In-situ monitoring of image texturing via random forests and clustering with applications to additive manufacturing

The amount of attention paid to in-situ monitoring in Additive Manufacturing (AM) has significantly increased over the last few years, paving the way to a paradigm shift for quality monitoring and control via big data analysis of signals, images, and videos. In-situ quality monitoring represents an opportunity for waste reduction and first-time-right production via inline detection of process flaws, which allows early identification of scraps and the possibility of correcting actions for first-time-right production. This article presents a solution for in-situ monitoring of images taken layerwise in material extrusion AM. Compared with the existing solutions, mainly focusing on monitoring the shape deviation observed at each layer with respect to the nominal shape, this article focuses on monitoring the internal surface texture with the aim of detecting over- and under-extrusion flaws. Inspired by an approach reported in the literature that was developed for textile image monitoring, we propose a solution for in-situ monitoring of textured surfaces which is based on combining Random Forests with clustering to automatically identify defective locations layerwise. A real case study based on Fused Filament Fabrication is used to compare the performance of the novel proposed solution with the original one and identify an appropriate direction for future research.