| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Melt Processing, Casting and Recycling
|
| Presentation Title |
A PoDFA Benchmarking Study Between Manual and AI Supervised Machine Learning Methods to Evaluate Inclusions in Wrought and Foundry Aluminum Alloys |
| Author(s) |
Pascal Gauthier, Vincent Bilodeau, John Sosa |
| On-Site Speaker (Planned) |
John Sosa |
| Abstract Scope |
The PoDFA inclusions measurement is achieved by identifying the inclusions and their concentration in the melt for each type with a trained operator. The standard manual technique is non-efficient and requires a lot of time, effort and can generate important variations in PoDFA results for the reproducibility and the repeatability. In the past, there were many unsuccessful attempts to automatically detect, count and to classify all inclusion types due to the complexity of the application. Discs sampling, image artifacts, polishing defects, metallurgical constituents are some examples that can interfere with the inclusions detection and the measurement methodology. The implementation of supervised machine learning algorithms are necessary to automate features detection, thresholding and classification steps. The benchmarking study was achieved between the standard PoDFA methodology compared to the artificial intelligent way. Results show that the new technique exhibits a good correlation and a high potential for an industrial use. |
| Proceedings Inclusion? |
Planned: Light Metals |
| Keywords |
Aluminum, Solidification, Machine Learning |