Seismic Event Detection using Bridge Monitoring Data Based on Multi-input Deep Neural Networks

DOI

10.2991/978-94-6463-728-1_70How to use a DOI?

Keywords

Structural health monitoring; Seismic event detection; Large-span bridges; Information fusion; Data anomaly detection

Abstract

Seismic events pose a significant threat to the safety of bridge structures, potentially causing extensive structural damage or collapse. Structural health monitoring (SHM) systems for large-span bridges capture structural response information and generate substantial data but face issues like sensor faults, environmental noise, and data transmission problems that can degrade data quality and hinder accurate seismic response identification. This paper proposes a multi-input deep learning method for seismic event detection, which exploits the correlation between sensors in different directions, especially in the case of sensor failure, to improve detection accuracy. The proposed approach creates an acceleration database, incorporating time-domain, frequency-domain, and probability density curve images as inputs for model training aimed at anomaly classification of sensor data. Then, the multi-input model integrates data from sensors in various orientations, significantly improving the identification rate of seismic events. Meanwhile, a global voting strategy is implemented to optimize the decision-making process during the prediction phase. When applied to actual seismic response data from a cable-stayed bridge, the experimental results confirm the effectiveness of the proposed method in accurately detecting sensor anomalies and identifying seismic events in bridges.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Hao Fang
AU  - Yao Chen
AU  - Zhou Su
AU  - Ying He
PY  - 2025
DA  - 2025/05/19
TI  - Seismic Event Detection using Bridge Monitoring Data Based on Multi-input Deep Neural Networks
BT  - Proceedings of the 3rd International Conference on Green Building, Civil Engineering and Smart City (GBCESC 2024)
PB  - Atlantis Press
SP  - 745
EP  - 758
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-728-1_70
DO  - 10.2991/978-94-6463-728-1_70
ID  - Fang2025
ER  -