3D Print Image Classification for Bead Irregularity 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.
Innovation Solution
A method and system that utilize cameras to acquire images during fabrication, identify fabrication irregularities, generate fabrication scores, and cluster objects based on these scores, with optional mechanical testing to attribute results across clusters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If additive manufacturing systems operate at high speed for mass production, then productivity increases, but fabrication irregularities such as variations in bead thickness and location increase
Solution Approach 1:
The system captures images of fabricated objects during the manufacturing process, analyzes them to identify fabrication irregularities, and uses this information to classify objects into clusters. This feedback mechanism allows the system to monitor and respond to variations in bead quality without reducing production speed, thereby maintaining both productivity and precision.
Solution Approach 2:
The system performs image capture and analysis during fabrication, and pre-classifies objects into clusters before final quality determination. By conducting preliminary classification based on fabrication scores, the system can efficiently sort objects and apply mechanical testing only to representative samples from each cluster, maintaining high productivity while ensuring quality control.
2Manufacturing precision
If mechanical testing is applied to every object to ensure quality, then manufacturing precision is improved, but productivity decreases due to time-consuming testing
Solution Approach 1:
Instead of applying mechanical testing to every object, the system applies it only to representative objects from each fabrication cluster. The fabrication score and image analysis provide sufficient quality information for most objects, allowing partial mechanical testing to maintain quality assurance while preserving production throughput.
3Manufacturing precision
If image analysis is performed on every object to identify irregularities, then manufacturing precision is improved, but device complexity increases
Solution Approach 1:
The system segments the quality assessment process into two levels: (1) image-based fabrication score analysis for all objects, and (2) mechanical testing for representative objects from each cluster. This segmentation allows comprehensive irregularity detection while managing system complexity by using the less complex image analysis for the majority of objects.
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.