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.
MARWIN is a mobile autonomous robot platform designed to carry out maintenance and inspection tasks in the European XFEL. The XFEL is an accelerator plant which is operated in Hamburg, Germany. The robot system consists of an four-wheel drive chassis and a scissor lift for easy inspection and maintenance tasks. Through this manipulator and the chassis, the robot system acquires three degrees of freedom. MARWIN is intended for autonomous radiation measurements along the XFEL research facility and thus needs accurate localization. The facility describes a straight tunnel and consists partly of irregular structures and also of sections with almost no obstacles. In the 1000 meter long sections in which MARWIN operates, the robot must approach the facilities to a few centimeters, but must not touch them. For this purpose, different localization methods were tested and checked for accuracy. Furthermore, the influence of radiation on the localization is investigated.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.