Magnetic flux leakage detection in non destructive tests performed on ferromagnetic pieces, using signal processing techniques and data mining

Aldair Barajas Aldana, Jaime Parra-Raad, Carlos Julio Arizmendi

Research output: Book / Book Chapter / ReportResearch Bookspeer-review

Abstract

In this paper we propose the use of Support Vector Machine classifiers (SVM) and linear discriminant analysis (LDA) to determine the existence of magnetic flux leakage (MFL) in non-destructive testing (NDT for its acronym in English) performed on ferromagnetic sheets. These signals were provided by the Corporation for Research in Corrosion (CIC) and were acquired on a dyno. The signals are preprocessed to; filter data (ie Wavelet Transform), remove the existing noise (ie thresholding), baseline correction (ie Least Squares Theorem (LST)) and normalize the data (ie First Normal Form). Within the aims of the project are design suitable classifier for each technical proposed for this phenomenon, and a comparison between them to determine which had the best performance.

Original languageEnglish
Title of host publication2014 3rd International Congress of Engineering Mechatronics and Automation, CIIMA 2014 - Conference Proceedings
EditorsAndres G. Marrugo
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479979325
DOIs
StatePublished - 11 Dec 2014
Event2014 3rd International Congress of Engineering Mechatronics and Automation, CIIMA 2014 - Cartagena, Colombia
Duration: 22 Oct 201424 Oct 2014

Publication series

Name2014 3rd International Congress of Engineering Mechatronics and Automation, CIIMA 2014 - Conference Proceedings

Conference

Conference2014 3rd International Congress of Engineering Mechatronics and Automation, CIIMA 2014
Country/TerritoryColombia
CityCartagena
Period22/10/1424/10/14

Keywords

  • LDA
  • MFL
  • NDT
  • SVM

Fingerprint

Dive into the research topics of 'Magnetic flux leakage detection in non destructive tests performed on ferromagnetic pieces, using signal processing techniques and data mining'. Together they form a unique fingerprint.

Cite this