Abstract

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.

Highlights

  • Lightweight structures are commonly used in aerospace manufacturing

  • The investigations in this paper demonstrate that the Geometrical Transformation and a reasonably configured conditional Deep Convolutional Generative Adversarial Network are well suited for the synthetic data generation from less than 50 representative origin images per class

  • The GANTrain Generative Adversarial Network (GAN)-Test method proves to be a suitable tool for the independent evaluation of artificially generated image data

Read more

Summary

Introduction

Lightweight structures are commonly used in aerospace manufacturing. Carbon Fiber Reinforced Plastic (CFRP) offers superior stiffness and strength properties. Lightweight structures are often made from CFRP. The manufacturing of these mostly complex lightweight structures is typically. Today, this manual inspection takes between 32% (Rudberg et al 2014) and 50% (Eitzinger 2019) of the total production time. Due to the manual inspection process, it is sometimes impossible to fulfil the required inspection accuracy. This aspect offers great potential for improvements in quality and speed

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call