Detection of Multiple Structural Damages Using Ultrasonic Guided Waves

Guided waves have been widely used for health monitoring of thin plate-like structures. In the literature, many algorithms have been developed to detect, to localize and to assess the severity of damage in thin structures using Guided waves. However, the majority of these algorithms are developed based on the assumption that only a single defect is present in the structure. In the present study, the effect of multiple defects on guide wave propagation modes is investigated. The interaction of guided wave modes with multiple defects is studied through numerical simulations. A series of numerical case studies are performed to identify the unique features specific to multiple defects. The identified unique features are used for training neural networks, which are further used for the prediction of multiple damages, their width and location. The results of the present study indicate the developed algorithm can detect and localize multiple defects accurately.