Melt Pool Feature Extraction for Real-Time AM Quality Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional additive manufacturing (AM) tools lack an online tuning mechanism to adjust process parameters in real-time, leading to variations in production quality due to factors like power distribution and moisture content, which are only measured after product completion.
Innovation Solution
An AM feature extraction method that measures temperature and captures images of melt pools during fabrication, extracting features such as length, width, and temperature to predict virtual metrology values using a prediction algorithm, allowing for real-time adjustment of process parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If conventional AM tools use fixed process parameters for production, then device complexity is reduced, but manufacturing precision deteriorates due to process variations
Solution Approach 1:
The system transitions from fixed process parameters to dynamic, real-time parameter adjustment. Sensors continuously monitor melt pool characteristics and provide feedback to adjust laser power, scan speed, and other parameters during fabrication, enabling the system to adapt to process variations and maintain manufacturing precision.
Solution Approach 2:
The system implements real-time feedback control by monitoring melt pool temperature, size, and shape during fabrication. This feedback is used to automatically adjust process parameters to compensate for variations in power distribution, flow control, and moisture content, thereby maintaining consistent production quality.
2Device complexity
If quality measurements are performed only after product completion, then measurement complexity is reduced, but loss of time increases due to delayed quality assessment
Solution Approach 1:
The system performs quality assessment during the fabrication process rather than after completion. By monitoring melt pool characteristics in real-time, the system can detect quality issues early and adjust parameters or halt production before defects propagate through subsequent layers, significantly reducing loss of time.
Solution Approach 2:
The quality measurement system operates continuously throughout the fabrication process, providing ongoing assessment rather than discrete post-completion checks. This continuous monitoring enables real-time detection and correction of quality issues, maintaining productive action without interruption.
3Manufacturing precision
If real-time temperature measurement and image capture are performed on melt pools, then manufacturing precision is improved through timely quality assessment, but use of energy increases due to additional sensors and processing
Solution Approach 1:
The system uses multi-functional sensors that serve multiple purposes. For example, optical sensors capture melt pool images for quality assessment while also providing information about process conditions. This multi-functionality reduces the total number of sensors needed and optimizes energy usage while maintaining manufacturing precision.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables timely quality assessment and adjustment of process parameters, thereby improving the yield and quality of end products by predicting potential issues before completion.
Implementation Method 1
using a high energy laser to irradiate a position at which a powder molding is desired to be formed, thereby melting and fusing the powders
Implementation Method 2
a pyrometer is used to perform a temperature measurement on each of the melt pools on the powder bed
Data Source
AI summary
An additive manufacturing (AM) method includes using an AM tool to fabricate a plurality of workpiece products; measuring qualities of the first workpiece products respectively; performing a temperature measurement on each of the melt pools on the powder bed during a fabrication of each of the workpiece products; performing photography on each of the melt pools on the powder bed during the fabrication of each of the workpiece products; extracting a length and a width of each of the melt pools; performing a melt-pool feature processing operation; building a conjecture model by using a plurality of sets of first process data and the actual metrology values of the first workpiece products in accordance with a prediction algorithm; and predicting a virtual metrology value of the second workpiece product by using the conjecture model based on a set of second process data.


