September 10, 2025Transportation Research Record Journal of the Transportation Research Board

Signal Reconstruction Method for Lateral Displacement Response of Long-Span Suspension Bridges

View Full Paper

Ask AI

Bookmark

Authors

LLLingfeng Luo LMLibo Meng ZLZhanghao Liu

Discussion

Member takes

Implication

This research utilizes machine learning to improve the predictive accuracy of lateral displacement in suspension bridges, highlighting its advantages over traditional methods.

Key Points

The LSTM model achieves a mean absolute error of only 5 mm, indicating its high accuracy for monitoring suspension bridge deformation.
Machine learning methods, particularly LSTM, substantially outperform linear models in reconstructing lateral displacement signals.
Using wind and temperature data, extreme gradient boosting and LSTM established effective prediction models for bridge displacement.
Nonlinear models like LSTM are designed to manage time-delay effects, improving the fitting of environmental parameters to displacement responses.

Cite This Study

Luo et al. (2025) studied this question.

synapsesocial.com/papers/68c2416eb210217d6479ed5c https://doi.org/10.1177/03611981251342238

View Full Paper

Ask AI

Bookmark

Implication

This research utilizes machine learning to improve the predictive accuracy of lateral displacement in suspension bridges, highlighting its advantages over traditional methods.

Signal Reconstruction Method for Lateral Displacement Response of Long-Span Suspension Bridges

Discussion

Member takes

Implication

Key Points

Cite This Study

Signal Reconstruction Method for Lateral Displacement Response of Long-Span Suspension Bridges

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider