Content area
Carbon fiber-reinforced polymer (CFRP) laminates are widely used in aerospace, automotive, and infrastructure industries due to their high strength-to-weight ratio. However, defect detection in CFRP remains challenging, particularly in low signal-to-noise ratio (SNR) conditions. Conventional segmentation methods often struggle with noise interference and signal variations, leading to reduced detection accuracy. In this study, we evaluate the impact of thermal image preprocessing on improving defect segmentation in CFRP laminates inspected via pulsed thermography. Polynomial approximations and first- and second-order derivatives were applied to refine thermographic signals, enhancing defect visibility and SNR. The U-Net architecture was used to assess segmentation performance on datasets with and without preprocessing. The results demonstrated that preprocessing significantly improved defect detection, achieving an Intersection over Union (IoU) of 95% and an F1-Score of 99%, outperforming approaches without preprocessing. These findings emphasize the importance of preprocessing in enhancing segmentation accuracy and reliability, highlighting its potential for advancing non-destructive testing techniques across various industries.
Details
Preprocessing;
Deep learning;
Nondestructive testing;
Defects;
Image segmentation;
Temperature;
Carbon fiber reinforced plastics;
Neural networks;
Process controls;
Polynomials;
Strength to weight ratio;
Thermal imaging;
Thermography;
Heat;
Manufacturing;
Laminates;
Performance evaluation;
Radiation;
Composite materials;
Preventive maintenance;
Carbon fiber reinforcement;
Signal to noise ratio
; Bruno Pereira Barella 1
; Iago Garcia Vargas 1
; Tarpani, José Ricardo 2
; Herrmann, Hans-Georg 3
; Fernandes, Henrique 4
1 Faculty of Computing, Federal University of Uberlandia, Uberlandia 38408-100, Brazil;
2 Department of Materials, Sao Carlos School of Engineering, University of Sao Paulo, Sao Carlos 13566-590, Brazil;
3 Fraunhofer IZFP Institute for Non-Destructive Testing, Campus E3 1, 66123 Saarbrucken, Germany;
4 Faculty of Computing, Federal University of Uberlandia, Uberlandia 38408-100, Brazil;