Downbeam Melt Pool Imaging for Real-Time Additive Process Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Additive manufacturing processes face challenges due to environmental variability, material quality fluctuations, and programming/configuration glitches, leading to inefficiencies, defects, and waste.
Innovation Solution
A monitoring and control system that captures in-process image data, analyzes it using artificial intelligence models to predict errors, and adjusts the additive manufacturing process in real-time to compensate for defects and anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-time image data capture and AI analysis are implemented to predict and compensate for errors during additive manufacturing, then product reliability and manufacturing precision are improved, but device complexity and computational requirements increase
Solution Approach 1:
The system performs preliminary error prediction by capturing image data and applying AI models during the additive manufacturing process to identify potential defects before they compromise the final product. This allows proactive compensation adjustments to be made during manufacturing rather than discovering defects after completion.
Solution Approach 2:
The system implements a closed-loop feedback mechanism where image data from the melt pool is continuously analyzed, error predictions are generated, and compensation parameters are adjusted in real-time. This feedback loop enables dynamic correction of manufacturing deviations to maintain high product reliability.
2Manufacturing precision
If comprehensive image data is captured and analyzed during the additive manufacturing process to detect errors, then manufacturing precision is improved, but processing time and computational resources increase
Solution Approach 1:
The system extracts only the most critical features from the captured image data that are relevant to error detection and manufacturing precision. By focusing analysis on key melt pool characteristics rather than processing all image data, the system maintains high precision while reducing computational overhead and processing time.
Solution Approach 2:
The system applies AI analysis selectively to image frames that show significant deviations or anomalies in the melt pool characteristics. Rather than analyzing every single frame with full computational intensity, the system uses partial analysis on critical frames to maintain manufacturing precision while optimizing processing time.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An example additive manufacturing apparatus (100, 200) includes an energy source (104) to melt material to form a component in an additive manufacturing process, a camera (102, 136) aligned with the energy source (104) to obtain image data of the melted material during the additive manufacturing process, and a controller (130, 154, 156, 200, 1012) to control the energy source (104) during the additive manufacturing process in response to processing of the image data. The controller (130, 154, 156, 200, 1012) adjusts control of the energy source (104) based on a correction determined by: applying an artificial intelligence model (335, 710-716) to image data (337, 405, 510) captured by the camera (102, 136) during an additive manufacturing process, the image data (337, 405, 510) including an image (337, 405, 510) of a melt pool of the additive manufacturing process; predicting an error in the additive manufacturing process using an output of the artificial intelligence model (335, 710-716); and compensating for the error by generating a correction to adjust a configuration of the energy source (104) during the additive manufacturing process.