North Carolina State University
Assembly Line
New Technique Improves Finishing Time for 3D Printed Machine Parts
North Carolina State University researchers have demonstrated a technique that allows people who manufacture metal machine parts with 3D printing technologies to conduct automated quality control of manufactured parts during the finishing process. The technique allows users to identify potential flaws without having to remove the parts from the manufacturing equipment, making production time more efficient. Specifically, the researchers have integrated 3D printing, automated machining, laser scanning and touch-sensitive measurement technologies with related software to create a largely automated system that produces metal machine components that meet critical tolerances.
When end users need a specific part, they pull up a software file that includes the measurements of the desired part. A 3D printer uses this file to print the part, which includes metal support structures. Users then take the printed piece and mount it in a finishing device using the support structure. At this point, lasers scan the mounted part to establish its dimensions. A software program then uses these dimensions and the desired critical tolerances to guide the finishing device, which effectively polishes out any irregularities in the part. As this process moves forward, the finishing device manipulates the orientation of the printed part so that it can be measured by a touch-sensitive robotic probe that ensures the part’s dimensions are within the necessary parameters.
Manufacturing service capability prediction with Graph Neural Networks
In the current landscape, the predominant methods for identifying manufacturing capabilities from manufacturers rely heavily on keyword matching and semantic matching. However, these methods often fall short by either overlooking valuable hidden information or misinterpreting critical data. Consequently, such approaches result in an incomplete identification of manufacturers’ capabilities. This underscores the pressing need for data-driven solutions to enhance the accuracy and completeness of manufacturing capability identification. To address the need, this study proposes a Graph Neural Network-based method for manufacturing service capability identification over a knowledge graph. To enhance the identification performance, this work introduces a novel approach that involves aggregating information from the graph nodes’ neighborhoods as well as oversampling the graph data, which can be effectively applied across a wide range of practical scenarios. Evaluations conducted on a Manufacturing Service Knowledge Graph and subsequent ablation studies demonstrate the efficacy and robustness of the proposed approach. This study not only contributes a innovative method for inferring manufacturing service capabilities but also significantly augments the quality of Manufacturing Service Knowledge Graphs.