Depth Evaluation in Pulsed Phase Thermography with Neural Network

Pulsed phase thermography (PPT) was recently introduced [1] and up to now analysis of this infrared thermographie approach for non destructive evaluation has been limited to qualitative aspects. The study presented in this paper uses a neural network (NN) approach to extract quantitative information from PPT results. Phase behavior with frequency is first analyzed with a theoretical model which is of further interest to establish the NN architecture, finally results are presented.