Pengembangan Sistem Deteksi Dini Kerusakan Jembatan Menggunakan Deep Learning Berbasis Citra dan Sensor Getaran
DOI:
https://doi.org/10.69503/ije.v6i2.1628Keywords:
Deteksi Dini Kerusakan Jembatan, Deep Learning Multimodal, Citra Jembatan, Sinyal Getaran, Structural Health MonitoringAbstract
Kerusakan jembatan menjadi isu kritis dalam sistem transportasi karena berdampak langsung pada keselamatan dan keberlanjutan infrastruktur. Penelitian ini bertujuan mengembangkan sistem deteksi dini kerusakan jembatan berbasis deep learning multimodal yang mengintegrasikan data citra dan sinyal getaran dalam satu arsitektur terpadu. Pendekatan ini mengatasi keterbatasan metode single modality dalam Structural Health Monitoring, baik berbasis inspeksi visual maupun analisis getaran. Metode yang digunakan adalah kuantitatif eksperimental dengan pengolahan data citra kerusakan dan sinyal getaran yang ditransformasikan ke domain time-frequency. Model dirancang menggunakan arsitektur dua cabang untuk mengekstraksi fitur dari masing-masing modalitas, kemudian digabungkan melalui feature fusion dan attention layer guna meningkatkan akurasi klasifikasi. Hasil menunjukkan bahwa integrasi multimodal meningkatkan performa deteksi dibandingkan pendekatan tunggal. Model mampu mengenali kerusakan permukaan dan karakteristik dinamis struktur secara simultan, serta lebih stabil terhadap noise dan variasi data. Sistem ini juga berpotensi diterapkan secara real-time untuk mendukung pemeliharaan jembatan berbasis data. Penelitian ini berkontribusi pada pengembangan Structural Health Monitoring modern yang lebih adaptif, akurat, dan komprehensif melalui integrasi kecerdasan buatan dan sensor multimodal.
References
Al-Qudah, S., Bai, X., Yang, M., & Gao, Z. (2025). Deep learning-based structural health monitoring through the infusion of optical photos and vibration data. Advances in Structural Engineering, 28(3), 532-552. https://doi.org/10.1177/13694332241289173
Casas, J. R., & Moughty, J. J. (2017). Bridge damage detection based on vibration data: Past and new developments. Frontiers in Built Environment, 3, 4. https://doi.org/10.3389/fbuil.2017.00004
Cho, S., & Kim, B. H. (2021). Image-driven bridge inspection framework using deep learning and image registration. IABSE Conference – Risk Intelligence of Infrastructures, 269-271. https://doi.org/10.2749/SEOUL.2020.269
Corbally, R., & Malekjafarian, A. (2024). A deep‐learning framework for classifying the type, location, and severity of bridge damage using drive‐by measurements. Computer‐Aided Civil and Infrastructure Engineering, 39(6), 852-871. https://doi.org/10.1111/mice.13104
Cuasay, R. M., Tan, N. G., Torres, J. N., & Estores, G. (2024). A faster region-based convolutional neural network approach to automated structural damage recognition of reinforced concrete bridge structures. AIP Conference Proceedings, 3034(1), 050008. https://doi.org/10.1063/5.0194714
Kruachottikul, P., Cooharojananone, N., Phanomchoeng, G., Chavarnakul, T., Kovitanggoon, K., & Trakulwaranont, D. (2021). Deep learning-based visual defect-inspection system for reinforced concrete bridge substructure: a case of Thailand’s department of highways. Journal of Civil Structural Health Monitoring, 11(4), 949-965. https://doi.org/10.1007/S13349-021-00490-Z
Liang, X. (2019). Image‐based post‐disaster inspection of reinforced concrete bridge systems using deep learning with Bayesian optimization. Computer‐Aided Civil and Infrastructure Engineering, 34(5), 415-430. https://doi.org/10.1111/MICE.12425
Liu, J., Xu, S., Bergés, M., & Noh, H. Y. (2023). HierMUD: Hierarchical multi-task unsupervised domain adaptation between bridges for drive-by damage diagnosis. Structural Health Monitoring, 22(3), 1941-1968. https://doi.org/10.1177/14759217221081159
Lu, N., Cui, J., Zeng, W., Xiao, X., & Luo, Y. (2025). Bridge damage detection framework based on multi-scale feature fusion and multi-attention enhanced residual network. Structural Health Monitoring, 14759217251389151. https://doi.org/10.1177/14759217251389151
Monteiro, D. K., Cardoso, J. P., & Miguel, L. F. F., Tavares, A. R., (2025). Bridge health monitoring using deep learning based on sinusoidal gratings. Structural Health Monitoring: An International Journal. 14759217251389099. https://doi.org/10.1177/14759217251389099
Nguyen-Tran, H., Bui-Ngoc, D., Pham-Tuan, D., Ngoc-Nguyen, L., Tran-Ngoc, H., Bui-Tien, T. (2024). Damage Detection in Structural Health Monitoring Using a One-Dimensional Convolutional Neural Network—The Z24 Bridge Case Study. International Conference on Sustainability in Civil Engineering. ICSCE. 344. https://doi.org/10.1007/978-981-99-2345-8_70
Saafi, M., Robinson, N., & Lazare, S. (2006). Durability Monitoring and Damage Detection in Civil Infrastructure Using Nanotechnology/MEMS-based Devices/Überwachung der Dauerhaftigkeit und Aufspüren von Schäden mit Hilfe der Nanotechnologie und auf MEMS basierten Geräten im Brücken-und Hochbau. Restoration of Buildings and Monuments, 12(5-6), 41-54. https://doi.org/10.1515/RBM-2006-6079
Sajedi, S. O., & Liang, X. (2022). Trident: A deep learning framework for high-resolution bridge vibration monitoring. Applied Sciences, 12(21), 10999. https://doi.org/10.3390/app122110999
Song, X., Dyogi, J., & Cho, C. (2022). Vibration-based bridge damage detection using image-based pre-trained deep learning network. SMASIS Smart Materials, Adaptive Structures and Intelligent Systems, 86274, V001T05A001. https://doi.org/10.1115/smasis2022-88421
Talaei, S., Zhu, X., Li, J., Yu, Y., & Chan, T. H. (2023). Transfer learning based bridge damage detection: Leveraging time-frequency features. Elsevier, 57,105052. https://doi.org/10.1016/j.istruc.2023.105052
Wang, X., Li, W., Ma, M., et al. (2024). Bridge damage identification based on encoded images and convolutional neural network. Buildings, 14(10), 3104. https://doi.org/10.3390/buildings14103104
Xiao, P. (2022). Three-dimensional vision-based structural damage detection and loss estimation–towards more rapid and comprehensive assessment. (Doctoral dissertation, University of British Columbia). https://doi.org/10.14288/1.0422384
Yamane, T., Chun, P. J., & Honda, R. (2024). Detecting and localising damage based on image recognition and structure from motion, and reflecting it in a 3D bridge model. Structure and Infrastructure Engineering, 20(4), 594-606. https://doi.org/10.1080/15732479.2022.2131845
Yin, C. (2025). Multimodal Machine Learning for Structural Damage Detection Integrating Visual and Vibration Data. (Doctoral dissertation, Carnegie Mellon University). https://doi.org/10.1184/r1/29450093
Zhang, C., Chang, C. C., & Jamshidi, M. (2018). Bridge damage detection using a single-stage detector and field inspection images. ArXiv, 1812, 10590. https://doi.org/10.48550/arXiv.1812.10590
