Machine Learning for Predicting Tensile Properties of Fiber-Reinforced Metal Matrix Composites

Fiber-reinforced metal matrix composites (FMMCs) hold broad application prospects in numerous fields due to their excellent comprehensive properties. The tensile properties of these materials, as a key performance indicator, play a decisive role in their engineering applications. Therefore, leveraging the data processing advantages and the ability to identify complex relationships of machine learning (ML) technology can significantly enhance the study of the tensile properties of fiber-metal matrix composites. This paper provides a comprehensive overview of machine learning algorithms and models, as well as the current status of ML in predicting the performance of fiber-reinforced composites. It discusses the application of ML technology in predicting the tensile properties of fiber-metal matrix composites, optimizing manufacturing processes, and elucidating the relationship between microstructure and performance. Additionally, it explores the challenges faced by ML in predicting material properties and offers insights into future development directions, aiming to provide a reference for advancing research and applications in this field.