Eventos Anais de eventos
COBEM 2023
27th International Congress of Mechanical Engineering
A FRAMEWORK OF CANTILEVER BEAM FOR DAMAGE DETECTION USING ARTIFICIAL NEURAL NETWORKS
Submission Author:
Amanda Aryda Silva Rodrigues de Sousa , DF
Co-Authors:
Amanda Aryda Silva Rodrigues de Sousa, Marcela Machado
Presenter: Amanda Aryda Silva Rodrigues de Sousa
doi://10.26678/ABCM.COBEM2023.COB2023-1541
Abstract
Damage can be considered any change in the material, geometry, or boundary condition of a structure that creates undesirable displacements and vibrations. Information and statistical analysis of such structure allow us to determine the current structural condition for short or long periods. Damage in aerospace, civil, and mechanical systems can compromise their functioning and generate future risks. In this context, early detection of damage and periodic assessment of structural integrity is necessary for the system to operate correctly and for damage to be identified, monitored, and corrected. Therefore, many Structural Health Monitoring (SHM) techniques have been used to identify and validate damage offline, near real-time, and online. These techniques use technologies that combine modern sensors and intelligent computational algorithms. Therefore, one of the techniques that have gained great prominence in recent years is using SHM with machine learning algorithms. that provide the tools needed to enhance the capabilities of SHM systems. This study aims to identify damage in a cantilever beam using an Artificial Neural Network (ANN). The results demonstrate that the ANN algorithm effectively detected damage in noise-free data compared to traditional algorithms such as SVM and Naive Bayes.
Keywords
Structural Health Monitoring, Damage Detection, Artificial neural networks, vibration signal, machine learning
