Structural Damage Prediction of a Concrete and Steel Bridge Using Acceleration Signal Processing and Artificial Intelligence Algorithms

Abstract:

This study presents a methodology for predicting structural damage in a concrete and steel bridge using acceleration signal processing and artificial intelligence techniques. Structural vibrations were recorded continuously for 24 hours using five LARA (Low-cost Adaptable Reliable Anglemete) triaxial sensors located on the metal beams under the bridge, capturing data in three axes. The signals were normalized in order to be able to have a fairness of accelerations in the 3 axes and processed through a Convolutional Autoencoder (CAE), which achieved a signal reconstruction fidelity of 97.22%, enabling the generation of realistic synthetic data. To evaluate the separability between real and synthetic signals, a Domain-Adversarial Neural Network (DANN) was applied, successfully classifying both domains. Subsequently, K-Means clustering was performed on the compressed latent space, identifying three distinct structural states: healthy, transitional, and anomalous, with a silhouette coefficient of 0.8947. Notably, Sensors 2 and 4 were grouped into the anomalous cluster, indicating potential localized structural degradation. Finally, a Temporal Convolutional Network (TCN) was implemented to predict the future structural condition based on sequences of latent features. The model achieved an overall accuracy of 85.29% and an F1-score of 0.9954 for transitional states, demonstrating its effectiveness in anticipating early structural changes and reinforcing the potential of the proposed methodology for real-time, predictive bridge monitoring applications.

• Periodical: Applied Mechanics and Materials (Volume 935)
• Pages: 263-268
• DOI: https://doi.org/10.4028/p-MVKm6i
• Online since: April 2026
• Authors: Nicole Xiomara Diaz, Aldahir William Ortega, Rick Milton Delgadillo*
• Keywords: Acceleration Signal Processing, Autoencoder, Bridge Damage Detection, Domain-Adversarial Neural Network, K-Means Clustering, Structural Health Monitoring

References

[1] Bouzas, O., Conde, B., Cabaleiro, M., & Riveiro, B. (2022). A holistic methodology for the non-destructive experimental characterization and reliability-based structural assessment of historical steel bridges. Engineering Structures, 270, 114867

DOI: 10.1016/J.ENGSTRUCT.2022.114867

[2] Hagen, A., & Andersen, T. M. (2024). Asset management, condition monitoring and Digital Twins: damage detection and virtual inspection on a reinforced concrete bridge. Structure and Infrastructure Engineering, 20(7–8), 1242–1273

DOI: 10.1080/15732479.2024.2311911

[3] Kauss, K., Alves, V., Barbosa, F., & Cury, A. (2024) Semi-supervised structural damage assessment via autoregressive models and evolutionary optimization. Structures, 59

DOI: 10.1016/J.ISTRUC.2023.105762

[4] Ding, Y., Ye, X. W., & Guo, Y. (2023). Data set from wind, temperature, humidity and cable acceleration monitoring of the Jiashao bridge. Journal of Civil Structural Health Monitoring, 13 (2–3), 579–589

DOI: 10.1007/S13349-022-00662-5

[5] Morgantini, M., Betti, R., & Balsamo, L. (2021). Structural damage assessment through features in quefrency domain. Mechanical Systems and Signal Processing, 147

DOI: 10.1016/J.YMSSP.2020.107017

[6] Zhang, Y., & Lei, Y. (2021). Data Anomaly Detection of Bridge Structures Using Convolutional Neural Network Based on Structural Vibration Signals. Symmetry, 13(7), 1186

DOI: 10.3390/SYM13071186

[7] Delgadillo, R. M., & Casas, J. R. (2022). Bridge damage detection via improved completed ensemble empirical mode decomposition with adaptive noise and machine learning algorithms. Structural Control and Health Monitoring, 29(8), e2966

DOI: 10.1002/stc.2966

[8] Nguyen, D. C., Salamak, M., Katunin, A., Poprawa, G., Przystałka, P., & Hypki, M. (2024). Vibration-based SHM of Dębica railway steel bridge with optimized ANN and ANFIS. Journal of Constructional Steel Research, 215, 108505

DOI: 10.1016/j.jcsr.2024.108505

[9] Svendsen, B. T., Frøseth, G. T., Øiseth, O., & Rønnquist, A. (2022). A data-based structural health monitoring approach for damage detection in steel bridges using experimental data. Journal of Civil Structural Health Monitoring, 12(1), 101–115

DOI: 10.1007/s13349-021-00530-8

[10] Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.

[11] Chollet, F. (2017). Deep Learning with Python. Manning Publications.

[12] Ganin, Y., & Lempitsky, V. (2015). Unsupervised domain adaptation by backpropagation. Proceedings of ICML.

[13] Jolliffe, I. T. (2002). Principal Component Analysis. Springer.

[14] MacQueen, J. (1967). Some Methods for Classification and Analysis of Multivariate Observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability.