A Novel WaveNet Deep Learning Approach for Enhanced Bridge Damage Detection
Source abstract
Abstract
Bridges are vital components of global infrastructure, with millions constructed over the years. Many of them face aging and are vulnerable to risks. Traditional bridge inspection methods are costly and time-consuming. They often rely on many manual laborers without providing system-level insights. Moreover, these outdated approaches make it difficult to obtain a clear representation of the current bridge health. This paper introduces a novel framework based on deep learning (DL) for identifying local bridge damage using acceleration data collected by Unmanned Aerial Vehicle (UAV)-mounted sensors. The framework employs WaveNet, which was designed as a generative audio DL model. Its causal dilated convolution deals with long-range temporal correlations without recurrence. Two WaveNet regressors are used to predict the damage location and its severity. The methodology is integrated with an optimized sensor spacing strategy for UAV deployments. The results demonstrate that the severity model achieved an average R2 = 0.98, while the location model reached R2 = 0.85. Optimal sensor spacing “S” was found at S = 1.0 m for localization and S = 0.5 m for severity. A field-simulated case was accurately identified by the two models, representing the potential of the proposed framework for more reliable bridge health monitoring.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Structural Health Monitoring Techniques · Ultrasonics and Acoustic Wave Propagation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Civil, Construction and Environmental Engineering, The University of Alabama at Birmingham, Birmingham, AL 35294, USA
Structural Engineering Department, Faculty of Engineering, Alexandria University, Alexandria 21544, Egypt
Department of Civil and Environmental Engineering, Auburn University, Auburn, AL 36849, USA
Funding
U.S. Department of Education (DOE) Graduate Assistance in Areas of National Need · National Science Foundation
References (85)
Show source-provided references
1. Issues in infrastructure health monitoring for management
2. Routine highway bridge inspection condition documentation accuracy and reliability10.1061/(ASCE)1084-0702(2004)9:4(403) ↗
3. Guided wave based structural health monitoring: A review10.1088/0964-1726/25/5/053001 ↗
4. Structural health monitoring: Closing the gap between research and industrial deployment10.1177/1475921717750047 ↗
5. Integrated structural health monitoring in bridge engineering10.1016/j.autcon.2022.104168 ↗
6. Recent advances in wireless sensor networks for structural health monitoring of civil infrastructure
7. Sonbul, O.S., and Rashid, M. (2023). Towards the structural health monitoring of bridges using wireless sensor networks: A systematic study. Sensors, 23.10.3390/s23208468 ↗
8. Zelenika, S., Hadas, Z., Bader, S., Becker, T., Gljušćić, P., Hlinka, J., Janak, L., Kamenar, E., Ksica, F., and Kyratsi, T. (2020). Energy harvesting technologies for structural health monitoring of airplane components—A review. Sensors, 20.10.3390/s20226685 ↗
9. Smart sensing technology: Opportunities and challenges10.1002/stc.48 ↗
10. Entezami, A., Sarmadi, H., Behkamal, B., and Mariani, S. (2020). Big data analytics and structural health monitoring: A statistical pattern recognition-based approach. Sensors, 20.10.3390/s20082328 ↗
11. Armijo, A., and Zamora-Sánchez, D. (2024). Integration of Railway Bridge Structural Health Monitoring into the Internet of Things with a Digital Twin: A Case Study. Sensors, 24.10.20944/preprints202401.1805.v1 ↗
12. Deep learning-based structural health monitoring10.1016/j.autcon.2024.105328 ↗
13. Jia, J., and Li, Y. (2023). Deep learning for structural health monitoring: Data, algorithms, applications, challenges, and trends. Sensors, 23.10.3390/s23218824 ↗
14. Finding structure in time10.1207/s15516709cog1402_1 ↗
15. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
16. Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv.10.3115/v1/D14-1179 ↗
17. Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv.
18. 1D convolutional neural networks and applications: A survey10.1016/j.ymssp.2020.107398 ↗
19. Deep learning for time series classification: A review10.1007/s10618-019-00619-1 ↗
20. LeCun, Y., and Bengio, Y. (1998). Convolutional networks for images, speech, and time series. The Handbook of Brain Theory and Neural Networks, HAL Open Science.
21. The application of deep learning in bridge health monitoring: A literature review10.1186/s43251-022-00078-7 ↗
22. Science, technology and the future of small autonomous drones10.1038/nature14542 ↗
23. Assessment and use of unmanned aerial vehicle for civil structural health monitoring10.1016/j.procs.2020.03.174 ↗
24. Wavelet-entropy approach for detection of bridge damages using direct and indirect bridge records10.1061/(ASCE)IS.1943-555X.0000577 ↗
25. Drive-by bridge damage monitoring using Bridge Displacement Profile Difference10.1007/s13349-016-0203-6 ↗
26. Vibration-based damage identification methods: A review and comparative study10.1177/1475921710365419 ↗
27. Extracting mode shapes from drive-by measurements to detect global and local damage in bridges10.1080/15732479.2020.1817105 ↗
28. Assessment of bridge natural frequency as an indicator of scour using centrifuge modelling10.1007/s13349-020-00420-5 ↗
29. Van Den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., and Kavukcuoglu, K. (2016). Wavenet: A generative model for raw audio. arXiv.
30. Causal dilated convolutional neural networks for automatic inspection of ultrasonic signals in non-destructive evaluation and structural health monitoring10.1016/j.ymssp.2021.107748 ↗
31. Oord, A., Li, Y., Babuschkin, I., Simonyan, K., Vinyals, O., Kavukcuoglu, K., Driessche, G., Lockhart, E., Cobo, L., and Stimberg, F. (2018, January 10–15). Parallel wavenet: Fast high-fidelity speech synthesis. Proceedings of the International Conference on Machine Learning, Stockholm, Sweden.
32. Engel, J., Resnick, C., Roberts, A., Dieleman, S., Norouzi, M., Eck, D., and Simonyan, K. (2017, January 6–11). Neural audio synthesis of musical notes with wavenet autoencoders. Proceedings of the International Conference on Machine Learning, Sydney, Australia.
33. Rethage, D., Pons, J., and Serra, X. (2018, January 15–20). A wavenet for speech denoising. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8462417 ↗
34. Pankka, H., Lehtinen, J., Ilmoniemi, R.J., and Roine, T. (2024). Forecasting EEG time series with WaveNet. bioRxiv.
35. Significant wave height prediction based on the local-EMD-WaveNet model10.1016/j.oceaneng.2023.115900 ↗
36. Oh, S.L., Jahmunah, V., Ooi, C.P., Tan, R.-S., Ciaccio, E.J., Yamakawa, T., Tanabe, M., Kobayashi, M., and Acharya, U.R. (2020). Classification of heart sound signals using a novel deep WaveNet model. Comput. Methods Programs Biomed., 196.10.1016/j.cmpb.2020.105604 ↗
37. Dorado Rueda, F., Durán Suárez, J., and del Real Torres, A. (2021). Short-term load forecasting using encoder-decoder wavenet: Application to the french grid. Energies, 14.10.3390/en14092524 ↗
38. LSTM, WaveNet, and 2D CNN for nonlinear time history prediction of seismic responses10.1016/j.engstruct.2023.116083 ↗
39. Data-driven modeling of long temperature time-series to capture the thermal behavior of bridges for SHM purposes10.1016/j.ymssp.2023.110934 ↗
40. Psathas, A.P., Iliadis, L., Achillopoulou, D.V., Papaleonidas, A., Stamataki, N.K., Bountas, D., and Dokas, I.M. (2022, January 17–20). Autoregressive deep learning models for bridge strain prediction. Proceedings of the International Conference on Engineering Applications of Neural Networks, Chersonissos, Crete, Greece.10.1007/978-3-031-08223-8_13 ↗
41. Bringing Intelligence to the Edge for Structural Health Monitoring. The Case Study of the Z24 Bridge10.1109/OJIES.2024.3434341 ↗
42. Gaebler, K.O., Shield, C.K., and Linderman, L.E. (2017). Feasibility of Vibration-Based Long-Term Bridge Monitoring Using the I-35W St. Anthony Falls Bridge, Minnesota Department of Transportation.
43. Extracting bridge frequencies from the dynamic response of a passing vehicle10.1016/S0022-460X(03)00378-X ↗
44. Extracting the bridge frequencies indirectly from a passing vehicle: Parametric study10.1016/j.engstruct.2009.06.001 ↗
45. Keenahan, J., McGetrick, P., O’Brien, E.J., and Gonzalez, A. (2012, January 22–27). Using instrumented vehicles to detect damage in bridges. Proceedings of the 15th International Conference on Experimental Mechanics, Porto, Portugal.
46. Bridge modal identification using acceleration measurements within moving vehicles10.1016/j.ymssp.2020.106733 ↗
47. Neubauer, K., Bullard, E., and Blunt, R. (2021). Collection of Data with Unmanned Aerial Systems (UAS) for Bridge Inspection and Construction Inspection.
48. Re-deployable sensors for modal estimates of bridges and detection of damage-induced changes in boundary conditions10.1080/15732479.2021.1887292 ↗
49. Identification of bridge mode shapes using short time frequency domain decomposition of the responses measured in a passing vehicle10.1016/j.engstruct.2014.10.007 ↗
50. Electrically active smart adhesive for a perching-and-takeoff robot10.1126/sciadv.adj3133 ↗
51. Landing and perching on vertical surfaces with microspines for small unmanned air vehicles10.1007/s10846-009-9377-z ↗
52. Array programming with NumPy10.1038/s41586-020-2649-2 ↗
53. Data structures for statistical computing in Python
54. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8–14). Pytorch: An imperative style, high-performance deep learning library. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada.
55. Matplotlib: A 2D graphics environment10.1109/MCSE.2007.55 ↗
56. Abdellatef, A.I.M. (2022). Integrated Structural Health Monitoring Techniques Using Drone Sensors. [Ph.D. Thesis, The University of Alabama at Birmingham].
57. One-dimensional theory of cracked Bernoulli-Euler beams10.1016/0020-7403(84)90017-1 ↗
58. Natural modes of Bernoulli-Euler beams with symmetric cracks10.1016/0022-460X(90)90707-7 ↗
59. Free vibrations of beams with a single-edge crack10.1006/jsvi.1994.1058 ↗
60. Damage assessment for reinforced concrete frames subject to progressive collapse10.1016/j.engstruct.2016.07.038 ↗
61. A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications10.1016/j.ymssp.2020.107077 ↗
62. Simplified models for the location of cracks in beam structures using measured vibration data10.1006/jsvi.2001.3978 ↗
63. Wavelet-based crack identification of bridge beam from operational deflection time history10.1016/j.ijsolstr.2005.07.024 ↗
64. Zhang, Y., Pintea, S.L., and Van Gemert, J.C. (2017, January 21–26). Video acceleration magnification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.61 ↗
65. Measurement of particle accelerations in fully developed turbulence10.1017/S0022112002001842 ↗
66. Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press.
67. UAV dispatch planning for a wireless rechargeable sensor network for bridge monitoring10.1109/TSUSC.2022.3224442 ↗
68. Salimans, T., and Kingma, D.P. (2016, January 5–10). Weight normalization: A simple reparameterization to accelerate training of deep neural networks. Proceedings of the Advances in Neural Information Processing Systems, Barcelona, Spain.
69. Wu, Y., and He, K. (2018, January 8–14). Group normalization. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01261-8_1 ↗
70. Dropout: A simple way to prevent neural networks from overfitting
71. Ghiasi, G., Lin, T.-Y., and Le, Q.V. (2018, January 3–8). Dropblock: A regularization method for convolutional networks. Proceedings of the Advances in Neural Information Processing Systems, Montréal, QC, Canada.
72. Kim, B.J., Choi, H., Jang, H., Lee, D., and Kim, S.W. (August, January 31). How to use dropout correctly on residual networks with batch normalization. Proceedings of the Uncertainty in Artificial Intelligence, Pittsburgh, PA, USA.
73. Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11–13). Deep sparse rectifier neural networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA.
74. Bishop, C.M., and Nasrabadi, N.M. (2006). Pattern Recognition and Machine Learning, Springer.
75. Huber, P.J. (1992). Robust estimation of a location parameter. Breakthroughs in Statistics: Methodology and Distribution, Springer.10.1007/978-1-4612-4380-9_35 ↗
76. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.169 ↗
77. Plateau phenomenon in gradient descent training of RELU networks: Explanation, quantification, and avoidance10.1137/20M1353010 ↗
78. Loshchilov, I., and Hutter, F. (2016). Sgdr: Stochastic gradient descent with warm restarts. arXiv.
79. Liaw, R., Liang, E., Nishihara, R., Moritz, P., Gonzalez, J.E., and Stoica, I. (2018). Tune: A research platform for distributed model selection and training. arXiv.
80. Park, D.S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E.D., and Le, Q.V. (2019). Specaugment: A simple data augmentation method for automatic speech recognition. arXiv.10.21437/Interspeech.2019-2680 ↗
81. Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., and Wilson, A.G. (2018). Averaging weights leads to wider optima and better generalization. arXiv.
82. Probability of detection, localization, and sizing: The evolution of reliability metrics in Structural Health Monitoring10.1177/14759217211060780 ↗
83. Fisher, R.A. (1928). Statistical Methods for Research Workers, Oliver and Boyd.
84. Parrot (2025, November 03). Anafi Ai Technical Specifications. Available online: https://www.parrot.com/en/drones/anafi-ai.
85. DJI (2025, November 03). Air 3 Product Specifications. Available online: https://www.dji.com/air-3/specs.