← Back to NASA Technology Projects
Completed TRL 3 (started at 1, targeting 3)
Project Objective
To apply ML.AI to analysis of the GRANTA Alloys Database and Similar Materials Databases. To characterize the relationships that exist between microscopic atomistic and thermodynamical properties.
Project Description
To apply ML.AI to analysis of the GRANTA Alloys Database and Similar Materials Databases. To characterize the relationships that exist between microscopic atomistic and thermodynamical properties and between macroscopic thermal-mechanical properties, and between themselves as well as to scale bridge between these. This is to be accomplished via nonlinear regression, Genetic Algorithms, Neural Networks. Long-term goals include being able to design from microscopic or ground up alloys based on the desired macroscopic thermal and mechanical properties. Also the converse, given a desired alloy thermo mechanical room scale properties, what are the underlying microscopic properties for the manufacturing and synthesis of such an alloy.
Project Results and Conclusions
Fully analyzed-characterized the ~1864 alloys GRANTA database and its ~20 variables for these alloys. And described what microscopic relations exist (for example between latent heat of formation, melting temperature, thermal conductivity, density, wt%, debye temperature, sound velocity, moduli of elasticity and bulk and shear et al.) as well as what macroscopic relations exist (between yield strength, tensile stress, hardness, fatigue, and so on.). Moreover found scale bridging between microscopic to macroscopic making possible predictive design. Moreover found inverse design methods. Two papers in writing by the team. One PhD candidate supported.
Predictively modeling novel alloys from atomistic components to room scale thermal mechanical properties is a hard task. Machine learning promises to make that path easier via correlations analysis and modeling.
Additionally and as a tool for characterizing existing worked alloys where sparse or incomplete data is available, the universal correlations obtainable via Machine Learning ML.AI make it possible to fill in the blanks even for these alloys, providing great insight to materials scientists and engineers.
And as always, NASA's mission depends crucially on materials and manufacturing these going hand in hand. Providing an understanding and a tool for materials prediction will be a large step forward, that in concert with ICME integrated computational materials engineering will advance capability significantly. We are seeing that in novel materials being advanced by NASA now (ICME predicted), and we expect many more innovations.
Listed on TechPort itself — the most direct way to ask about this specific project.
This is early/mid-stage (TRL 3) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.
None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.