Title : ( Design of an expert system based on neuro-fuzzy inference analyzer for on-line microstructural characterization using magnetic NDT method )
Authors: Sadegh Ghanei , H. Vafaeenezhad , Mehrdad Kashefi Torbati , A.R. Eivani , Mohammad Mazinani ,Access to full-text not allowed by authors
Abstract
Tracing microstructural evolution has a significant importance and priority in manufacturing lines of dual-phase steels. In this paper, an artificial intelligence method is presented for on-line microstructural characterization of dual-phase steels. A new method for microstructure characterization based on the theory of magnetic Barkhausen noise non destructive testing method is introduced using adaptive neuro- fuzzy inference system(ANFIS). In order to predict the accurate martensite volume fraction of dual-phase steels while eliminating the effect and interference of frequency on the magnetic Barkhausen noise outputs, the magnetic responses were fed into the ANFIS structure in terms of position, height and width of the Barkhausen profiles. The results showed that ANFIS approach has the potential to detect and characterize microstructural evolution while the considerable effect of the frequency on magnetic outputs is overlooked. In fact, implementing multiple outputs simultaneously enables ANFIS to approach to the accurate results using only height, position and width of the magnetic Barkhausen noise peaks without knowing the value of the used frequency.
Keywords
, Adaptive neuro-fuzzy inference system, Dual-phase steels, Magnetic Barkhausen noise, Microstructure, Non destructive testing@article{paperid:1045285,
author = {Ghanei, Sadegh and H. Vafaeenezhad and Kashefi Torbati, Mehrdad and A.R. Eivani and Mazinani, Mohammad},
title = {Design of an expert system based on neuro-fuzzy inference analyzer for on-line microstructural characterization using magnetic NDT method},
journal = {Journal of Magnetism and Magnetic Materials},
year = {2015},
volume = {379},
number = {1},
month = {January},
issn = {0304-8853},
pages = {131--136},
numpages = {5},
keywords = {Adaptive neuro-fuzzy inference system; Dual-phase steels; Magnetic Barkhausen noise; Microstructure; Non destructive testing},
}
%0 Journal Article
%T Design of an expert system based on neuro-fuzzy inference analyzer for on-line microstructural characterization using magnetic NDT method
%A Ghanei, Sadegh
%A H. Vafaeenezhad
%A Kashefi Torbati, Mehrdad
%A A.R. Eivani
%A Mazinani, Mohammad
%J Journal of Magnetism and Magnetic Materials
%@ 0304-8853
%D 2015