Automatic Detection of CFRP Subsurface Defects via Thermal Signals in Long Pulse and Lock-In Thermography.

Thermography is widely used to detect delamination defects in carbon fiber-reinforced plastics (CFRPs). This article proposes a model to detect defects automatically by extracting the thermal signal characteristics of CFRP materials. An optically excited thermography system is constructed for pulsed and lock-in thermography (LT) experiments to compare thermal signal datasets in different excitation modes. A multi-task joint loss function is defined to train the model for defect detection and depth prediction. The effects of different attention modules (AMs) are analyzed to improve the model performance. By comparing the effects of traditional thermography processing methods and methods based on convolutional neural network (CNN), it is found that the proposed model can detect defects with a minimum aspect ratio (ratio of short side to depth) of 2.5, and a relative error percentage in-depth prediction is below 10%.