| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Magnesium Technology 2024
|
| Presentation Title |
Machine learning Guided Accelerated Discovery of Structure-Property Correlations in Lean Magnesium Alloys for Biomedical Applications |
| Author(s) |
Sreenivas Raguraman, Ryan McGovern, Andrew Kim, Veronica Ivanovskaya, Tram Nguyen, Tunde Ayodeji, Adam Griebel, Timothy Weihs |
| On-Site Speaker (Planned) |
Sreenivas Raguraman |
| Abstract Scope |
Magnesium alloys present a compelling alternative to conventional orthopedic implant materials due to their biodegradability, biocompatibility, and impressive mechanical characteristics. However, their rapid deterioration in vivo poses a challenge to practical applications, jeopardizing their mechanical integrity. This study delves into the evolution of mechanical and degradation properties after the alloys are subjected to high-temperature thermal processing. Utilizing efficient characterization techniques such as X-ray diffraction and microscopy, we swiftly assessed microstructural changes post-thermal treatment. We conduct a Pearson correlation coefficient analysis to unravel the relationship between the individual microstructural features and the targets, namely hardness and corrosion. We also employ feature selection machine learning methods, such as LASSO, to identify the dominant microstructural factor among these closely correlated variables. The results reveal the influential roles of grain boundary and strain hardening in enhancing hardness and the dominant impact of dislocation density and precipitates on corrosion. This thorough investigation offers valuable insights into the intricate relationships between processing, structure, and properties in magnesium alloys, thereby paving the way for the development of superior biodegradable implant materials. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Magnesium, Biomaterials, Machine Learning |