Metal Plate Thickness Classification In Eddy Current Testing Using Support Vector Machine

Tiago Rocha, Dário Pasadas, Helena G. Ramos, Artur L. Ribeiro
Abstract:
Eddy current testing (ECT) is a non destructive technique that can be used in the measurement of conductive material thickness. In this work a machine learning algorithm (support vector machine - SVM) is applied to ECT data, obtained for three different types of conductive plates, and classifies their thicknesses. Eddy currents are induced by imposing a voltage step in an excitation coil, while a giant magnetoresistor (GMR) magnetic sensor measures the transitory magnetic field intensity in the sample vicinity. An experimental validation procedure, including machine training with linear and exponential kernels and classification errors, was made for each metal type with sets of sample thicknesses up to 7.5 mm.
Keywords:
eddy current testing, support vector machine, GMR, thickness
Download:
IMEKO-TC4-2013-055.pdf
DOI:
-
Event details
IMEKO TC:
TC4
Event name:
TC4 Symposium 2013
Title:
19th IMEKO TC4 Symposium Measurements of Electrical Quantities (together with 17th TC4 IWADC Workshop on ADC and DAC Modelling and Testing)
Place:
Barcelona, SPAIN
Time:
18 July 2013 - 19 July 2013