Estimación Del Deterioro En El Acero Al Carbón SA 210 Grado A-1 Mediante Un Sistema Neuronal-Difuso Y Procesamiento Digital De Imágenes (Condition Estimation Of Carbon Steel Using A Neuro-Fuzzy System And Image Processing)

Edgar Augusto Ruelas Santoyo (edruelas@itesi.edu.mx)1, José Antonio Vázquez López (antonio.vazquez@itcelaya.edu.mx)2, Javier Yáńez Mendiola (jyanez@ciatec.mx)1, Ismael López Juárez (ismael.lopez@cinvestav.edu.mx)3, Carlos Fernando Bravo Barrera (fernando.bravo01@cfe.gob.mx)4


1Centro de Innovación en Tecnologías Competitivas (CIATEC)
2Instituto Tecnológico de Celaya
3Centro de Investigación y de Estudios Avanzados del IPN (CINVESTAV)
4Laboratorio de Pruebas de Equipo y Materiales (LAPEM)

This paper appears in: Revista IEEE América Latina

Publication Date: July 2015
Volume: 13,   Issue: 7 
ISSN: 1548-0992


Abstract:
This paper describes the development of an intelligent integrated system comprised of a fuzzy logic architecture developed from descriptive statistics and an artificial neural network multilayer perceptron applied in pattern recognition with digital image processing. 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.

Index Terms:
Artificial neural network, digital image processing, fuzzy logic, material defects   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (872)]