Optical Image Analysis for Additive Manufacturing Error Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Additive Manufacturing (AM) processes, particularly Selective Laser Melting (SLM), face challenges in quality monitoring and control due to variability in input parameters and boundary conditions, leading to errors that can compound and result in non-functional or non-compliant parts.
Innovation Solution
A method and system for detecting errors in AM processes using optical images analysis, where gray values of pixels in captured images are compared to thresholds based on reference images to identify issues such as warpage and dross formation, enabling non-destructive, in-process inspection and quality control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional quality monitoring methods are used in additive manufacturing, then the process is simple to implement, but the detection sensitivity and accuracy are insufficient to identify errors early
Solution Approach 1:
The patent captures optical images of the build platform at multiple stages during the additive manufacturing process (before melting, during melting, after melting, and after recoating). This preliminary capture of data during the build process enables early error detection before defects compound, resolving the contradiction by implementing detection actions in advance rather than as a post-processing step.
Solution Approach 2:
The patent creates digital copies of the build platform through optical imaging. These image copies are then processed through gray value analysis and comparison with reference images to detect errors. This copying approach enables sophisticated analysis without requiring complex physical inspection equipment, thus improving detection accuracy while managing system complexity.
2Reliability
If comprehensive quality monitoring is implemented throughout the build process, then error detection capability is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent divides the build process into distinct stages (before melting, during melting, after melting, after recoating) and captures images at each stage. This segmentation allows for targeted analysis of specific error types at appropriate build stages, improving reliability while reducing unnecessary processing time compared to continuous monitoring of the entire process.
Solution Approach 2:
The patent performs gray value analysis on specific regions of interest in the optical images rather than analyzing every pixel throughout the entire build volume. This partial action approach maintains high reliability for error detection while significantly reducing computational time and resources required for processing.
3Ease of manufacture
If optical imaging is used to capture build platform images, then non-destructive inspection is achieved, but the complexity of image processing and analysis increases
Solution Approach 1:
The patent replaces complex mechanical inspection systems with optical imaging and computational analysis. By using gray value processing and image comparison algorithms, the system achieves sophisticated error detection without requiring complex physical measurement devices, thus maintaining ease of manufacture while managing processing complexity.
Solution Approach 2:
The patent transforms optical images into gray value parameters for analysis. This parameter transformation simplifies the image processing by converting visual information into quantitative data that can be compared against reference values, reducing the complexity of analysis while maintaining effective error detection capability.
4Manufacturing precision
If errors are detected early in the build process, then defective parts can be prevented, but the frequency of monitoring requires more resources
Solution Approach 1:
The patent implements periodic optical imaging at specific intervals during the build process (before melting, during melting, after melting, after recoating). This periodic monitoring approach enables early error detection that maintains manufacturing precision while avoiding continuous monitoring that would reduce productivity, thus resolving the contradiction between detection frequency and build efficiency.
Data Source
AI summary
The present disclosure relates to the prediction of part and material quality of Additive Manufacturing (AM) processes using layer based images. Described herein are methods and systems for detection of errors in parts built by AM processes such as Selective Laser Melting (SLM). The detection comprises analysis of optical images to identify errors which appear in layers during the AM build process. Errors include but are not limited to warpage of parts and dross formation of overhang surfaces.