Eventos Anais de eventos
DINAME 2023
XIX International Symposium on Dynamic Problems of Mechanics
A Deep learning approach for interfacial defect identification based on reduced acoustic scattering models
Submission Author:
Bernardo Junqueira , RJ
Co-Authors:
Bernardo Junqueira, DANIEL CASTELLO, Ricardo Leiderman
Presenter: DANIEL CASTELLO
doi://10.26678/ABCM.DINAME2023.DIN2023-0043
Abstract
An inverse scattering problem methodology for identification and recovery of damage fields in laminated structure interfaces from the reflected field is presented. The training procedure of the deep learning method uses stochastic Gaussian fields as output, which are related to interfacial damage fields of the physical problem. We assume prior knowledge of the material properties of the ultrasound incident field and the elastic layers properties. Furthermore, we model the interfaces using the Quasi-Static-Approximation, a method that generates position dependent interfacial stiffness matrices, composed of set of uncoupled normal and tangential springs. This methodology aims to assist ultrasound tests and may be able to detect and recover defects in real time.
Keywords
Deep learning, Acoustic Scattering, Structural Health Monitoring (SHM), laminated composite, Quasi Static Approximation (QSA)
