Sound Damage Detection of Bridge Expansion Joints Using a Support Vector Data Description.

Sensors (Basel)

School of Civil Engineering, Xiangtan University, Xiangtan 411105, China.

Published: March 2023

A novel method is proposed for the damage identification of modal bridge expansion joints (MBEJs) based on sound signals. Two modal bridge expansion joint specimens were fabricated to simulate healthy and damaged states. A microphone was used to collect the impact signals from different specimens. The wavelet packet energy ratio of the sound signal was used to identify the difference in specimen state. Firstly, the wavelet packet energy ratio was used to establish the feature vectors, which were reduced dimensionality using principal component analysis. Subsequently, a support vector data description model was established to detect the difference in the signals. The identification effects of three parameter optimization methods (particle swarm optimization, genetic algorithm optimization, and Bayesian optimization) were compared. The results showed that the wavelet packet energy ratio of sound signals could effectively distinguish the state of the support bar. The support vector data description of Bayesian optimization worked best, and the proposed method could successfully detect damage to the support bar of MBEJs with an accuracy of 99%.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10099060PMC
http://dx.doi.org/10.3390/s23073564DOI Listing

Publication Analysis

Top Keywords

bridge expansion
12
support vector
12
vector data
12
data description
12
wavelet packet
12
packet energy
12
energy ratio
12
expansion joints
8
modal bridge
8
sound signals
8

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!