Sensor-Assisted 3D Printing Control for Voxel-Level Part Quality
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 are material and geometry-specific.
Innovation Solution
In-situ sensor information is used to control part quality through voxel-level reference generation and a closed-loop control architecture that adjusts process parameters in real-time, enabling faster and more efficient development of high-quality 3D printed parts by translating desired part qualities into process observables and adjusting parameters at the voxel level.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional parameter selection methods are used for additive manufacturing, then high-quality parts 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 continuously fed back to adjust process parameters. This real-time feedback mechanism enables the system to self-optimize and achieve high-quality parts without requiring extensive manual parameter testing and evaluation, thereby resolving the contradiction between part quality and development time
Solution Approach 2:
The system dynamically changes process parameters based on sensor measurements and machine learning model predictions. By automatically adjusting parameters such as laser power, scan speed, and hatch spacing during the manufacturing process, the system achieves optimal part quality without requiring time-consuming manual parameter selection and iteration
2Manufacturing precision
If extensive parameter testing is performed to achieve optimal printing parameters, then part quality improves, but the complexity of the manufacturing process increases
Solution Approach 1:
The additive manufacturing system performs self-optimization through integrated sensors and machine learning models that automatically analyze process data and adjust parameters. This self-service capability eliminates the need for external expert intervention and complex manual testing protocols, reducing process complexity while maintaining high part quality
Solution Approach 2:
The system employs a universal machine learning framework that can handle multiple material types and geometries with a single integrated approach. The closed-loop control architecture serves multiple functions including real-time monitoring, parameter optimization, and quality assurance, thereby simplifying the overall manufacturing process complexity
3Manufacturing precision
If numerous tests and evaluations are conducted to determine optimal parameters, then manufacturing precision improves, but productivity decreases
Solution Approach 1:
The system performs preliminary optimization by using machine learning models to predict optimal parameters before actual manufacturing begins. The closed-loop control system is pre-configured with material-specific models that enable immediate parameter optimization, eliminating the need for time-consuming trial-and-error testing and significantly improving part development throughput
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 identify a reference process observable of a computer-generated part, receive input from at least one sensor during three-dimensional printing to identify an estimated process observable using feature extraction, and adjust at least one three-dimensional printing process parameter to reduce an error identified from a mismatch between the estimated process observable and the reference process observable.