Advanced Deep Learning Methods for Vibration-based Structural Damage Identification

Abstract

Vibration-based damage identification has been a challenging task in structural health monitoring. The main difficulty lies on the reliable correlation between the measured vibration characteristics and the damage states of structures. However, the measured vibration signals are often high-dimensional and noise-contaminated, and sometimes in multiple scales or have multiple physical meanings. In this thesis, we propose advanced deep learning models for effective and efficient structural damage identification.