Depth classification of defects in composite materials by long-pulsed thermography and blind linear unmixing

Abstract

This paper presents the automatic analysis of surface thermograms in response to a long-pulsed thermography inspection to classify buried defects in composite materials. Time-dependent thermal contrasts, captured from the sample surface by an infrared thermal camera, are linearly unmixed at the pixel scale to produce results independent of the in-plane defect shapes in the training dataset. The extended blind end-member and abundance extraction (EBEAE) method unmix the thermograms to compute feature vectors carrying information about the internal structure of the composite. The estimated abundances fed an optimized support vector machine (SVM) classifier, which learns a model from the data and labels the defects accordingly to their depths. The inspection of a calibrated glass fiber reinforced polymer proves the ability of EBEAE and SVM in defect classification with an average balanced accuracy of 96.18% in testing. This methodology clearly improves the current state of the art, even without the need for inspections with different source excitations. Furthermore, the estimated end-members automatically model the thermal response of the surface, providing crucial feedback for experimental optimization.