| Abstract Scope |
Magnesium’s rapid corrosion necessitates advanced protective coatings and predictive models like machine learning (ML) to anticipate corrosion behavior. ML has proven effective in forecasting corrosion rates by capturing complex interactions among key factors. Building on existing research, this study pursues two main objectives. First, we aim to predict the in vitro corrosion current density and corrosion potential of micro-arc oxidation (MAO) magnesium coated implants based on well-established parameters, extending the model to include sol-gel coatings. Second, to enable this extension, a deep understanding of sol-gel coating parameters is essential. As a foundation for future work, we explore the effects of critical factors such as dipping time, hydroxyapatite (HA) concentration, and the number of coating layers on corrosion behavior. By integrating predictive modeling with coating advancements, this research contributes to improving magnesium’s corrosion resistance and broadening the applicability of ML in materials science. |