Automated defect detection in large-scale bonded parts by active thermography

Zaeh, M.F.; Srajbr, C.

doi:10.21611/qirt.2010.137

Cited by 3 publications

(2 citation statements)

References 3 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further work demonstrated the detectability of hidden defects up to a depth of about 1 mm in ferritic steel [6], which is normally not possible with MT. Using inductive excitation, the integrity of bonded joints in the automotive sector was investigated [7]. Current research by Oswald-Tranta et al is concerned with determining the crack depth from the cooling sequences of thermography [8].…”

Section: Introductionmentioning

confidence: 99%

Defect shape detection and prediction in active thermography by means of supervised semantic segmentation

Müller¹,

Netzelmann²,

Valeske³

2020

Proceedings of the 2020 International Conference on Quantitative InfraRed Thermography

View full text Add to dashboard Cite

A fully convolutional neural network was set up for the detection of crack-type defects and for the defect shape prediction of thermography datasets. The method uses a supervised neural network for sematic segmentation (U-Net). For these tasks, training datasets of forged parts were acquired through induction thermography. The approach provides a significant improvement over conventional methods of thermal signal and image processing used in active thermography. Furthermore, the results may lead to new procedures for a quantitative evaluation of flaws and defects in non-destructive testing using infrared thermography.

show abstract

Section: Introductionmentioning

confidence: 99%

Defect shape detection and prediction in active thermography by means of supervised semantic segmentation

Müller¹,

Netzelmann²,

Valeske³

2020

Proceedings of the 2020 International Conference on Quantitative InfraRed Thermography

View full text Add to dashboard Cite

show abstract

“…Before launching of the new product or the material on the market, they must be tested in order to assess their in-service usage ability for the specific exploitation conditions. Recent research (Avdelidis et al, 2010;Bremond, 2010;Choi et al, 2008;Galietti & Palumbo 2010;Huebner et al, 2010;Kruczek, 2008;Murariu et al, 2010;Pieczyska et al 2008;Sahli et al 2010;Thiemann, 2010) has shown the potential of thermography in the monitoring of the mechanical damage but, at the same time, more detailed investigations and analyses are needed in order to develop a more practical thermography method for characterizing the materials' proprieties. In the following section some applications of thermography in materials science are presented.…”

Section: Introductionmentioning

confidence: 99%