Structural change identification using machine learning techniques

• Grant number: 17/19028-3
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: December 01, 2017
• End date: November 30, 2018
• Field of knowledge: Engineering - Mechanical Engineering - Mechanics of Solids
• Principal Investigator: Paulo José Paupitz Gonçalves
• Grantee: Nickolas Castro Bernardini
• Host Institution: Faculdade de Engenharia (FE). Universidade Estadual Paulista (UNESP). Campus de Bauru. Bauru , SP, Brazil

Abstract

The structural health condition monitoring in mechanical systems is of great importance in the engineering field. In the aeronautical engineering area it is essential to evaluate the dynamic behavior history of the structure in order to predict failures and catastrophes. In this area, extensive fatigue tests are often done to predict how many hours an aircraft can fly before passing through inspection and maintenance processes. These tests, however, represent the average behavior of an aircraft, since they are done in a controlled environment in test body. In this context, monitoring each aircraft would be safer, but more costly process for operators of such equipment. In this context, this scientific initiation project aims to evaluate machine learning techniques to identify when a mechanical structure undergoes changes in its parameters. (AU)