Identificação dos níveis de deterioração em barras de aço submetidas a processo de aceleração de corrosão em corpos de prova de concreto

Abstract

This work investigated the application of machine learning techniques applied to the problem of corrosion in concrete. The degradation of these buildings occurs all over the world and affects the safety of thousands of people, just as there are larger expenses involved to repair these structures. The objective was to diagnose the deterioration level through computer vision. Several techniques and tools, among those selected, were be used to assess and achieve the best classification rates. The standards obtained through scientific results served to identify the different levels of corrosion.