An Evaluation of Artificial Neural Networks Applied to Infrared Thermography Inspection of Composite Aerospace Structures

Trétout, H.; David, D.; Marin, J. Y.; Dessendre, M.; Couet, M.; Avenas-Payan, I.

doi:10.1007/978-1-4615-1987-4_103

Cited by 11 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last layer of transpose convolutions, another function 𝑔(𝑥) = 𝑠𝑖𝑔𝑚𝑜𝑖𝑑(𝑥) is used. The convolution operation in each layer produces a feature map after it is multiplied with predefined number of kernels as shown in (8), where 𝐶 𝑗 is the feature map of layer 𝑗, 𝐶 𝑖𝑛 is the dimension of the input to 𝑗 𝑡ℎ layer and 'weight' and 'bias' are the parameters learnt by the network. During convolution, rectified linear units (ReLu) defined in (9) are inserted as activation functions to include non-linearity and to help in loss convergence.…”

Section: Autoencoder Based Defect Visualizationmentioning

confidence: 99%

A deep learning approach based defect visualization in pulsed thermography

Selvan¹,

Sharath²,

Menaka

et al. 2022

IJ-AI

View full text Add to dashboard Cite

<span lang="EN-US">Non-destructive evaluation (NDE) is very essential in measuring the properties of materials and in turn detect flaws and irregularities. Pulsed thermography (PT) is one of the advanced NDE technique which is used for detecting and characterizing subsurface defects. Recently many methods have been reported to enhance the signal and defect visibility in PT. In this paper, a novel unsupervised deep learning-based auto-encoder (AE) approach is proposed for enhancing the signal-to-noise ratio (SNR) and visualize the defects clearly. A detailed theoretical background of AE and its application to PT is discussed. The SNR and defect detectability results are compared with the existing approaches namely, higher order statistics (HOS), principal component thermography (PCT) and partial least square regression (PLSR) thermography. Experimental results show that AE approach provides better SNR at the cost of defect detectability.</span><br /><div id="ext-mouse-move" style="display: none;"> </div><div id="ext-mouse-down" style="display: none;"> </div><div id="ext-mouse-up" style="display: none;"> </div>

show abstract

Section: Autoencoder Based Defect Visualizationmentioning

confidence: 99%

A deep learning approach based defect visualization in pulsed thermography

Selvan¹,

Sharath²,

Menaka

et al. 2022

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Different kinds of training and validation datasets have been used such as raw temperature and time derivatives [4,5], TSR (thermal signal reconstruction) polynomial fitting coefficients [6] phase and phase contrast [2,7] and thermal contrast [8][9][10][11]. Thermal contrast allows evaluating defect visibility and enhancing image quality.…”

Section: Introductionmentioning

confidence: 99%