3D Weld Microhardness Prediction from Thermal History
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for obtaining three-dimensional microhardness distributions of welds are time-consuming and heavily reliant on physical testing, making them inefficient and labor-intensive.
Innovation Solution
A system and method utilizing a processor programmed to receive temperature and composition data, determine peak temperature values and cooling rates, and apply machine learning to predict three-dimensional microhardness distributions of welds, reducing the need for extensive physical testing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional physical testing methods are used to obtain 3D microhardness distribution, then measurement precision is improved, but productivity deteriorates due to time-consuming and labor-intensive procedures
Solution Approach 1:
The patent creates a virtual copy of the physical welding process through computational simulation. A digital twin of the weld is generated with predicted microhardness distribution based on process parameters, eliminating the need for extensive physical testing while maintaining measurement accuracy. The simulation model replicates the thermal history and microstructural evolution to produce accurate predictions.
Solution Approach 2:
The patent replaces the mechanical physical testing system with a computational simulation system. Instead of physically cutting, mounting, and testing weld specimens with microhardness testers, the system uses computer-based thermal-metallurgical models to predict microhardness distribution, dramatically improving productivity while maintaining measurement precision.
2Measurement precision
If extensive physical testing is performed to obtain accurate 3D microhardness distribution, then measurement precision is improved, but loss of time increases significantly
Solution Approach 1:
The patent performs preliminary computational analysis by simulating the welding process and predicting microhardness distribution before any physical testing occurs. The simulation model pre-calculates the thermal history and microstructural evolution, providing accurate predictions that eliminate or minimize the need for time-consuming physical testing and post-processing analysis.
Solution Approach 2:
The patent creates a virtual representation of the weld with predicted microhardness values at multiple 3D locations. This digital copy provides all necessary measurement data instantaneously without requiring physical specimen preparation, mounting, and testing at each location, thereby eliminating time loss while maintaining measurement precision.
3Productivity
If machine learning methods are used to predict microhardness distribution, then productivity is improved by reducing physical testing, but device complexity increases due to computational requirements
Solution Approach 1:
The patent transforms the complex physical metallurgical processes into simplified computational parameters. By identifying key input parameters (welding conditions, material composition, thermal history) and their relationships with microhardness output, the system creates a predictive model that balances computational complexity with prediction accuracy, improving productivity without excessive device complexity.
Solution Approach 2:
The patent introduces a computational simulation model as an intermediary between the physical welding process and the final microhardness measurement. This intermediary layer translates process parameters into predicted microhardness distribution, reducing the need for direct physical testing while managing system complexity through established thermal-metallurgical modeling approaches.
Data Source
AI summary
Systems and methods are provided for predicting microhardness properties of a weld that defines a weld joint between at least two workpieces. The system includes a processor programmed to: receive temperature data that includes temperature values each attributed to a corresponding one of a plurality of points of the weld at corresponding times during a welding process used to produce the weld, determine peak temperature values and cooling rate values for each of the points of the weld based on the temperature values, predict a three-dimensional (3D) distribution of microhardness values of the weld based on a machine learning method that evaluates the peak temperature values and the cooling rate values, and generate display data based on the 3D distribution of microhardness values.