Title: Synthetic image data augmentation for fibre layup inspection processes
Subtitle: Techniques to enhance the data set
Authors: Meister, Sebastian
Möller, Nantwin 
Stüve, Jan
Groves, Roger M.
Language: en
Issue Date: 2-Feb-2021
Publisher: Springer Science + Business Media B.V
Document Type: Article
Journal / Series / Working Paper (HSU): Journal of Intelligent Manufacturing 
Volume: 32.2021
Pages: 23
Publisher Place: Dordrecht
Abstract: 
© 2021, The Author(s). In the aerospace industry, the Automated Fiber Placement process is an established method for producing composite parts. Nowadays the required visual inspection, subsequent to this process, typically takes up to 50% of the total manufacturing time and the inspection quality strongly depends on the inspector. A Deep Learning based classification of manufacturing defects is a possibility to improve the process efficiency and accuracy. However, these techniques require several hundreds or thousands of training data samples. Acquiring this huge amount of data is difficult and time consuming in a real world manufacturing process. Thus, an approach for augmenting a smaller number of defect images for the training of a neural network classifier is presented. Five traditional methods and eight deep learning approaches are theoretically assessed according to the literature. The selected conditional Deep Convolutional Generative Adversarial Network and Geometrical Transformation techniques are investigated in detail, with regard to the diversity and realism of the synthetic images. Between 22 and 166 laser line scan sensor images per defect class from six common fiber placement inspection cases are utilised for tests. The GAN-Train GAN-Test method was applied for the validation. The studies demonstrated that a conditional Deep Convolutional Generative Adversarial Network combined with a previous Geometrical Transformation is well suited to generate a large realistic data set from less than 50 actual input images. The presented network architecture and the associated training weights can serve as a basis for applying the demonstrated approach to other fibre layup inspection images.
Organization Units (connected with the publication): Informatik im Maschinenbau 
URL: https://api.elsevier.com/content/abstract/scopus_id/85100346594
DOI: 10.1007/s10845-021-01738-7
Appears in Collections:Publications of the HSU Researchers (before HSU)

Show full item record

CORE Recommender

SCOPUSTM   
Citations

11
checked on May 19, 2022

Google ScholarTM

Check

Altmetric

Altmetric


Items in openHSU are protected by copyright, with all rights reserved, unless otherwise indicated.