About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Environmental Degradation of Multiple Principal Component Materials
|
| Presentation Title |
Accelerated Discovery of Corrosion-Resistant Co-Cr-Fe-Ni High-Entropy Alloys via Deep Learning |
| Author(s) |
Zhengyu Zhang, Wenjun Cai |
| On-Site Speaker (Planned) |
Wenjun Cai |
| Abstract Scope |
Designing alloys with exceptional corrosion resistance in diverse environments, particularly in acidic or chloride-rich conditions, remains a major challenge in materials science. Traditional trial-and-error methods are often inefficient and limit the exploration of the vast compositional space of non-equiatomic high-entropy alloys (HEAs). This study introduces a deep learning model that integrates physics-based descriptors to predict corrosion rates in Co-Cr-Fe-Ni HEAs. Trained on approximately 1,400 literature data points and refined with 35 new experimental data points from underexplored compositional space, this machine learning model enables precise tuning of alloy compositions to achieve targeted corrosion rates. Its effectiveness was demonstrated through the discovery of novel HEAs with corrosion resistance superior to stainless steel. This framework accelerates alloy design, reduces costs, and offers a transformative tool for advancing corrosion science. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
High-Entropy Alloys, Environmental Effects, Machine Learning |