No abstract

No abstract

Due to the threat of natural disasters such as earthquakes and floods, as well as the influence of the aging of civil engineering structures, the safety of long-term service structures cannot be guaranteed. In order to monitor the working status of structural engineering in real time and capture its damage information, a multi-scale damage identification method based on wireless sensor network is proposed in this paper. Autocorrelation analysis of time series data is carried out through nonlinear autoregressive network with exogenous inputs (NARX) neural network, the overall health of the structure is initially diagnosed locally at the node, and the sensor nodes are divided into different monitoring subnetworks according to the spatial location when the structure is damaged, and the empirical mode decomposition (EMD) method is used. The time-series data were preprocessed to further locate and quantify damage. Experiments show that the method can accurately identify and locate structural damage, and can visually represent the amount of structural damage.