scholarly journals Enhancing the Visibility of Delamination during Pulsed Thermography of Carbon Fiber-Reinforced Plates Using a Stacked Autoencoder

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 2809 ◽  
Author(s):  
Changhang Xu ◽  
Jing Xie ◽  
Changwei Wu ◽  
Lemei Gao ◽  
Guoming Chen ◽  
...  
Keyword(s):  
Carbon Fiber ◽  
Learning Algorithm ◽  
Principal Component ◽  
Fiber Reinforced ◽  
Destructive Testing ◽  
Pulsed Thermography ◽  
Stacked Autoencoder ◽  
Deep Learning Algorithm ◽  
Novel Approach ◽  
Carbon Fiber Reinforced

The effectiveness of pulsed thermography (PT) for detecting delamination in carbon fiber-reinforced polymer (CFRP) plates has been widely verified. However, delaminations are usually characterized by weak visibility due to the influences of inspection factors and the delaminations with weak visibility are easily missed in real inspections. In this study, by introducing a deep learning algorithm—stacked autoencoder (SAE)—to PT, we propose a novel approach (SAE-PT) to enhance the visibility of delaminations. Based on the ability of SAE to learn unsupervised features from data, the thermal features of delaminations are extracted from the raw thermograms. The extracted features are then employed to construct SAE images, in which the visibility of delaminations is expected to be enhanced. To test the performance of SAE-PT, we inspected CFRP plates with prefabricated delaminations. By implementing SAE-PT on the raw inspection data, the delaminations were more clearly indicated in the constructed SAE images. We also compare SAE-PT to the widely used principal component thermography (PCT) method to further verify the validity of the proposed approach. The results reveal that compared to PCT, SAE-PT can show delaminations in CFRP with higher contrast. By effectively enhancing the delamination visibility, SAE-PT thus has potential for improving the inspection accuracy of PT for non-destructive testing (NDT) of CFRP.

INCREASING SENSITIVITY OF EDDY CURRENT NON-DESTRUCTIVE TESTING OF DELAMINATION IN CARBON-FIBER REINFORCED PLASTICS

2021 ◽  
pp. 28-37
Author(s):  
P. N. Shkatov ◽  
G. A. Didin ◽  
A. A. Ermolaev
Keyword(s):  
Carbon Fiber ◽  
Eddy Current ◽  
Calculation Model ◽  
Fiber Reinforced ◽  
Destructive Testing ◽  
Carbon Fiber Reinforced Plastics ◽  
Reinforced Plastics ◽  
Fiber Reinforced Plastics ◽  
Carbon Fiber Reinforced ◽  
The Difference

The paper is concerned with increasing sensitivity of eddy current nondestructive testing of most dangerous delamination in carbon-fiber reinforced plastics (CFRP). Increased sensitivity is achieved by separate registration and comparison of eddy current signals obtained from a set of stratifications of carbon fibers with the same orientation. The separation of eddy current signals is possible due to pronounced anisotropy of the electrical conductivity of the layers dominant in the direction of the fibers of the corresponding layer. Eddy-current signals are registered by eddy current probes with maximum sensitivity in a given angular direction. Prior to the scan eddy current signals of the probe are leveled on a defect-free area. The influence of the working gap on the difference between the eddy current signals of the probe is suppressed by normalizing it according to one of the signals. The analysis of the registered signals from delamination has been performed using an approximate calculation model. The reliability of the obtained results has been confirmed by comparison with experimental results and calculations using the finite element method.

scholarly journals Data Enhancement via Low-Rank Matrix Reconstruction in Pulsed Thermography for Carbon-fiber-Reinforced Polymers

2021 ◽  
Author(s):  
Samira Ebrahimi ◽  
Julien R Fleuret ◽  
Matthieu Klein ◽  
Louis-Daniel Théroux ◽  
Clemente Ibarra-Castanedo ◽  
...  
Keyword(s):  
Carbon Fiber ◽  
Matrix Decomposition ◽  
Low Rank ◽  
Fiber Reinforced Polymers ◽  
Main Process ◽  
Fiber Reinforced ◽  
Post Processing ◽  
Pulsed Thermography ◽  
Thermal Data ◽  
Carbon Fiber Reinforced

Pulsed thermography is a commonly used non-destructive testing method, and is increasingly studied for advanced materials such as carbon fiber-reinforced polymer (CFRP) evaluation. Different processing approaches are proposed to detect and characterize anomalies that may be generated in structures during the manufacturing cycle or service period. In this study, we used a type of matrix decomposition using Robust-PCA via Inexact-ALM in our experiment. We investigate this method as a pre-and post-processing method on thermal data acquired by pulsed thermography. We employed state-of-the-art methods, i.e., PCT, PPT, and PLST, as the main process. The results indicate that pre-processing on thermal data can elevate the defect detectability while post-processing, in some cases, can deteriorate the results.

Sign in / Sign up

Export Citation Format

Share Document