In this paper, we present a benchmark dataset for defect detection systems in the carbon fibre tape placement process. The dataset includes a combination of artificial and real scans, providing a comprehensive representation of the defects encountered in this manufacturing process. We describe the process of creating the dataset, including the translation of process features into a geometrical model and the collection and processing of real data.
Funding
GA51557 under the Global Innovation Linkages program Round 2 by the Department of Industry, Science and Resources of the Australian Federal Government