A Systematic Review of Available Datasets in Additive Manufacturing
Xiao Liu, Alessandra Mileo, Alan F. Smeaton
TL;DR
This systematic review addresses the shortage of open, annotated image datasets for defect detection in additive manufacturing. By surveying nine dataset repositories and a leading AM journal's supplementary information, it reveals that very few open image datasets exist that cover microstructure defects like melt-pool porosity or cracking, with many datasets either non-image or poorly documented for ready reuse. The findings highlight a critical gap hindering CV/ML progress in AM and underscore the need for community-driven publishing of accessible, well-labeled imaging datasets to enable real-time quality control and defect mitigation in manufacturing processes.
Abstract
In-situ monitoring incorporating data from visual and other sensor technologies, allows the collection of extensive datasets during the Additive Manufacturing (AM) process. These datasets have potential for determining the quality of the manufactured output and the detection of defects through the use of Machine Learning during the manufacturing process. Open and annotated datasets derived from AM processes are necessary for the machine learning community to address this opportunity, which creates difficulties in the application of computer vision-related machine learning in AM. This systematic review investigates the availability of open image-based datasets originating from AM processes that align with a number of pre-defined selection criteria. The review identifies existing gaps among the current image-based datasets in the domain of AM, and points to the need for greater availability of open datasets in order to allow quality assessment and defect detection during additive manufacturing, to develop.