Molten Pool Spatter Imaging for Real-Time Build State Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing additive manufacturing techniques, such as those described in Japanese Patent Publication No. 2022-121427, can detect undesirable fluctuations in laser irradiation conditions during the manufacturing process but are inadequate for evaluating the quality of a completed build object without destroying the finished product, lacking detailed information about the build state.
Innovation Solution
A system and method that includes an image acquisition unit to capture spatter images during the manufacturing process, an analysis unit to extract features and calculate coordinates of molten pools, and a control unit to adjust laser conditions based on estimated local parameters, enabling non-destructive evaluation of the build object's quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If spatter images are acquired and analyzed to estimate build state parameters, then measurement precision of build quality is improved, but device complexity increases due to additional image acquisition and analysis units
Solution Approach 1:
The patent introduces an image acquisition unit and analysis unit as intermediary components that capture spatter images and process them to estimate build state parameters. These intermediaries enable non-destructive measurement of build quality without direct physical contact with the build object, resolving the contradiction between measurement precision and device complexity by using optical fields as a non-invasive mediator.
Solution Approach 2:
The patent replaces mechanical inspection methods (such as physical sampling or destructive testing) with an optical-based image acquisition and analysis system. By substituting mechanical measurement approaches with optical field-based non-contact measurement, the system achieves high measurement precision while avoiding the complexity of mechanical inspection equipment and sample destruction.
2Manufacturing precision
If real-time image acquisition and analysis is performed, then manufacturing precision is improved through real-time feedback, but productivity decreases due to additional processing time
Solution Approach 1:
The patent implements a real-time feedback mechanism where spatter images are continuously captured during laser irradiation, analyzed to estimate build state parameters, and used to adjust manufacturing conditions immediately. This closed-loop feedback system enables real-time quality control and process optimization, resolving the contradiction by using feedback to prevent defects rather than inspecting finished products after production.
Solution Approach 2:
The patent performs preliminary analysis of spatter images during the manufacturing process itself, rather than waiting for completion. By conducting build state estimation in real-time during laser irradiation, the system can identify and correct issues early in the process, improving manufacturing precision without requiring post-production inspection that would reduce productivity.
3Measurement precision
If detailed local parameter estimation is performed for each molten pool, then measurement precision of build state is improved, but calculation time increases
Solution Approach 1:
The patent divides the build object into multiple regions corresponding to individual molten pools, with each region analyzed separately to estimate local build state parameters. By segmenting the analysis into discrete, manageable units rather than performing a single comprehensive analysis of the entire build object, the system achieves high measurement precision for each local area while reducing overall calculation time through parallel processing of multiple regions.
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 accurate and reliable assessment of the build object's quality by estimating local parameters like porosity and calculating molten pool coordinates, allowing for real-time adjustments to improve the manufacturing process and ensure the quality of the finished product.
Implementation Method 1
a solidified layer forming step of irradiating the material layer with one or more laser beams to form a solidified layer
Implementation Method 2
irradiating the material layer with one or more laser beams to form a solidified layer
Implementation Method 3
irradiating the material layer with one or more laser beams to form a solidified layer
Implementation Method 4
acquires, in real time, an image of spatter generated around each molten pool formed by the irradiation of the one or more laser beams
Data Source
AI summary
A system estimates a build state of a build object. The system includes an image acquisition unit and an analysis unit. The build object is manufactured by repeating: forming a material layer by supplying material powder onto a build area, and forming a solidified layer by irradiating the material layer with one or more laser beams. The image acquisition unit acquires, in real time, an image of spatter around each molten pool formed by the irradiation of the laser beams. The analysis unit extracts at least one feature related to the spatter from the image, calculates coordinates indicating a position of the molten pool, estimates a local parameter representing the build state of the solidified layer by inputting the at least one feature to a trained model, and outputs the local parameter in a form associated with the coordinates.