About this Abstract |
Meeting |
2023 TMS Annual Meeting & Exhibition
|
Symposium
|
Algorithm Development in Materials Science and Engineering
|
Presentation Title |
M-14: Differential Property Prediction: A Machine Learning Approach to Experimental Design in Advanced Manufacturing |
Author(s) |
Loc Truong, WoongJo Choi, Colby Wight, Elizabeth Coda, Tegan Emerson, Keerti Kappagantula, Henry Kvinge |
On-Site Speaker (Planned) |
Elizabeth Coda |
Abstract Scope |
Advanced manufacturing techniques have enabled the production of materials with state-of-the-art properties. In many cases however, the development of physics-based models of these techniques are nascent and emerging comparatively, making designing and running experiments largely Edisonian. This is sub-optimal since experiments are cost-, time-, and labor-intensive. In this work we propose a machine learning framework, differential property classification (DPC), which enables an experimenter to use pattern matching capability for data-driven experimental design. DPC takes two possible experiment conditions and outputs a prediction of which will produce a more desirable performance. We demonstrate the success of DPC on AA7075 tube process design and mechanical property data. We show that by focusing on the need to choose between multiple candidate experimental parameters, we can reframe the challenging regression task of predicting material properties from processing parameters, into a classification task on which machine learning models can achieve good performance. |
Proceedings Inclusion? |
Planned: |
Keywords |
Aluminum, Machine Learning, Shaping and Forming |