|About this Abstract
||7th World Congress on Integrated Computational Materials Engineering (ICME 2023)
||Sustainable Aluminum Alloy Design Using Physics-informed Machine Learning
||Fatih G. Sen, Marat Latypov, Heath Murphy, Dasha Artsykhovska, Kyle Haines, Shruthi Kumar Raj, Aurele Mariaux, Sazol Das, Yudie Yuan, Vishwanath Hegadekatte
|On-Site Speaker (Planned)
||Fatih G. Sen
Aluminum has been increasingly the sustainable material of choice for aerospace, automotive and beverage cans due to its high strength-to-weight ratio and infinite recyclability. Aluminum recycling is surging, and more end of automotive life aluminum scrap will be available in the market. To minimize prime aluminum use, design of new aluminum alloys which can utilize more diverse sources of scrap is needed, while simultaneously satisfying the performance requirements for desired applications. In the present work, we have coupled scrap mass flow model with a physics-informed machine-learning framework to design sustainable aluminum alloys. Microstructural features pertaining to strength, formability, and corrosion properties we estimated using CALPHAD methods and integrated into machine learning framework. The model predictions for sustainable alloy chemistries were then validated through lab trials.