Fast eddy current testing defect classification using lissajous figures

In this paper, we present a fast method for classification of defects detected by eddy current testing (ECT). This is done by using defects derived by lab experiments. For any defect, the ECT magnetic field response for different EC-probe's paths is represented on a complex plane to obtain Lissajous' figures. Their shapes are described through the use of few geometrical parameters forming a feature vector. Such vectors are used as signatures of the defects detected by the probe at different crossing angles and distances from the defect. The effectiveness of the proposed approach is evaluated by measuring the performances of three machine learning-based classifiers (Naïve Bayes, C4.5/J48 Decision Tree, and Multilayer Perceptron neural network), through the following metrics: area under ROC curve, the Matthews correlation coefficient, and F-Measure. The results confirm the usefulness of the proposed approach to defects detection and classification without the need of an overall scanning of the faulty area. So, it is able to minimize the efforts, and, consequently, the cost of an ECT test.