Damage Detection Of Bridge Structure Based On Variational Auto-encoder

Structural health monitoring(SHM)is a practical tool for assessing the safety and system performance of existing structures.And structural damage identification has become the core of a SHM system.However,how to extract damage-sensitive features from structural response has become a challenging problem.Thus deep learning methods have attracted increasing attention for its ability to effectively extract high-level abstract features form raw data.This paper presents a damage detection method based on Variational Auto-encoder(VAE),one of the most important generative models in unsupervised deep learning.In this paper,VAE is used to process responses of the structure,which reduces the high-dimensional data to low-dimensional feature space,and then restores the original data from the low-dimensional representations.This structure forces the VAE to learn the essential features hidden behind the complex data.Since the VAE is an unsupervised learning model,it is not necessary to classify the original data in advance and directly analyze the measured response data of the structure.Taking advantage of this characteristic,we apply the VAE to damage identification task of a bridge under moving vehicle.Through the numerical simulation,the detection of single damage and double damage in different positions is carried out respectively,and then experiments are carried out to verify.The acceleration response data measured is put into the VAE training,and different VAE network structure models are established through different data types,and finally the damage identification results are obtained.By analyzing the final results,it can be proved that the proposed method can accurately identify the damage in different locations under different moving load mass,moving speeds and damage degrees,which can effectively process the massive data in the SHM system without the lossless data of the original structure,making a good research value for the application of the actual project of SHM.