A Time–Frequency-Based Data-Driven Approach for Structural Damage Identification and Its Application to a Cable-Stayed Bridge Specimen
2024

Improving Structural Damage Detection in Bridges

Sample size: 1152 publication Evidence: high

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)

10.3390/s24248007

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication