Keywords
noisy time series
diffusion denoising
anomaly detection
latent disentanglement
structural response
early fault warning
Abstract
Bridge structural health monitoring systems collect continuous time series from strain gauges, accelerometers, displacement sensors, cable-force meters, temperature sensors, humidity probes, and wind-speed monitors. These signals are often affected by vehicle load variation, wind disturbance, thermal expansion, sensor aging, electromagnetic interference, and missing transmission segments. Strong noise may hide early structural anomalies or cause false maintenance alarms in conventional reconstruction-based models. This study proposes a latent noise suppression method for structural anomaly detection in bridge monitoring time series. The method uses a conditional diffusion denoising module to recover stable structural response trajectories from noisy observations. A disentangled latent representation is then constructed to separate traffic-load variation, environmental noise, and structural abnormal components. Anomaly scores are calculated using denoised residual energy and component-specific deviation margins. Experiments are conducted on a bridge monitoring dataset containing 42 long-span bridges, 3,860 sensors, 28 monitoring variables, and 1-minute records collected over 24 months. The dataset contains 1.46 billion timestamped measurements and 2,740 engineer-reviewed abnormal episodes, including cable-force drift, abnormal deck displacement, bearing stiffness degradation, local vibration increase, sensor malfunction, and expansion-joint abnormality. The proposed method reduces median early-warning delay from 9.4 days to 2.8 days compared with a wavelet-filtered temporal autoencoder. False maintenance alerts are limited to 1.4 cases per bridge-month. Diffusion denoising improves structural-response signal-to-noise ratio by 8.1 dB, while event-boundary deviation decreases by 19.6 hours. The model completes daily bridge-level assessment in 11.2 minutes. The results show that diffusion-driven denoising and latent disentanglement can improve robust anomaly detection in noisy bridge monitoring time series.
References
Fu, Y., Gui, H., Li, W., & Wang, Z. (2020, August). Virtual Material Modeling and Vibration Reduction Design of Electron Beam Imaging System. In 2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) (pp. 1063-1070). IEEE.
Bodke, K., Bhirud, S., & Sangle, K. K. (2025). Structural health monitoring using image processing and advanced technologies for the identification of deterioration of building structure: A review. Structural Durability & Health Monitoring, 19(6), 1547-1562.
Mardanshahi, A., Sreekumar, A., Yang, X., Barman, S. K., & Chronopoulos, D. (2025). Sensing techniques for structural health monitoring: A state-of-the-art review on performance criteria and new-generation technologies. Sensors, 25(5), 1424.
Zhang, Z., Gao, Y., & Tong, Y. (2026). Semantic-Temporal Graph Learning for Demand Forecasting and Resource Allocation in Public Information Systems. Available at SSRN 6792279.
Saki, M., Keshavarz, R., Franklin, D., Abolhasan, M., Lipman, J., & Shariati, N. (2025). A data-driven review of remote sensing-based data fusion in precision agriculture from foundational to transformer-based techniques. IEEE Access.
Chen, X., Xiao, H., Zeng, Z., Zhang, S., & Xiao, R. (2025). Fine-Grained Multivariate Time Series Anomaly Detection via Causal Inference. Knowledge-Based Systems, 114765.
Liang, R., Feifan, F. N. U., Liang, Y., & Ye, Z. (2025). Emotion-Aware Interface Adaptation in Mobile Applications Based on Color Psychology and Multimodal User State Recognition. Frontiers in Artificial Intelligence Research, 2(1), 51-57.
Ataei, S., Ataei, S. T., Rahmani, Z., Ghajari, E., Mohammadagha, M., Khodadadi, N., & Mosalam, K. M. (2026). Artificial intelligence in bridge structural health monitoring: A comprehensive systematic analysis of methods, models, and applications. Archives of Computational Methods in Engineering, 1-32.
Xu, T., Zhu, W., & Zhang, J. (2026). Stability and Consistency of Explainable Deep Learning Methods in Credit Risk Assessment. Available at SSRN 6893938.
Du, Y., Dong, Y., Liu, Q., & Chen, Z. (2026). Modal Reliability Assessment and Drift Early Warning in Visible-Infrared Target Tracking. Available at SSRN 7132381.
Naqash, T. M., & Alam, M. M. (2025). A state-of-the-art review of wind turbine blades: principles, flow-induced vibrations, failure, maintenance, and vibration suppression techniques. Energies, 18(13), 3319.
Hong, Z., Chen, H., & Xu, T. (2026). Long-Horizon Load Stability Testing and Degradation Forecasting for High-Concurrency Cloud Storage. Available at SSRN 7115859.
Li, J., Zhang, Y., & Gu, Y. (2026). Chain-Hash Audit Framework with Trusted Anchoring for Tamper-Evident Evidence Lifecycle Management.
Zhang, Y., Wang, J., & Gu, W. (2026, February). Research on the Construction and Effectiveness of a Computer-Aided Systematic Training Framework for Wind Farm O&M Quality Amidst High Personnel Turnover. In Proceedings of the 2nd International Conference on Digital Management and Information Technology (pp. 647-651).
Yosefi, A., Mojtahedi, F. F., & Bahrami, M. (2025). Identification of damages in concrete and steel structures: A comprehensive review. Damage Detection and Structural Health Monitoring of Concrete and Masonry Structures: Novel Techniques and Applications, 207-247.
Jeong, E., & Lim, S. C. (2026). A Review of Language-Guided Dexterous Grasping with Human-in-the-Loop Adaptation. Mathematics, 14(15), 2709.
Du, Y., Chen, Z., Liu, Q., & Dong, Y. (2026). Co-identification of Vibration, Structural Looseness, and Surface Damage in Industrial Equipment Operation Videos.
Yin, J., Huang, Y., & Rao, H. (2026). A Study on the Dynamic Evolution of Learning Behavior and Outcome Prediction in Digital Educational Environments. Available at SSRN 6607139.
Zhang, Z. (2026). A Study on Multimodal Product Understanding and Assembly Guidance Optimization in e-commerce for Complex Consumer Goods. Available at SSRN 6734559.
Sonbul, O. S., & Rashid, M. (2025). Bridge structural health monitoring: A multi-dimensional taxonomy and evaluation of anomaly detection methods. Buildings, 15(19), 3603.
Qi, C., & Qiao, X. (2026). Efficient Data Sampling and Feature Selection Algorithms for Scalable Machine Learning Pipelines.
Su, D., & Dong, Y. (2026). Classroom-Based Assessment with Bayesian Learning Analytics for Instructional Decision-Making in ASD Inclusive Education.
Kumar, N., Agrawal, A., Kumar, R., & Badoni, M. (2026). Autoencoder-Based Latent Representation Learning, SoH Estimation, and Anomaly Detection in Electric Vehicle Battery Energy Storage Systems. Vehicles, 8(4), 81.
Xu, T., Zhang, J., & Zhu, W. (2026). Reproducible Modeling Pipelines and Cross-Window Stability in Subprime Auto Loan Credit Risk Assessment. Available at SSRN 6893861.
Xiong, W., & Guo, Y. (2026). A Study on the Phenomenon of Abnormal Load Concentration and Its Cross-system Transmission Characteristics in High-density Building Operations. Available at SSRN 7120661.
Zhang, Y., & Wang, J. (2026, February). Design and Implementation of a Computer-Aided Full Lifecycle Quality Management System for Wind Farms in Upgrades, Renovations, and Subcontractor Supervision. In Proceedings of the 2026 International Conference on Big Data and Informatization Education (pp. 1309-1314).
Sonbul, O. S., & Rashid, M. (2025). Bridge structural health monitoring: A multi-dimensional taxonomy and evaluation of anomaly detection methods. Buildings, 15(19), 3603.
Zhang, Z., Tong, Y., & Gao, Y. (2026). Retrieval-Augmented Generation with Low-Latency Deployment for Vertical Domains Question Answering: A Case Study on Economic Resource Platforms.
Xiong, W., Guo, Y., & Zeng, Y. (2026). A Study on the Energy Efficiency of MEP Systems and Coordinated Dispatch Mechanisms for Multi-energy Systems in High-density Urban Buildings. Available at SSRN 7120518.
Nesackon Abraham, J., Tran, M. Q., Jayaraj, J. S., Matos, J. C., Valluzzi, M. R., & Dang, S. N. (2026). Unsupervised learning-based anomaly detection for bridge structural health monitoring: identifying deviations from normal structural behaviour. Sensors, 26(2), 561.
Khatun, Z. (2025). AI-Driven Predictive Maintenance For Motor Drives In Smart Manufacturing A Scada-To-Edge Deployment Study. American Journal of Interdisciplinary Studies, 6(1), 394-444.
Hong, Z., Chen, H., & Xu, T. (2026). Real-Time Capacity Risk Forecasting for Low-Latency Financial Trading Cloud Platforms. Available at SSRN 7118180.