Eddy Currents Signatures Classification by Using Time Series: a System Modeling Approach

Abstract

Non destructive testing methods are often used in order to detect and classify structural flaws. The detection of structural flaws is useful for maintenance. In this paper we propose to classify flaws in ferromagnetic materials by measuring Eddy currents. Our approach consists of two steps. First, we use a system identification algorithm to find a dynamical system which describes the data. Then, we use the parameters of this dynamical system as a feature vector and we use support vector machines in order to classify the various cracks. We test our method on a well-known benchmark.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 23, 2014
Accession Number
AD1002855

Entities

People

  • Blaise Guepie
  • Mihály Petreczky
  • Stephane Lecoeuche

Tags

Communities of Interest

  • Advanced Electronics
  • Sensors
  • Weapons Technologies

DTIC Thesaurus Topics

  • Acoustic Emissions
  • Algorithms
  • Data Sets
  • Databases
  • Detection
  • Eddy Currents
  • Factor Analysis
  • Feature Extraction
  • Ferromagnetic Materials
  • Identification
  • Information Science
  • Machine Learning
  • Materials
  • Supervised Machine Learning
  • Test And Evaluation
  • Test Methods
  • Trajectories

Fields of Study

  • Computer science

Readers

  • Computational Fluid Dynamics (CFD)
  • Materials Science (Mechanical Engineering).
  • Systems Analysis and Design

Technology Areas

  • AI & ML