In-situ point cloud fusion for layer-wise monitoring of additive manufacturing

Additive manufacturing (AM) has received an increasing attention in the manufacturing sector, owing to its highlevel design freedom and enhanced capability to produce parts with complex geometries. With advances in AM technologies, the role of AM has been shifting from rapid prototyping to viable production-worthy manufacturing of functional parts. However, AM processes are highly inconsistent, and the lack of quality assurance significantly hampers the broader adoption of AM. Most existing techniques for AM online monitoring focus on the detection of conspicuous defects, such as under-fills and cracks. They are limited in their ability to detect layer surface variations induced by miniature process shifts. The objective of this study is to develop a new layer-wise monitoring framework for AM quality assurance based on in-situ point cloud fusion. Specifically, online 3D structured-light scanning is used to capture the surface morphology from each printed layer. The collected point cloud is partitioned, and the morphological patterns in local regions are delineated with a new affinity measure to evaluate the conformity to the reference. A deep cascade model is further introduced to leverage the local affinities for the identification of abnormal patterns on the printed layers. Finally, a statistical control chart is constructed for process monitoring and the identification of miniature shifts. Simulation and real-world case studies using the fused filament fabrication (FFF) process are conducted, and experimental results have demonstrated the effectiveness of the developed framework. It has a great potential to be implemented in diverse AM processes with a wide variety of materials for mission-critical applications.

Automated summary

Additive manufacturing (AM) has gained attention for its design freedom and capability to produce complex geometries, but faces challenges in quality assurance. This study proposes a new layer-wise monitoring framework based on in-situ point cloud fusion to address this issue, effectively identifying abnormal patterns with a deep cascade model. Experimental results demonstrate the framework's effectiveness in various AM processes.