Machine Learning On Structural Vibration Time-Series Signals For Structural Stability Prediction And Seismic Performance Evaluation
DOI:
https://doi.org/10.29284/np3jwe67Keywords:
structural vibration, seismic performance evaluation, machine learning, structural stability prediction, damage classification.Abstract
Machine learning–based analysis of structural vibration time-series signals has emerged as a promising approach for enhancing structural stability prediction and damage-based seismic performance evaluation. Continuous monitoring systems equipped with accelerometers and strain sensors generate large volumes of response data that can be leveraged for data-driven assessment of structural condition. This study investigates the application of supervised machine learning techniques to classify structural condition states using multi-channel vibration and strain measurements. A structured framework is developed that includes data preprocessing, feature scaling, class imbalance handling, and comparative model evaluation. Random Forest and Support Vector Machine classifiers are employed to assess their effectiveness in multi-class damage classification under imbalanced data conditions. The results demonstrate that vibration and strain features provide meaningful information for distinguishing healthy, minor damage, and severe damage states. Feature relevance analysis highlights the dominant contribution of structural strain, while class balancing improves sensitivity to less-represented damage conditions. Among the evaluated models, the Support Vector Machine exhibits the most balanced performance across structural condition states, particularly in detecting minor damage, which is critical for early-stage deterioration assessment. The findings indicate that combining interpretable vibration-based features with appropriate machine learning strategies can support reliable and practical seismic performance evaluation. The proposed framework offers a scalable foundation for sensor-based structural health monitoring and data-informed decision support in seismic risk management.
References
1. Avci, O., Abdeljaber, O., Kiranyaz, S., Hussein, M., Gabbouj, M. and Inman, D.J., 2021. A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications. Mechanical systems and signal processing, 147, p.107077.
2. Kubo, H., Naoi, M. and Kano, M., 2024. Recent advances in earthquake seismology using machine learning. Earth, Planets and Space, 76(1), p.36.
3. Fitzgerald, P.C., Malekjafarian, A., Bhowmik, B., Prendergast, L.J., Cahill, P., Kim, C.W., Hazra, B., Pakrashi, V. and OBrien, E.J., 2019. Scour damage detection and structural health monitoring of a laboratory-scaled bridge using a vibration energy harvesting device. Sensors, 19(11), p.2572.
4. Zhang, G.Q., Wang, B., Li, J. and Xu, Y.L., 2022. The application of deep learning in bridge health monitoring: a literature review. Advances in Bridge Engineering, 3(1), p.22.
5. Singh, T., Sehgal, S., Prakash, C. and Dixit, S., 2022. Real-time structural health monitoring and damage identification using frequency response functions along with finite element model updating technique. Sensors, 22(12), p.4546.
6. Xie, Y., 2025. Deep learning in earthquake engineering: A comprehensive review. ASCE OPEN: Multidisciplinary Journal of Civil Engineering, 3(1), p.03125001.
7. Zhang, M., Guo, T., Zhang, G., Liu, Z. and Xu, W., 2024. Physics-informed deep learning for structural vibration identification and its application on a benchmark structure. Philosophical Transactions of the Royal Society A, 382(2264), p.20220400.
8. Zhou, X., Zhao, Y., Khan, I. and Cao, L., 2024. Comparative study on CNN-based bridge seismic damage identification using various features. KSCE Journal of Civil Engineering, 28(12), pp.5618-5627.
9. Gomez Munoz, C.Q., García-Vellisca, M.A., do Cabo, C.T., Xi, Y. and Mao, Z., 2025. Structural health monitoring through deep learning: A study on scalogram-based vibration signal classification. Journal of Low Frequency Noise, Vibration and Active Control, p.14613484251351788.
10. Lee, Y., Kim, H., Min, S. and Yoon, H., 2023. Structural damage detection using deep learning and FE model updating techniques. Scientific Reports, 13(1), p.18694.
11. Teng, S., Chen, G., Liu, Z., Cheng, L. and Sun, X., 2021. Multi-sensor and decision-level fusion-based structural damage detection using a one-dimensional convolutional neural network. Sensors, 21(12), p.3950.
12. Sarma, I.V., Chanda, S. and Reddy, M.S., 2025. Interpretable AI for vibration-based structural health monitoring: a comparative study of CNN and transformer architectures on a benchmark shear building. Asian Journal of Civil Engineering, 26(11), pp.4615-4628.
13. Kashyap, P., Shivgan, K., Patil, S., Raja, B.R., Mahajan, S., Banerjee, S. and Tallur, S., 2024. Unsupervised deep learning framework for temperature-compensated damage assessment using ultrasonic guided waves on edge device. Scientific Reports, 14(1), p.3751.
14. Amanollah, H., Mohammadi, R.K. and Ghorbani-Tanha, A.K., 2025. Structural damage detection using voting ensemble of fine-tuned convolutional neural networks and time-frequency images. Scientific Reports, 15(1), p.36199.
15. Azimi, M., Eslamlou, A.D. and Pekcan, G., 2020. Data-driven structural health monitoring and damage detection through deep learning: State-of-the-art review. Sensors, 20(10), p.2778.
16. Ziya, 2025. Building Structural Health Sensor Dataset. Kaggle. Available at: https://www.kaggle.com/datasets/ziya07/building-structural-health-sensor-dataset
17. Ghimire, S., Guéguen, P., Giffard-Roisin, S. and Schorlemmer, D., 2022. Testing machine learning models for seismic damage prediction at a regional scale using building-damage dataset compiled after the 2015 Gorkha Nepal earthquake. Earthquake Spectra, 38(4), pp.2970-2993.
18. Minonzio, J.G., Cataldo, B., Olivares, R., Ramiandrisoa, D., Soto, R., Crawford, B., De Albuquerque, V.H.C. and Munoz, R., 2020. Automatic classifying of patients with non-traumatic fractures based on ultrasonic guided wave spectrum image using a dynamic support vector machine. IEEE Access, 8, pp.194752-194764.
19. Giglioni, V., Poole, J., Mills, R., Venanzi, I., Ubertini, F. and Worden, K., 2025. Transfer learning in bridge monitoring: Laboratory study on domain adaptation for population-based SHM of multispan continuous girder bridges. Mechanical Systems and Signal Processing, 224, p.112151.
20. Lin, Q., Ci, T., Wang, L., Mondal, S.K., Yin, H. and Wang, Y., 2022. Transfer learning for improving seismic building damage assessment. Remote Sensing, 14(1), p.201.
21. Khan, A., Hussain, M.A. and Anwer, F., 2025. A Hybrid Lightweight Deep Learning-Based Intrusion Detection Approach in IoT Utilizing Feature Selection & Explainable Artificial Intelligence. IEEE Access, 13, pp.192451-192466.
22. Gao, J., Gao, Z., Fan, X., Manzhos, S., Zhang, T. and Liu, Y., 2025. Transfer learning of high-dimensional features via attention-based embedding for Ni-based superalloys. Journal of Applied Physics, 138(2).
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
