Researchers at MIT have developed a new technique using artificial intelligence to improve the performance of microstructured materials, such as those used in cars and airplanes. The new system integrates physical experiments, physics-based simulations, and neural networks to create materials with extraordinary performance.
The study focused on finding a balance between two critical properties of materials: stiffness and toughness. Using a large design space of two types of base materials, the team explored various spatial arrangements to discover optimal microstructures.
One key innovation in their approach was the use of neural networks as surrogate models for simulations, reducing the time and resources needed for material design. The research team combined physical trials with sophisticated simulations and used a high-performance computing framework to predict and refine the material characteristics before creating them.
While the journey has been challenging, the next steps for the team are focused on making the process more usable and scalable. Ultimately, they hope to see everything, from fabrication to testing and computation, automated in an integrated lab setup.
The research was published in Science Advances and was supported by Baden Aniline and Soda Factory (BASF).