A Novel Hybrid Wavelet-deep Learning Framework for Advanced Structural Damage Detection
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Published
Nov 20, 2025
Oumayma Najem
Mohammed Benbrahim
Mohammed Nabil Kabbaj
Jaouad Boumhidi
Abstract
Infrastructures globally are nearing or surpassing their designated lifespans, with recent structural failures serving as a reminder. The aging of infrastructure is a natural eventuality that causes a decline in the structures’ mechanical characteristics, consequently affecting their serviceability. The rapid aging of global infrastructure necessitates the development of precise and effective damage detection techniques to preserve public safety. Traditional inspection techniques cannot adequately address modern structural issues, which calls for more sophisticated methods. This study proposes a novel hybrid wavelet-CNN-Transformer framework for structural damage detection that simultaneously extracts localized damage signs and gradual changes in the overall behavior of structural vibrations. Our proposed framework uses the Ben wavelet transform to convert raw acceleration signals into time-frequency representations, which are then processed through a parallel CNN and Transformer branches to extract spatial and temporal features before fusion. We validated this approach on two datasets: the Z24 Bridge dataset and the Qatar University Grandstand Simulator (QUGS) dataset. Our proposed framework achieved 98.85% on the Z24 Bridge dataset and 97.9% on the QUGS dataset, representing a 1.35% improvement over state-of-the-art methods. The proposed framework identifies both the sharp structural discontinuities and the subtle shift in the global behavior of the structure.
##plugins.themes.bootstrap3.article.details##
Keywords
Structural Health Monitoring, Damage Detection, Wavelet Transform, Deep Learning, Civil Infrastructure
References
Abdeljaber, O., Avci, O., Kiranyaz, S., Gabbouj, M., & In-man, D. J. (2017). Real-time vibration-based struc-tural damage detection using one-dimensional con-volutional neural networks. Journal of Sound and Vibration, 388, 154–170.
Avci, O., Abdeljaber, O., Kiranyaz, S., Hussein, M., Gab-bouj, M., & Inman, D. (2022). A New Benchmark Problem for Structural Damage Detection: Bolt Loosening Tests on a Large-Scale Laboratory Struc-ture. In K. Grimmelsman (Ed.), Dynamics of Civil Structures, Volume 2 (pp. 15–22). Springer Interna-tional Publishing. https://doi.org/10.1007/978-3-030-77143-0_2
Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer Normal-ization (arXiv:1607.06450). arXiv. https://doi.org/10.48550/arXiv.1607.06450
Benbrahim, M., Benjelloun, K., Ibenbrahim, A., & Daoudi, A. (2005). Classification of non stationary signals using Ben wavelet and artificial neural networks. Proceedings of the 2nd World Enfomatika Congress, February 25-27, 2005, Istanbul, Turkey.
Chen, D., Zhang, Y., Wan, R., Li, Z., Xu, S., & Yang, C. (2024). Indirect identification of bridge damage based on coupled vehicle–bridge vibration and 2D-CNN. Measurement Science and Technology, 35(5), 055019. https://doi.org/10.1088/1361-6501/ad2ad5
Demirlioglu, K., & Erduran, E. (2024). Drive-by Bridge Damage Detection Using Continuous Wavelet Transform. Applied Sciences, 14(7), Article 7. https://doi.org/10.3390/app14072969
Deng, Z., Huang, M., Wan, N., & Zhang, J. (2023). The Cur-rent Development of Structural Health Monitoring for Bridges: A Review. Buildings, 13(6), Article 6. https://doi.org/10.3390/buildings13061360
Fukuoka, T., & Fujiu, M. (2023). Detection of Bridge Dam-ages by Image Processing Using the Deep Learning Transformer Model. Buildings, 13(3), Article 3. https://doi.org/10.3390/buildings13030788
Garg, R. K., Chandra, S., & Kumar, A. (2022). Analysis of bridge failures in India from 1977 to 2017. Structure and Infrastructure Engineering, 18(3), 295–312. https://doi.org/10.1080/15732479.2020.1832539
Goupillaud, P., Grossmann, A., & Morlet, J. (1984). Cycle-octave and related transforms in seismic signal anal-ysis. Geoexploration, 23(1), 85–102. https://doi.org/10.1016/0016-7142(84)90025-5
He, Z., Li, W., Salehi, H., Zhang, H., Zhou, H., & Jiao, P. (2022). Integrated structural health monitoring in bridge engineering. Automation in Construction, 136, 104168. https://doi.org/10.1016/j.autcon.2022.104168
Hester, D., & González, A. (2017). A discussion on the merits and limitations of using drive-by monitoring to de-tect localised damage in a bridge. Mechanical Sys-tems and Signal Processing, 90, 234–253. https://doi.org/10.1016/j.ymssp.2016.12.012
Kim, H., & Melhem, H. (2004). Damage detection of struc-tures by wavelet analysis. Engineering Structures, 26(3), 347–362. https://doi.org/10.1016/j.eng-struct.2003.10.008
Kobak, D., & Berens, P. (2019). The art of using t-SNE for single-cell transcriptomics. Nature Communica-tions, 10(1), 5416. https://doi.org/10.1038/s41467-019-13056-x
Kuo, C.-C., & Lee, C.-H. (2023). An Enhanced Structural Damage Identification Approach Using Statistical Analysis and Optimization. IEEE Sensors Journal, 23(24), 31082–31097.
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gra-dient-based learning applied to document recogni-tion. Proceedings of the IEEE, 86(11), 2278–2324. https://doi.org/10.1109/5.726791
Maeck, J., & De Roeck, G. (2003). DESCRIPTION OF Z24 BENCHMARK. Mechanical Systems and Signal Processing, 17(1), 127–131. https://doi.org/10.1006/mssp.2002.1548
Mallat, S. G. (1989). A theory for multiresolution signal de-composition: The wavelet representation. IEEE Transactions on Pattern Analysis and Machine In-telligence, 11(7), 674–693. https://doi.org/10.1109/34.192463
M.ASCE, O. A., Ph D. ,. P. E. (2018, December 14). Qatar University Grandstand Simulator (QUGS). Onur Avci. http://onur-avci.com/benchmark/qugs/
Najdi, B., Benbrahim, M., & Kabbaj, M. N. (2025). Adaptive Res-LSTM Attention-based Remaining Useful Life-time Prognosis of Rolling Bearings. International Journal of Prognostics and Health Management, 16(1), Article 1. https://doi.org/10.36001/ijphm.2025.v16i1.4171
Nguyen, D. C., Salamak, M., Katunin, A., Poprawa, G., & Gerges, M. (2024). Vibration-based SHM of rail-way steel arch bridge with orbit-shaped image and wavelet-integrated CNN classification. Engineering Structures, 315, 118431. https://doi.org/10.1016/j.engstruct.2024.118431
Papoulis, A. (1977). Signal analysis (16. [print]). McGraw-Hill.
Qiu, Y., Ahmed, B., Abueidda, D. W., El-Sekelly, W., de Soto, B. G., Abdoun, T., Ji, H., Qiu, J., & Mobasher, M. E. (2024). Damage identification for bridges us-ing machine learning: Development and application to KW51 bridge (arXiv:2408.03002). arXiv. http://arxiv.org/abs/2408.03002
Rabi, R. R., Vailati, M., & Monti, G. (2024). Effectiveness of Vibration-Based Techniques for Damage Localiza-tion and Lifetime Prediction in Structural Health Monitoring of Bridges: A Comprehensive Review. Buildings, 14(4), Article 4. https://doi.org/10.3390/buildings14041183
Saidin, S. S., Jamadin, A., Abdul Kudus, S., Mohd Amin, N., & Anuar, M. A. (2022). An Overview: The Appli-cation of Vibration-Based Techniques in Bridge Structural Health Monitoring. International Journal of Concrete Structures and Materials, 16(1), 69. https://doi.org/10.1186/s40069-022-00557-1
Salehin, I., & Kang, D.-K. (2023). A Review on Dropout Regularization Approaches for Deep Neural Net-works within the Scholarly Domain. Electronics, 12(14), Article 14. https://doi.org/10.3390/electron-ics12143106
Santaniello, P., & Russo, P. (2023). Bridge Damage Identifi-cation Using Deep Neural Networks on Time–Fre-quency Signals Representation. Sensors, 23(13), Ar-ticle 13. https://doi.org/10.3390/s23136152
Schabowicz, K. (2019). Non-Destructive Testing of Materi-als in Civil Engineering. Materials, 12(19), Article 19. https://doi.org/10.3390/ma12193237
Song, X., Li, D., & Cho, C. (2024). Image-based machine learning approach for structural damage detection through wavelet transforms. Urban Lifeline, 2(1), 4. https://doi.org/10.1007/s44285-023-00010-z
Sony, S., Gamage, S., Sadhu, A., & Samarabandu, J. (2022a). Multiclass Damage Identification in a Full-Scale Bridge Using Optimally Tuned One-Dimensional Convolutional Neural Network. Journal of Compu-ting in Civil Engineering, 36(2), 04021035. https://doi.org/10.1061/(ASCE)CP.1943-5487.0001003
Sony, S., Gamage, S., Sadhu, A., & Samarabandu, J. (2022b). Vibration-based multiclass damage detection and localization using long short-term memory net-works. Structures, 35, 436–451. https://doi.org/10.1016/j.istruc.2021.10.088
Sun, L., Shang, Z., Xia, Y., Bhowmick, S., & Nagarajaiah, S. (2020). Review of Bridge Structural Health Moni-toring Aided by Big Data and Artificial Intelligence: From Condition Assessment to Damage Detection. Journal of Structural Engineering, 146(5), 04020073. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002535
Tan, C., Zhao, H., Uddin, N., & Yan, B. (2022). A Fast Wavelet-Based Bridge Condition Assessment Ap-proach Using Only Moving Vehicle Measurements. Applied Sciences, 12(21), Article 21. https://doi.org/10.3390/app122111277
Truong, T. T., Lee, J., & Nguyen-Thoi, T. (2022). An effec-tive framework for real-time structural damage de-tection using one-dimensional convolutional gated recurrent unit neural network and high performance computing. Ocean Engineering, 253, 111202. https://doi.org/10.1016/j.oceaneng.2022.111202
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł. ukasz, & Polosukhin, I. (2017). Attention is All you Need. Advances in Neural Information Processing Systems, 30. https://proceedings.neurips.cc/pa-per/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html
Wan, H., Gao, L., Yuan, Z., Qu, H., Sun, Q., Cheng, H., & Wang, R. (2023). A novel transformer model for surface damage detection and cognition of concrete bridges. Expert Systems with Applications, 213, 119019. https://doi.org/10.1016/j.eswa.2022.119019
Wu, C.-S., Peng, Y.-X., Zhuo, D.-B., Zhang, J.-Q., Ren, W., & Feng, Z.-Y. (2022). Energy Ratio Variation-Based Structural Damage Detection Using Convo-lutional Neural Network. Applied Sciences, 12(20), Article 20. https://doi.org/10.3390/app122010220
Xu, C., Ni, Y.-Q., & Wang, Y.-W. (2022). A novel Bayesian blind source separation approach for extracting non-stationary and discontinuous components from structural health monitoring data. Engineering Structures, 269, 114837. https://doi.org/10.1016/j.engstruct.2022.114837
Z24 Bridge benchmark. (n.d.). [Page]. Departement Burg-erlijke Bouwkunde KU Leuven. Retrieved February 17, 2025, from https://bwk.kuleuven.be/bwm/z24
Avci, O., Abdeljaber, O., Kiranyaz, S., Hussein, M., Gab-bouj, M., & Inman, D. (2022). A New Benchmark Problem for Structural Damage Detection: Bolt Loosening Tests on a Large-Scale Laboratory Struc-ture. In K. Grimmelsman (Ed.), Dynamics of Civil Structures, Volume 2 (pp. 15–22). Springer Interna-tional Publishing. https://doi.org/10.1007/978-3-030-77143-0_2
Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer Normal-ization (arXiv:1607.06450). arXiv. https://doi.org/10.48550/arXiv.1607.06450
Benbrahim, M., Benjelloun, K., Ibenbrahim, A., & Daoudi, A. (2005). Classification of non stationary signals using Ben wavelet and artificial neural networks. Proceedings of the 2nd World Enfomatika Congress, February 25-27, 2005, Istanbul, Turkey.
Chen, D., Zhang, Y., Wan, R., Li, Z., Xu, S., & Yang, C. (2024). Indirect identification of bridge damage based on coupled vehicle–bridge vibration and 2D-CNN. Measurement Science and Technology, 35(5), 055019. https://doi.org/10.1088/1361-6501/ad2ad5
Demirlioglu, K., & Erduran, E. (2024). Drive-by Bridge Damage Detection Using Continuous Wavelet Transform. Applied Sciences, 14(7), Article 7. https://doi.org/10.3390/app14072969
Deng, Z., Huang, M., Wan, N., & Zhang, J. (2023). The Cur-rent Development of Structural Health Monitoring for Bridges: A Review. Buildings, 13(6), Article 6. https://doi.org/10.3390/buildings13061360
Fukuoka, T., & Fujiu, M. (2023). Detection of Bridge Dam-ages by Image Processing Using the Deep Learning Transformer Model. Buildings, 13(3), Article 3. https://doi.org/10.3390/buildings13030788
Garg, R. K., Chandra, S., & Kumar, A. (2022). Analysis of bridge failures in India from 1977 to 2017. Structure and Infrastructure Engineering, 18(3), 295–312. https://doi.org/10.1080/15732479.2020.1832539
Goupillaud, P., Grossmann, A., & Morlet, J. (1984). Cycle-octave and related transforms in seismic signal anal-ysis. Geoexploration, 23(1), 85–102. https://doi.org/10.1016/0016-7142(84)90025-5
He, Z., Li, W., Salehi, H., Zhang, H., Zhou, H., & Jiao, P. (2022). Integrated structural health monitoring in bridge engineering. Automation in Construction, 136, 104168. https://doi.org/10.1016/j.autcon.2022.104168
Hester, D., & González, A. (2017). A discussion on the merits and limitations of using drive-by monitoring to de-tect localised damage in a bridge. Mechanical Sys-tems and Signal Processing, 90, 234–253. https://doi.org/10.1016/j.ymssp.2016.12.012
Kim, H., & Melhem, H. (2004). Damage detection of struc-tures by wavelet analysis. Engineering Structures, 26(3), 347–362. https://doi.org/10.1016/j.eng-struct.2003.10.008
Kobak, D., & Berens, P. (2019). The art of using t-SNE for single-cell transcriptomics. Nature Communica-tions, 10(1), 5416. https://doi.org/10.1038/s41467-019-13056-x
Kuo, C.-C., & Lee, C.-H. (2023). An Enhanced Structural Damage Identification Approach Using Statistical Analysis and Optimization. IEEE Sensors Journal, 23(24), 31082–31097.
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gra-dient-based learning applied to document recogni-tion. Proceedings of the IEEE, 86(11), 2278–2324. https://doi.org/10.1109/5.726791
Maeck, J., & De Roeck, G. (2003). DESCRIPTION OF Z24 BENCHMARK. Mechanical Systems and Signal Processing, 17(1), 127–131. https://doi.org/10.1006/mssp.2002.1548
Mallat, S. G. (1989). A theory for multiresolution signal de-composition: The wavelet representation. IEEE Transactions on Pattern Analysis and Machine In-telligence, 11(7), 674–693. https://doi.org/10.1109/34.192463
M.ASCE, O. A., Ph D. ,. P. E. (2018, December 14). Qatar University Grandstand Simulator (QUGS). Onur Avci. http://onur-avci.com/benchmark/qugs/
Najdi, B., Benbrahim, M., & Kabbaj, M. N. (2025). Adaptive Res-LSTM Attention-based Remaining Useful Life-time Prognosis of Rolling Bearings. International Journal of Prognostics and Health Management, 16(1), Article 1. https://doi.org/10.36001/ijphm.2025.v16i1.4171
Nguyen, D. C., Salamak, M., Katunin, A., Poprawa, G., & Gerges, M. (2024). Vibration-based SHM of rail-way steel arch bridge with orbit-shaped image and wavelet-integrated CNN classification. Engineering Structures, 315, 118431. https://doi.org/10.1016/j.engstruct.2024.118431
Papoulis, A. (1977). Signal analysis (16. [print]). McGraw-Hill.
Qiu, Y., Ahmed, B., Abueidda, D. W., El-Sekelly, W., de Soto, B. G., Abdoun, T., Ji, H., Qiu, J., & Mobasher, M. E. (2024). Damage identification for bridges us-ing machine learning: Development and application to KW51 bridge (arXiv:2408.03002). arXiv. http://arxiv.org/abs/2408.03002
Rabi, R. R., Vailati, M., & Monti, G. (2024). Effectiveness of Vibration-Based Techniques for Damage Localiza-tion and Lifetime Prediction in Structural Health Monitoring of Bridges: A Comprehensive Review. Buildings, 14(4), Article 4. https://doi.org/10.3390/buildings14041183
Saidin, S. S., Jamadin, A., Abdul Kudus, S., Mohd Amin, N., & Anuar, M. A. (2022). An Overview: The Appli-cation of Vibration-Based Techniques in Bridge Structural Health Monitoring. International Journal of Concrete Structures and Materials, 16(1), 69. https://doi.org/10.1186/s40069-022-00557-1
Salehin, I., & Kang, D.-K. (2023). A Review on Dropout Regularization Approaches for Deep Neural Net-works within the Scholarly Domain. Electronics, 12(14), Article 14. https://doi.org/10.3390/electron-ics12143106
Santaniello, P., & Russo, P. (2023). Bridge Damage Identifi-cation Using Deep Neural Networks on Time–Fre-quency Signals Representation. Sensors, 23(13), Ar-ticle 13. https://doi.org/10.3390/s23136152
Schabowicz, K. (2019). Non-Destructive Testing of Materi-als in Civil Engineering. Materials, 12(19), Article 19. https://doi.org/10.3390/ma12193237
Song, X., Li, D., & Cho, C. (2024). Image-based machine learning approach for structural damage detection through wavelet transforms. Urban Lifeline, 2(1), 4. https://doi.org/10.1007/s44285-023-00010-z
Sony, S., Gamage, S., Sadhu, A., & Samarabandu, J. (2022a). Multiclass Damage Identification in a Full-Scale Bridge Using Optimally Tuned One-Dimensional Convolutional Neural Network. Journal of Compu-ting in Civil Engineering, 36(2), 04021035. https://doi.org/10.1061/(ASCE)CP.1943-5487.0001003
Sony, S., Gamage, S., Sadhu, A., & Samarabandu, J. (2022b). Vibration-based multiclass damage detection and localization using long short-term memory net-works. Structures, 35, 436–451. https://doi.org/10.1016/j.istruc.2021.10.088
Sun, L., Shang, Z., Xia, Y., Bhowmick, S., & Nagarajaiah, S. (2020). Review of Bridge Structural Health Moni-toring Aided by Big Data and Artificial Intelligence: From Condition Assessment to Damage Detection. Journal of Structural Engineering, 146(5), 04020073. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002535
Tan, C., Zhao, H., Uddin, N., & Yan, B. (2022). A Fast Wavelet-Based Bridge Condition Assessment Ap-proach Using Only Moving Vehicle Measurements. Applied Sciences, 12(21), Article 21. https://doi.org/10.3390/app122111277
Truong, T. T., Lee, J., & Nguyen-Thoi, T. (2022). An effec-tive framework for real-time structural damage de-tection using one-dimensional convolutional gated recurrent unit neural network and high performance computing. Ocean Engineering, 253, 111202. https://doi.org/10.1016/j.oceaneng.2022.111202
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł. ukasz, & Polosukhin, I. (2017). Attention is All you Need. Advances in Neural Information Processing Systems, 30. https://proceedings.neurips.cc/pa-per/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html
Wan, H., Gao, L., Yuan, Z., Qu, H., Sun, Q., Cheng, H., & Wang, R. (2023). A novel transformer model for surface damage detection and cognition of concrete bridges. Expert Systems with Applications, 213, 119019. https://doi.org/10.1016/j.eswa.2022.119019
Wu, C.-S., Peng, Y.-X., Zhuo, D.-B., Zhang, J.-Q., Ren, W., & Feng, Z.-Y. (2022). Energy Ratio Variation-Based Structural Damage Detection Using Convo-lutional Neural Network. Applied Sciences, 12(20), Article 20. https://doi.org/10.3390/app122010220
Xu, C., Ni, Y.-Q., & Wang, Y.-W. (2022). A novel Bayesian blind source separation approach for extracting non-stationary and discontinuous components from structural health monitoring data. Engineering Structures, 269, 114837. https://doi.org/10.1016/j.engstruct.2022.114837
Z24 Bridge benchmark. (n.d.). [Page]. Departement Burg-erlijke Bouwkunde KU Leuven. Retrieved February 17, 2025, from https://bwk.kuleuven.be/bwm/z24
Section
Technical Papers