NEURO-FUZZY SYSTEM APPLIED TO RECOGNIZE AND ASSESSING THE DAMAGE IN CARBON STEEL SUPPORTED BY DESCRIPTIVE STATISTICS

Abstract

This paper describes the development of an intelligent integrated system able to estimate the damage to carbon steel, the system, comprises an fuzzy logic architecture developed from descriptive statistics and an artificial neural network multilayer perceptron applied in metallographic pattern recognition with digital image processing is also carried just characterizing textures metallographic images using statistical first, second and third order. The studied patterns are from the microstructure of carbon steel SA 210 Grade A-1. The purpose is to estimate the damage present in the material from the determination of the physical state of the material. Steel samples were tested in actual conditions, such as the steam and water at high temperature suffering deterioration not easily detectable by standard metallographic means. Studied patterns in the microstructure of the material were: pearlite lamellar, spheronization and graphitization. The microstructure was revealed from images obtained by an inverted metallographic microscope (Olympus - GX71) in the Testing Laboratory Equipment and Materials of the Federal Electricity Commission in Mexico. (LAPEM - CFE). The results showed that the damage estimation and pattern recognition in the material were correctly predicted with the developed system compared to the human expert. Furthermore, the analysis can be performed in less time and cost.