Advanced Thermal Imaging Processing and Deep Learning Integration for Enhanced Defect Detection in Carbon Fiber-Reinforced Polymer Laminates

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Materials vol. 18, no. 7 (2025), p. 1448
1. Verfasser: Renan Garcia Rosa
Weitere Verfasser: Bruno Pereira Barella, Iago Garcia Vargas, Tarpani, José Ricardo, Herrmann, Hans-Georg, Fernandes, Henrique
Veröffentlicht:
MDPI AG
Schlagworte:
Online-Zugang:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!

MARC

LEADER 00000nab a2200000uu 4500
001 3188831402
003 UK-CbPIL
022 |a 1996-1944 
024 7 |a 10.3390/ma18071448  |2 doi 
035 |a 3188831402 
045 2 |b d20250101  |b d20251231 
084 |a 231532  |2 nlm 
100 1 |a Renan Garcia Rosa  |u Faculty of Computing, Federal University of Uberlandia, Uberlandia 38408-100, Brazil; <email>renan.garcia@ufu.br</email> (R.G.R.); <email>brunobarella@ufu.br</email> (B.P.B.); <email>iagogarcia@ufu.br</email> (I.G.V.) 
245 1 |a Advanced Thermal Imaging Processing and Deep Learning Integration for Enhanced Defect Detection in Carbon Fiber-Reinforced Polymer Laminates 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a 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. 
653 |a Fiber reinforced polymers 
653 |a Preprocessing 
653 |a Deep learning 
653 |a Nondestructive testing 
653 |a Defects 
653 |a Image segmentation 
653 |a Temperature 
653 |a Carbon fiber reinforced plastics 
653 |a Neural networks 
653 |a Process controls 
653 |a Polynomials 
653 |a Strength to weight ratio 
653 |a Thermal imaging 
653 |a Thermography 
653 |a Heat 
653 |a Manufacturing 
653 |a Laminates 
653 |a Performance evaluation 
653 |a Radiation 
653 |a Composite materials 
653 |a Preventive maintenance 
653 |a Carbon fiber reinforcement 
653 |a Signal to noise ratio 
700 1 |a Bruno Pereira Barella  |u Faculty of Computing, Federal University of Uberlandia, Uberlandia 38408-100, Brazil; <email>renan.garcia@ufu.br</email> (R.G.R.); <email>brunobarella@ufu.br</email> (B.P.B.); <email>iagogarcia@ufu.br</email> (I.G.V.) 
700 1 |a Iago Garcia Vargas  |u Faculty of Computing, Federal University of Uberlandia, Uberlandia 38408-100, Brazil; <email>renan.garcia@ufu.br</email> (R.G.R.); <email>brunobarella@ufu.br</email> (B.P.B.); <email>iagogarcia@ufu.br</email> (I.G.V.) 
700 1 |a Tarpani, José Ricardo  |u Department of Materials, Sao Carlos School of Engineering, University of Sao Paulo, Sao Carlos 13566-590, Brazil; <email>jrpan@sc.usp.br</email> 
700 1 |a Herrmann, Hans-Georg  |u Fraunhofer IZFP Institute for Non-Destructive Testing, Campus E3 1, 66123 Saarbrucken, Germany; <email>hans-georg.herrmann@izfp.fraunhofer.de</email>; Chair for Lightweight Systems, Saarland University, Campus E3 1, 66123 Saarbrucken, Germany 
700 1 |a Fernandes, Henrique  |u Faculty of Computing, Federal University of Uberlandia, Uberlandia 38408-100, Brazil; <email>renan.garcia@ufu.br</email> (R.G.R.); <email>brunobarella@ufu.br</email> (B.P.B.); <email>iagogarcia@ufu.br</email> (I.G.V.); IVHM Centre, Faculty of Engineering and Applied Sciences, Cranfield University, Cranfield MK43 0AL, UK 
773 0 |t Materials  |g vol. 18, no. 7 (2025), p. 1448 
786 0 |d ProQuest  |t Materials Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3188831402/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3188831402/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3188831402/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch