A brief review of machine learning-assisted Mg alloy design, processing, and property predictions

Abstract

Owing to the hexagonal close-packed (HCP) crystal structure inherent in Mg alloys, strong basal texture can readily be induced through the processes of rolling or extrusion. The anisotropy of the texture of Mg alloys impacts their stamping and forming capabilities, limiting their use in certain applications. Microalloying and shear deformation are currently the most common methods of weakening the texture of Mg alloys. Many shearing processes have been extensively studied, and given that they require complex equipment and make it difficult to achieve mass production, major attention has turned to studying the design of microalloys. Traditional trial-and-error approaches for developing micro-alloying confront many challenges, including longer test cycles and increasing expenses. The rapid advancement of big data and artificial intelligence opens up a new channel for the efficient advancement of metallic materials, specifically the application of machine learning to aid in the design of Mg alloys. ML modeling can be used to find correlations between features and attributes in data, allowing for the development and design of high-performance Mg alloys. The article provides an extensive overview of machine learning applications in Mg alloys. These include the discovery of high-performance alloys, the selection of coating designs, the design of Mg matrix composites, the prediction of second phases, the microstructure modification, optimization of rolling or extrusion parameters, and the prediction of mechanical and corrosion properties. In conclusion, challenges and prospects for the rational design of alloys with machine learning support were discussed.

Keywords

• Mg alloy
• Machine learning
• Strength
• Plasticity
• Microalloying