Please use this identifier to cite or link to this item:
Author(s): Edgard M. Silva
Leandro B. Marinho
Pedro P. Rebouças Filho
João P. Leite
Josinaldo P. Leite
Walter M. L. Fialho
Victor Hugo C. de Albuquerque
João Manuel R. S. Tavares
Title: Classification of induced magnetic field signals for the microstructural characterization of sigma phase in duplex stainless steels
Issue Date: 2016-07-14
Abstract: Duplex stainless steels present excellent mechanical and corrosion resistance properties.However, when heat treated at temperatures above 600 ºC, the undesirable tertiary sigma phaseis formed. This phase presents high hardness, around 900 HV, and it is rich in chromium, thematerial toughness being compromised when the amount of this phase is not less than 4%. Thiswork aimed to develop a solution for the detection of this phase in duplex stainless steels throughthe computational classification of induced magnetic field signals. The proposed solution is based onan Optimum Path Forest classifier, which was revealed to be more robust and effective than Bayes,Artificial Neural Network and Support Vector Machine based classifiers. The induced magneticfield was produced by the interaction between an applied external field and the microstructure.Samples of the 2205 duplex stainless steel were thermal aged in order to obtain different amounts ofsigma phases (up to 18% in content). The obtained classification results were compared against theones obtained by Charpy impact energy test, amount of sigma phase, and analysis of the fracturesurface by scanning electron microscopy and X-ray diffraction. The proposed solution achieved aclassification accuracy superior to 95% and was revealed to be robust to signal noise, being thereforea valid testing tool to be used in this domain.
Document Type: Artigo em Revista Científica Internacional
Rights: openAccess
Appears in Collections:FEUP - Artigo em Revista Científica Internacional

Files in This Item:
File Description SizeFormat 
136102.pdfPaper7.15 MBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons