Improving Structural Damage Detection in Bridges
Author Information
Author(s): Lu Naiwei, Liu Yiru, Cui Jian, Xiao Xiangyuan, Luo Yuan, Noori Mohammad
Primary Institution: School of Civil Engineering, Changsha University of Science and Technology, Changsha, China
Hypothesis
Can a time-frequency-based data-driven approach enhance the identification of structural damage in cable-stayed bridges?
Conclusion
The study demonstrates that the proposed method effectively identifies cable damage in a cable-stayed bridge model, achieving high accuracy even under noisy conditions.
Supporting Evidence
- The ResNet model achieved the highest test accuracy of 92.75% for damage identification.
- As the Signal-to-Noise Ratio (SNR) decreased from 20 dB to 2.5 dB, ResNet's prediction accuracy declined from 86.63% to 62.5%.
- The method retains the time-dependent and nonlinear characteristics of the time series in the resulting images.
Takeaway
This study shows a new way to find damage in bridges using special images made from vibration data, which helps us understand when a bridge is hurt.
Methodology
The study used a time-frequency-based approach to convert vibration data into images, which were then analyzed using convolutional neural networks (CNNs) for damage identification.
Limitations
The study focuses on a cable structure without accounting for the complexity of real bridge environments.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website