Automated Defect Detection in Non-planar Objects Using Deep Learning Algorithms

The non-uniformity of non-planar object inspection data makes their analysis challenging. This paper reports a study of the use of recurrent neural network and artificial feed-forward neural network in pulsed thermography during the automated inspection of non-planar carbon fiber reinforced plastic...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of nondestructive evaluation Ročník 41; číslo 1; s. 14
Hlavní autoři: Tao, Yuntao, Hu, Caiqi, Zhang, Hai, Osman, Ahmad, Ibarra-Castanedo, Clemente, Fang, Qiang, Sfarra, Stefano, Dai, Xiaobiao, Maldague, Xavier, Duan, Yuxia
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.03.2022
Springer Nature B.V
Témata:
Algorithms
Artificial intelligence
Automation
Cameras
Carbon fiber reinforced plastics
Characterization and Evaluation of Materials
Classical Mechanics
Classification
Control
Cooling
Data analysis
Data processing
Deep learning
Defects
Design
Dynamical Systems
Engineering
Fourier transforms
Inspection
Machine learning
Neural networks
Nonuniformity
Object recognition
Radiation
Recurrent neural networks
Signal processing
Signal reconstruction
Solid Mechanics
Thermography
Time dependence
Time series
Vibration
Long short-term memory recurrent neural network
Carbon fiber reinforced plastic
Artificial feed-forward neural networks
Pulsed thermography
Non-planar
ISSN:0195-9298, 1573-4862
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The non-uniformity of non-planar object inspection data makes their analysis challenging. This paper reports a study of the use of recurrent neural network and artificial feed-forward neural network in pulsed thermography during the automated inspection of non-planar carbon fiber reinforced plastic samples. The time series, including the raw temperature–time series and sequenced signals obtained from the first derivative after thermographic signal reconstruction was used to train and test the models respectively. Quantitative comparisons of testing results showed that the long short-term memory recurrent neural network model was more accurate in handling time dependent information compared to the artificial feed-forward neural network model.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0195-9298
1573-4862
DOI:10.1007/s10921-022-00845-6