Thermal Overlay Visualization for 3D Printing Defect Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing additive manufacturing techniques lack intuitive methods for users to evaluate performance, particularly in identifying the location and severity of defects in 3D printed objects, making it difficult for end-users to interpret and address manufacturing errors effectively.
Innovation Solution
The implementation of object manufacturing visualizations, including graphical overlays and thermal images, utilizing machine learning models like neural networks to predict and compare thermal images with contone maps, providing users with intuitive insights into printing performance and defect locations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional additive manufacturing processes are used, then 3D objects can be manufactured, but users cannot intuitively evaluate manufacturing performance or identify defect locations
Solution Approach 1:
The patent creates visual copies (thermal images and graphical overlays) of the manufacturing process and defects. Thermal images capture thermal patterns during printing, while graphical overlays map defect locations onto 3D model representations, allowing users to visually evaluate manufacturing performance without directly observing the physical object
Solution Approach 2:
The patent uses color-coded thermal images and graphical overlays to represent different temperature zones and defect severities. Variations in color intensity and hue provide intuitive visual cues about manufacturing quality, enabling users to quickly identify problem areas without technical expertise
2Measurement precision
If detailed manufacturing data is collected, then defect information becomes available, but users struggle to interpret the data to understand defect location and severity
Solution Approach 1:
The patent segments manufacturing data into distinct visual components: thermal images show temperature distribution, graphical overlays indicate defect locations, and annotations provide severity information. This segmentation transforms complex raw data into organized, easily interpretable visual elements
Solution Approach 2:
The patent introduces graphical overlays as an intermediary between raw manufacturing data and user understanding. These overlays translate complex thermal and mechanical data into intuitive visual representations that clearly indicate defect locations and severity without requiring users to interpret raw measurements
3Measurement precision
If thermal imaging and machine learning analysis are implemented, then defect identification accuracy improves, but system complexity increases
Solution Approach 1:
The patent implements machine learning models that automatically analyze thermal images and generate defect assessments without requiring manual intervention. The system self-evaluates manufacturing quality by comparing thermal patterns against learned norms, reducing the need for complex manual analysis tools
Solution Approach 2:
The patent creates a feedback loop where thermal imaging data is continuously analyzed during manufacturing, and results are immediately visualized through graphical overlays. This real-time feedback mechanism enables automatic defect detection and communication, reducing system complexity by eliminating manual inspection steps
Data Source
AI summary
Examples of methods for object manufacturing visualization by an electronic device are described herein. In some examples, a predicted thermal image of additive manufacturing is determined using a machine learning model. In some examples, a captured thermal image is obtained. In some examples, a graphical overlay of the predicted thermal image with the captured thermal image is presented.