Detection and characterization of defects using GMR probes and artificial neural networks
Postolache, O.
;
Ramos, H.
;
Ribeiro, A. L.
Computer Standards and Interfaces Vol. 33, Nº 2011, pp. 191 - 200, June, 2010.
ISSN (print): 0920-5489
ISSN (online):
Scimago Journal Ranking: 0,50 (in 2010)
Digital Object Identifier: 10.1016/j.csi.2010.06.011
Abstract
This work presents an eddy-current testing system based on a giant magnetoresistive (GMR) sensing device. Nondestructive tests in aluminumplates are applied in order to extract information about possible defects: cracks, holes and other mechanical damages. Eddy-current testing (ECT) presentsmajor benefits such as low cost, high checking speed, robustness and high sensitivity to large classes of defects. Coil based architecture probes or coil-magnetoresistive probes are usually used in ECT. In our application theGMRsensor is used to detect a magnetic field component parallel to a plate surface,whenan excitationfield perpendicular to the plate is imposed.Aneuralnetwork processing architecture, including amultilayer perceptron and a competitive neural network, is used to classify defects using the output amplitude of the eddy-current probe (ECP) and its operation frequency. The crack detection, classification and estimation of the geometrical characteristics, for different classes of defects, are described in the paper.