Voxel Meltpool Control for Faster Additive Part Development
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing additive manufacturing processes require time-consuming and expensive parameter selection to achieve high-quality 3D printed parts, especially for complex geometries, due to the need for numerous tests and evaluations to determine optimal printing parameters, which can introduce defects and deviations from the intended design.
Innovation Solution
The use of in-situ information and a closed-loop control architecture that adjusts process parameters in real-time, utilizing voxel-level references and sensor data to control part quality, enabling faster and more efficient development of high-quality 3D printed parts by controlling meltpool characteristics at the voxel level.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional additive manufacturing parameter selection methods are used, then part quality can be achieved, but part development time and costs increase significantly
Solution Approach 1:
The patent implements a closed-loop control system where sensor data from the additive manufacturing process is fed back to a machine learning model in real-time. The model continuously predicts optimal process parameters and feeds them back to the manufacturing system, enabling dynamic adjustment during printing. This feedback mechanism eliminates the need for extensive pre-printing parameter testing while maintaining high part quality through real-time optimization.
Solution Approach 2:
The machine learning model autonomously selects and optimizes process parameters without requiring manual intervention or extensive expert knowledge. The system self-adjusts by learning from sensor data and automatically determining optimal printing conditions, thereby eliminating time-consuming trial-and-error parameter selection while ensuring consistent part quality.
2Manufacturing precision
If traditional additive manufacturing parameter selection methods are used, then part quality can be achieved, but costs increase due to numerous tests and evaluations
Solution Approach 1:
The closed-loop feedback system continuously monitors the additive manufacturing process using sensors and adjusts parameters in real-time based on machine learning predictions. This eliminates the need for multiple physical test prints and evaluations, significantly reducing material consumption and development costs while maintaining high part quality through automated real-time optimization.
Solution Approach 2:
The machine learning model creates a virtual digital twin of the additive manufacturing process, simulating and predicting optimal parameters before actual printing. This virtual modeling allows parameter optimization without physical trial-and-error testing, reducing material waste and development costs while ensuring part quality through pre-simulated optimal conditions.
3Loss of time
If automated parameter optimization is implemented, then part development time is reduced, but system complexity increases
Solution Approach 1:
The machine learning model serves multiple functions simultaneously: it predicts process parameters, analyzes sensor data, optimizes printing conditions, and controls the additive manufacturing process. This multi-functional approach consolidates what would otherwise require multiple separate systems into a single integrated platform, reducing overall system complexity while enabling automated real-time parameter optimization.
Solution Approach 2:
The machine learning model acts as an intelligent intermediary between sensor data and process control, translating raw sensor inputs into optimized printing parameters. This intermediary layer simplifies the control architecture by centralizing the optimization logic in a single model rather than requiring complex distributed control systems, thereby reducing system complexity while achieving automated parameter optimization.
Data Source
AI summary
Methods and apparatus for sensor-based part development are disclosed. An example apparatus includes at least one memory, instructions in the apparatus, and processor circuitry to execute the instructions to translate at least one user-defined material property selection into a desired process observable, the desired process observable including a meltpool property, perform voxel-based autozoning of an input part geometry, the input part geometry based on a computer-generated design, and output a voxelized reference map for the input part geometry based on the desired process observable and the voxel-based autozoning.