Nondestructive Evaluation of Composite Bonding Structure Used in Electrical Insulation Based on Active Infrared Thermography

Guo, Chenjun; Liu, Lishuai; Mei, Hongwei; Tu, Yanxin; Wang, Liming

doi:10.3390/polym14163373

Cited by 2 publications

(1 citation statement)

References 31 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The unknown sizes, shapes, locations, and physical properties of the defects make the NDE study of CFRP a challenge. Infrared thermography (IRT) [2], as a classical non-destructive test technique, has gained wide interest in CFRP quality assessment and cultural heritage restoration [3][4][5][6][7]. Although IRT offers several advantages in terms of detection efficiency, its direct performance does not provide satisfactory results.…”

Section: Introductionmentioning

confidence: 99%

Data-Augmented Manifold Learning Thermography for Defect Detection and Evaluation of Polymer Composites

Liu

Wang

et al. 2022

Polymers

View full text Add to dashboard Cite

Infrared thermography techniques with thermographic data analysis have been widely applied to non-destructive tests and evaluations of subsurface defects in practical composite materials. However, the performance of these methods is still restricted by limited informative images and difficulties in feature extraction caused by inhomogeneous backgrounds and noise. In this work, a novel generative manifold learning thermography (GMLT) is proposed for defect detection and the evaluation of composites. Specifically, the spectral normalized generative adversarial networks serve as an image augmentation strategy to learn the thermal image distribution, thereby generating virtual images to enrich the dataset. Subsequently, the manifold learning method is employed for the unsupervised dimensionality reduction in all images. Finally, the partial least squares regression is presented to extract the explicit mapping of manifold learning for defect visualization. Moreover, probability density maps and quantitative metrics are proposed to evaluate and explain the obtained defect detection performance. Experimental results on carbon fiber-reinforced polymers demonstrate the superiorities of GMLT, compared with other methods.

show abstract