Wire 3D Printing Data Models for Material Property Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing additive manufacturing technologies struggle to accurately predict material properties and quality of 3D objects, particularly in wire-based metal printing, due to the complex interactions of process parameters and ambient conditions affecting thermal history and grain structure.
Innovation Solution
A method and system that utilize process input parameters, measurements, and analysis techniques such as statistical process control, machine learning, and computational models to predict intermediate states and final material properties of 3D objects by analyzing feedstock heating and deposition processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If process input parameters and measurements are used to predict material properties and quality, then prediction accuracy of material properties and quality is improved, but device complexity increases due to need for multiple sensors, computational models, and data processing systems
Solution Approach 1:
The system segments the prediction process into distinct functional modules: sensor data acquisition, thermal history calculation, microstructure prediction, and property prediction. Each module handles specific aspects of the complex prediction task, making the overall system more manageable and maintainable while achieving high prediction accuracy through coordinated operation of these specialized components
Solution Approach 2:
The system introduces intermediate computational models as mediators between raw sensor measurements and final material property predictions. These intermediaries (thermal history calculators, microstructure predictors) transform and interpret raw data into meaningful predictions, reducing the direct complexity burden on the hardware while maintaining high prediction accuracy through sophisticated data processing
2Measurement precision
If thermal history and microstructure predictions are calculated to improve material property prediction, then prediction accuracy is improved, but loss of time increases due to computational processing requirements
Solution Approach 1:
The system performs preliminary calculations of thermal history and microstructure predictions during the additive manufacturing process itself, rather than waiting until after production. By calculating these intermediate states in real-time as the part is being built, the system prepares prediction data in advance, enabling rapid final property predictions without time-consuming post-processing computations
Solution Approach 2:
The prediction system operates continuously throughout the additive manufacturing process, with thermal history and microstructure calculations updating as new layers are deposited. This continuous operation eliminates idle computational time between manufacturing stages, maintaining steady progress toward final property predictions and reducing total prediction time while preserving accuracy through ongoing data accumulation
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 precise prediction of material properties and quality measures of 3D objects, including strength, toughness, and resistance to fatigue, by processing measured parameters against predicted states, enhancing the control and reliability of the manufacturing process.
Implementation Method 1
directing current through the feedstock to melt (e.g., via Joule heating) the feedstock
Data Source
AI summary
Disclosed herein are systems and methods for using printing process data to predict quality measures for three-dimensional (3D) printed objects and properties of the materials comprising the 3D objects. Printing may be performed using resistive or Joule printing. The system may include a computer communicatively coupled to a 3D printing apparatus, which may store printing parameters. The 3D printing apparatus may be able to take measurements during a print job, and record those measurements in memory. The 3D printing apparatus may also be able to record printing states before, during, and/or after printing. A combination of printing states, printing parameters, and measurements may be analyzed, for example, by a machine learning algorithm, in order to predict material properties and quality measures.


