Details
Original language | English |
---|---|
Article number | 105679 |
Number of pages | 18 |
Journal | Journal of Wind Engineering and Industrial Aerodynamics |
Volume | 247 |
Early online date | 2 Mar 2024 |
Publication status | Published - Apr 2024 |
Abstract
Monitoring the wind-induced lateral displacement (WLD) of the bridge deck is crucial for structural health monitoring (SHM) of suspension bridges. An accurate WLD prediction model can aid the bridge SHM systems in abnormal data detection and reconstruction, structural response estimation under specific wind events, and structural condition assessment. However, WLD prediction faces challenges due to stochastic wind action and complex aerodynamic effects acting on the bridge deck. To address this, a deep learning-based framework was proposed for predicting the WLD response of the suspension bridge deck. This framework decomposed the WLD response into two components, namely the quasi-static and the dynamic one. Two separate deep-learning tasks were employed to predict these components using the lateral wind speed as input. In Task 1, a recurrent neural network (RNN) based on the gated recurrent unit (GRU) was built, whereas a fully convolutional neural network (CNN) based on U-Net was built in Task 2. Novel loss functions tailored to each task were established to facilitate accurate predictions. Measured data from the SHM system of the Jiangyin Yangtze River Bridge, China, was used as a case study to verify the proposed predictive framework's feasibility and high accuracy. The extreme value-weighted loss function in Task 1 enhanced the prediction accuracy for the extreme quasi-static WLD, while the time-frequency cross-domain loss functions in Task 2 effectively integrated the prediction accuracies in both time and frequency domains for the dynamic component of WLD. However, trade-offs were identified between the prediction errors of extreme and non-extreme values, as well as between the time- and frequency-domain prediction accuracies.
Keywords
- Deep learning, Extreme values, Structural health monitoring, Suspension bridge deck, U-net, Wind-induced lateral displacement
ASJC Scopus subject areas
- Engineering(all)
- Civil and Structural Engineering
- Energy(all)
- Renewable Energy, Sustainability and the Environment
- Engineering(all)
- Mechanical Engineering
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Journal of Wind Engineering and Industrial Aerodynamics, Vol. 247, 105679, 04.2024.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Deep learning-based prediction of wind-induced lateral displacement response of suspension bridge decks for structural health monitoring
AU - Wang, Zhi wei
AU - Lu, Xiao fan
AU - Zhang, Wen ming
AU - Fragkoulis, Vasileios C.
AU - Zhang, Yu feng
AU - Beer, Michael
N1 - Funding Information: The authors gratefully acknowledge the support by the National Key R&D Program of China (No. 2022YFB3706703 ), the National Natural Science Foundation of China under Grant 52078134 , the Postgraduate Research & Practice Innovation Program of Jiangsu Province ( KYCX210118 ), and the Scientific Research Foundation of Graduate School of Southeast University ( YBPY2129 ).
PY - 2024/4
Y1 - 2024/4
N2 - Monitoring the wind-induced lateral displacement (WLD) of the bridge deck is crucial for structural health monitoring (SHM) of suspension bridges. An accurate WLD prediction model can aid the bridge SHM systems in abnormal data detection and reconstruction, structural response estimation under specific wind events, and structural condition assessment. However, WLD prediction faces challenges due to stochastic wind action and complex aerodynamic effects acting on the bridge deck. To address this, a deep learning-based framework was proposed for predicting the WLD response of the suspension bridge deck. This framework decomposed the WLD response into two components, namely the quasi-static and the dynamic one. Two separate deep-learning tasks were employed to predict these components using the lateral wind speed as input. In Task 1, a recurrent neural network (RNN) based on the gated recurrent unit (GRU) was built, whereas a fully convolutional neural network (CNN) based on U-Net was built in Task 2. Novel loss functions tailored to each task were established to facilitate accurate predictions. Measured data from the SHM system of the Jiangyin Yangtze River Bridge, China, was used as a case study to verify the proposed predictive framework's feasibility and high accuracy. The extreme value-weighted loss function in Task 1 enhanced the prediction accuracy for the extreme quasi-static WLD, while the time-frequency cross-domain loss functions in Task 2 effectively integrated the prediction accuracies in both time and frequency domains for the dynamic component of WLD. However, trade-offs were identified between the prediction errors of extreme and non-extreme values, as well as between the time- and frequency-domain prediction accuracies.
AB - Monitoring the wind-induced lateral displacement (WLD) of the bridge deck is crucial for structural health monitoring (SHM) of suspension bridges. An accurate WLD prediction model can aid the bridge SHM systems in abnormal data detection and reconstruction, structural response estimation under specific wind events, and structural condition assessment. However, WLD prediction faces challenges due to stochastic wind action and complex aerodynamic effects acting on the bridge deck. To address this, a deep learning-based framework was proposed for predicting the WLD response of the suspension bridge deck. This framework decomposed the WLD response into two components, namely the quasi-static and the dynamic one. Two separate deep-learning tasks were employed to predict these components using the lateral wind speed as input. In Task 1, a recurrent neural network (RNN) based on the gated recurrent unit (GRU) was built, whereas a fully convolutional neural network (CNN) based on U-Net was built in Task 2. Novel loss functions tailored to each task were established to facilitate accurate predictions. Measured data from the SHM system of the Jiangyin Yangtze River Bridge, China, was used as a case study to verify the proposed predictive framework's feasibility and high accuracy. The extreme value-weighted loss function in Task 1 enhanced the prediction accuracy for the extreme quasi-static WLD, while the time-frequency cross-domain loss functions in Task 2 effectively integrated the prediction accuracies in both time and frequency domains for the dynamic component of WLD. However, trade-offs were identified between the prediction errors of extreme and non-extreme values, as well as between the time- and frequency-domain prediction accuracies.
KW - Deep learning
KW - Extreme values
KW - Structural health monitoring
KW - Suspension bridge deck
KW - U-net
KW - Wind-induced lateral displacement
UR - http://www.scopus.com/inward/record.url?scp=85186503997&partnerID=8YFLogxK
U2 - 10.1016/j.jweia.2024.105679
DO - 10.1016/j.jweia.2024.105679
M3 - Article
AN - SCOPUS:85186503997
VL - 247
JO - Journal of Wind Engineering and Industrial Aerodynamics
JF - Journal of Wind Engineering and Industrial Aerodynamics
SN - 0167-6105
M1 - 105679
ER -