About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Environmentally Assisted Cracking: Theory and Practice
|
| Presentation Title |
Machine Learning-Driven Design of Aluminum Alloys With Optimized Tribocorrosion Resistance |
| Author(s) |
Wenjun Cai |
| On-Site Speaker (Planned) |
Wenjun Cai |
| Abstract Scope |
Aluminum alloys are widely used in structural applications for their low density, high strength-to-weight ratio, and corrosion resistance. However, in complex environments involving both mechanical wear and electrochemical attack, such as tribocorrosion, these alloys often suffer accelerated degradation due to wear-induced-depassivation. Using a validated multiphysics finite element model, we simulate tribocorrosion behavior across a wide material property space defined by six key parameters. An ensemble of artificial neural networks is trained to predict surface damage and material loss, dramatically reducing computational cost. Our model identifies corrosion current density and yield strength as the most influential parameters governing tribocorrosion performance. The genetic algorithms optimization then efficiently searches for optimal property combinations that balance mechanical and electrochemical requirements. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Aluminum, Environmental Effects, Computational Materials Science & Engineering |