A dynamic early-warning method for bridge structural safety based on data reconstruction and depth prediction

• Published in: PloS one Vol. 20; no. 6; p. e0324816
• Main Authors: Men, Yanqing, Li, Hu, Liu, Fengzhou, Huang, Yongliang, Gao, Mingxin, Wang, Xiaohui, Xie, Hao, Cao, Jianxin
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 03.06.2025; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Big Data; Bridge failures; Bridges; China; Computer and Information Sciences; Decomposition; Decoupling; Deep learning; Early warning systems; Engineering and Technology; Evaluation; False alarms; Forecasts and trends; Long short-term memory; Machine learning; Methods; Monitoring; Neural networks; Physical Sciences; Prediction models; Real time; Reconstruction; Research and Analysis Methods; Safety; Safety and security measures; Singular value decomposition; Structural engineering; Structural response; Structural safety; Temperature; Time series; Warning systems; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0324816

The structural response of bridges involves a complex interplay of various coupled effects, rendering the identification of long-term variation trends inherently challenging. Consequently, effectively detecting and alerting abnormal monitoring data for bridge structures under complex coupled loads remains a significant difficulty. To address this issue, this study proposes a dynamic early-warning method for bridge structural safety, leveraging data reconstruction and deep learning-based prediction. First, the singular value decomposition (SVD) algorithm is employed to decompose and reconstruct the monitoring data based on the contribution rate of influencing factors, thereby decoupling the data from various coupled effects. Second, a deep learning architecture utilizing a long short-term memory (LSTM) network is applied to establish a prediction model for each group of decomposed monitoring data, significantly enhancing prediction accuracy. Building on this foundation, the dynamic early-warning system for bridge structural safety is realized by integrating anomaly diagnosis theory with both predicted and measured data. A validation case using measured strain data demonstrates that the proposed method accurately predicts bridge strain data and calculates real-time adaptive thresholds, enabling real-time detection of anomalous monitoring data.