Additive Manufacturing Thermal Profiles for Material Property Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Additive manufacturing processes result in significant variations in thermal characteristics and material properties due to complex geometries, leading to inconsistencies in fabricated parts.
Innovation Solution
A system and method utilizing thermal data collection devices and machine-learning algorithms to predict material properties by analyzing thermal profiles of standard parts, storing data in a database, and using supervised learning models to forecast properties of future parts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If additive manufacturing is used to fabricate parts with complex geometries, then manufacturing flexibility and design freedom are improved, but variations in thermal characteristics and material properties increase
Solution Approach 1:
The system performs preliminary thermal modeling and simulation before actual additive manufacturing to predict thermal characteristics and material properties. By pre-calculating thermal profiles using finite element analysis and storing them in a database, the system prepares reference data that enables later comparison and quality assessment without requiring physical prototypes or extensive testing.
Solution Approach 2:
The patent replaces physical material testing and characterization with computational thermal modeling and machine learning algorithms. Instead of fabricating multiple test parts to determine material properties, the system uses thermal simulation models, infrared thermal imaging, and predictive algorithms to determine material properties virtually, reducing the need for physical experimentation.
2Measurement precision
If thermal characteristics are monitored during additive manufacturing, then material property prediction accuracy is improved, but measurement and detection complexity increases
Solution Approach 1:
The system employs infrared cameras that serve multiple functions: they capture thermal profiles during additive manufacturing, store data in databases, and enable both real-time monitoring and post-processing analysis. The same thermal imaging technology is used across different parts and manufacturing conditions, creating a universal measurement approach that simplifies the overall process despite the complexity of thermal measurements.
Solution Approach 2:
The patent introduces thermal modeling software and machine learning algorithms as intermediaries between raw thermal data and material property predictions. These computational tools process complex thermal profiles, compare them against database references, and translate thermal characteristics into meaningful material property estimates, reducing the complexity of direct measurement and interpretation.
3Measurement precision
If machine learning algorithms are used to predict material properties, then prediction accuracy is improved, but data processing requirements and computational resources increase
Solution Approach 1:
The system segments thermal data collection into discrete temperature profiles at specific locations and time points during additive manufacturing. By dividing the continuous thermal field into manageable data points and storing them as individual records in a database, the system makes large volumes of thermal data processable by machine learning algorithms while maintaining prediction accuracy.
Solution Approach 2:
The system performs preliminary data processing by storing thermal profiles and corresponding material properties in a structured database before machine learning analysis. This pre-organization of data into standardized formats with known ground truth values enables efficient training of predictive models without requiring complex real-time data processing during manufacturing.
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 prediction of material properties, allowing for virtual design and testing, reducing costs and improving quality assurance in additive manufacturing, especially for complex geometries.
Implementation Method 1
one or more infrared cameras for collecting thermal data associated with additive-manufactured standard parts
Data Source
AI summary
A method is provided for predicting material properties of a part to be additive-manufactured. The method includes additive-manufacturing a plurality of standard parts, and obtaining thermal profiles at select predetermined locations of physical samples of the plurality of standard parts during additive-manufacturing of the plurality of standard parts. The method also includes storing the thermal profiles and corresponding material properties of the physical samples of the plurality of standard parts in a database. The method further includes running a machine-learning algorithm to predict material properties of the part to be additive-manufactured based upon the thermal profiles and corresponding material properties of the physical samples of the plurality of standard parts stored in the database.