In-Process AM Image Scoring for Clustered Part Quality Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing additive manufacturing (AM) systems face challenges in producing identical parts during mass production due to random imperfections in the extrusion process, leading to variations in bead thickness and location, which affect the quality and consistency of manufactured objects.
Innovation Solution
A method and system that utilize cameras coupled with the extruder system to acquire images during fabrication, analyze fabrication irregularities, generate fabrication scores, and cluster objects based on these scores, allowing for mechanical test results to be attributed across similar clusters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If mass production of identical parts is pursued using extrusion-based additive manufacturing, then productivity increases, but manufacturing precision deteriorates due to random imperfections in the extrusion process
Solution Approach 1:
The system performs preliminary classification of manufactured objects into clusters based on fabrication scores before mechanical testing. By pre-grouping objects with similar fabrication characteristics, the system enables efficient quality assurance where only representative samples from each cluster need detailed testing, thereby maintaining precision requirements while supporting mass production throughput
Solution Approach 2:
The system implements feedback through fabrication scores that quantify irregularities in bead thickness and location. These scores are used to classify objects into clusters and determine which objects require mechanical testing. This feedback mechanism enables continuous monitoring and classification of manufacturing quality, allowing the system to maintain precision standards across mass production by identifying and testing only the critical samples
2Manufacturing precision
If comprehensive mechanical testing is applied to all manufactured objects, then manufacturing precision and quality control improve, but productivity decreases due to time-consuming testing procedures
Solution Approach 1:
The system segments the quality assurance process by dividing manufactured objects into distinct clusters based on their fabrication scores. Instead of applying uniform comprehensive testing to all objects, the system segments testing requirements by cluster, allowing efficient quality control where only representative samples from each cluster undergo mechanical testing. This segmentation maintains quality assurance effectiveness while dramatically reducing the total testing burden and preserving production throughput
Solution Approach 2:
The system applies partial action by performing mechanical testing on only a subset of objects (one per cluster) rather than all manufactured objects. The fabrication score-based clustering identifies representative samples that sufficiently characterize each group's quality. This partial testing approach maintains adequate quality control by testing critical representatives while avoiding the excessive time consumption of universal testing, thus balancing precision requirements with productivity maintenance
Data Source
AI summary
A method of additive manufacturing comprises operating an additive manufacturing system for fabricating a multiplicity of objects, while acquiring a set of images during fabrication of each of the objects. For each object, a respective set of images is analyzed to identify fabrication irregularities, and a fabrication score is generated based on the irregularities. The multiplicity of objects is clustered according to the fabrication scores into at least two clusters.