Detection and characterization of defects using GMR probes and artificial neural networks

摘要: This work presents an eddy-current testing system based on a giant magnetoresistive (GMR) sensing device. Non-destructive tests in aluminum plates are applied order to extract information about possible defects: cracks, holes and other mechanical damages. Eddy-current (ECT) major benefits such as low cost, high checking speed, robustness sensitivity large classes of defects. Coil architecture probes or coil-magnetoresistive usually used ECT. In our application the GMR sensor is detect magnetic field component parallel plate surface, when excitation perpendicular imposed. A neural network processing architecture, including multilayer perceptron competitive network, classify defects using output amplitude probe (ECP) its operation frequency. The crack detection, classification estimation geometrical characteristics, for different defects, described paper.