Machine learning-guided accelerated discovery of structure-property correlations in lean magnesium alloys for biomedical applications

• DOI: 10.1016/j.jma.2024.06.008
• Publication Date: 2024-06-28T13:36:37Z
• Authors: Sreenivas Raguraman; Maitreyee Sharma ...; Tram Nguyen; Ryan McGovern; Andrew Kim; Adam J. Griebel; Paulette Clancy; Timothy P. Weihs
• Keywords: Biocompatibility

Magnesium alloys are emerging as promising alternatives to traditional orthopedic implant materials thanks their biodegradability, biocompatibility, and impressive mechanical characteristics. However, rapid in-vivo degradation presents challenges, notably in upholding integrity over time. This study investigates the impact of high-temperature thermal processing on attributes a lean Mg-Zn-Ca-Mn alloy, ZX10. Utilizing rapid, cost-efficient characterization methods like X-ray diffraction optical, we swiftly examine microstructural changes post-thermal treatment. Employing Pearson correlation coefficient analysis, unveil relationship between properties critical targets (properties): hardness corrosion resistance. Additionally, leveraging least absolute shrinkage selection operator (LASSO), pinpoint dominant factors among closely correlated variables. Our findings underscore significant role grain size refinement strengthening predominance ternary Ca2Mg6Zn3 phase behavior. suggests that achieving an optimal blend strength resistance is attainable through fine grains reduced concentration phases. thorough investigation furnishes valuable insights into intricate interplay processing, structure, magnesium alloys, thereby advancing development superior biodegradable materials.