Mechanical behavior of materials based on big data and machine learning finds broad applications in fields such as plasticity, fatigue and fracture, and multi-scale simulation. It holds particular significance for studying aerospace structural materials and energy materials. Materials in these domains often operate under extreme conditions—such as high temperature, high pressure, and high stress—making the study of their mechanical properties, life prediction, and failure behavior critically important. Traditional experimental approaches are often time-consuming and labor-intensive, posing challenges for rapid iteration in material design. Big data and machine learning provide powerful tools to address this difficulty.

In aerospace structural materials, which require high strength, light weight, and fatigue resistance, big data analytics can collect performance data of various materials under complex stress states. Combined with machine learning models, this approach can accelerate material design and optimize predictions for plastic deformation, fatigue life, and fracture toughness. Moreover, multi-scale simulation can link atomic-scale microstructure with macroscopic mechanical performance, revealing the failure mechanisms of materials under high-stress conditions.

In the field of energy materials—especially those used in energy storage, power transmission, and new energy applications—excellent durability and long-term stability are essential. Machine learning can leverage large volumes of historical data to predict material service life and optimize microstructures to enhance performance, thereby advancing the development of next-generation energy materials. This research direction employs data-driven methods to accelerate the discovery and optimization of high-performance materials, fostering innovation in the aerospace and energy sectors.