Synthetic image data augmentation for fibre layup inspection processes: Techniques to enhance the data set

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.

Review of image segmentation techniques for layup defect detection in the Automated Fiber Placement process

“…Further crucial tasks in the field of image processing are the smoothing of sensor data and the adjustment of pixel values. For this purpose, the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm is a suitable method for image contrast equalisation, as Meister et al (2020Meister et al ( , 2021 have already explained. This technique was developed in the mid 80's and Pizer et al (1986) used it first in the field of medical imaging.…”

“…The detailed defect analysis and interpretation will be considered separately in further research and is therefore not part of this paper. In addition, the presented procedure can serve as a partially automated input generator for the synthesis of further defect images in AFP inspection, as described in our publication from Meister et al (2021) or in similar fields as mentioned from Jain et al (2020). For this reason the following research questions are selected for this publication:…”

Simulation-Based Data Augmentation for the Quality Inspection of Structural Adhesive With Deep Learning

“…Meister et al [20] Automated fiber placement defects 5000 DCGAN However, as it can be observed in Table 1 a large amount of real training data is still necessary in order to train GAN models to generate training data with sufficient quality. While considerable progress has been made towards solving this challenge, a state-of-the-art approach for small datasets developed by researchers at NVIDIA [21] still requires over 1000 images to train.…”

Optical Material Characterisation of Prepreg CFRP for Improved Composite Inspection

“…Sensor and Laser are aligned at an angle towards each other. To capture the three dimensional surface data the joined camera-laser device is moved in parallel to the surface, perpendicular to the laser line [9,31].…”

“…Thus, the potential for improvement in quality and speed is enormous [8]. Due to their ability to record a three dimensional topological map of a surface, Laser Line Scan Sensor (LLSS) based inspection systems are particularly popular for automated inspection in fibre composite manufacturing [4,9,10] .These sensor systems project a laser beam at a specific incidence angle onto the fibre material surface. A camera senses the position of this laser line at a different viewing angle.…”