Artificial Intelligence methods applied to the damage detection in beams

Resumo

Structural health monitoring (SHM) has become increasingly important in the field of civil engineer-
ing. The objective of this paper is on the application of Artificial Intelligence Methods in the SHM field. The

formulation uses modal parameters of a structure to detect damage related to the reduction of stiffness of a section.
The databases for training and validating the AI methods were generated in a structured and automatic way by
an algorithm developed in Python programming language within the finite element software Abaqus. The modal

parameters analyzed were the first five natural frequencies of a beam. An exploratory analysis was performed us-
ing other characteristics such as: length of the beam, failure severity, material, boundary conditions, cross section

and others. It was possible to evaluate the performance of the AI methods on the proposed problem. Finally, a
parametric comparison was made between the different Artificial Intelligence methods.