iranian Journal of Science and Technology, Transactions of Civil Engineering, vol. 47, no. 6, pp. 3649-3661, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  38. Zhou Zhou et al., “Prediction of Damage Potential in Mainshock-Aftershock Sequences using Machine Learning Algorithms,” Earthquake Engineering and Engineering Vibration, vol. 23, no. 4, pp. 919-938, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  39. Arghavan Asghari et al., “A Novel Approach for Structural Damage Detection using Multi-Headed Stacked Deep Ensemble Learning,” Journal of Vibration Engineering and Technologies, vol. 12, no. 3, pp. 4209-4224, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  40. Rama Krishna Shinagam et al., “Development of a Machine Learning Algorithm for Efficient Localization of Damage in a Composite Structure using Random Forest Technique,” Iranian Journal of Science and Technology, Transactions of Civil Engineering, vol. 48, no. 6, pp. 4793-4809, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]