Abstract

The application of distributed fiber sensing technology in civil engineering has been developed to obtain more accurate and reliable information for structural health monitoring (SHM). With this sensing technique, high-density strain data are provided to benefit the stability and robustness in a closed-loop damage detection method which has not yet been investigated. To address this concern, a two-stage approach for structural damage detection combining a modal strain energy-based index (MSEBI) method with a hybrid artificial neural network (ANN) and particle swarm optimization (PSO) algorithm is proposed. In this study, the fully distributed strain measurement is taken advantage of, and a strain-based, closed-loop system with multiple gains aggregated for damage sensitivity enhancement is established, by which high-precision damage location and quantification can be realized through the proposed two-stage method. For the first step, the closed-loop strain mode shapes are used to construct the MSEBI for damage localization. For the second step, we adopt the PSO algorithm to train the parameters (weights and biases) of the neural network in order to reduce the difference between the real and expected outputs and then use the trained network for quantifying the damage extent. Furthermore, validation is completed by contemplating a two-span, bridge-like structure.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call