AI-driven Advanced Materials-Manufacturing Innovation

M. Kolel-Veetil, S. Kalidindi
Naval Research Laboratory,
United States

Keywords: AI, ML, Advanced, Materials, Manufacturing, Innovation


The rich details of the material internal structures (including details of material chemistry), spanning a hierarchy of length scales from the sub-atomic to the macroscale, control the property combinations and/or performance characteristics needed to propel most advanced technologies. As a result, innovation efforts aimed at customizing the material's performance for a selected application need to explore extremely large design spaces. This challenge is the central focus of the federal Materials Genome Initiative (MGI). Emerging concepts and toolsets in AI/ML can become strong enablers for systematic mining and capture of Materials Knowledge needed to guide efficient and possibly autonomous explorations of the unimaginably large materials and process design spaces, while synergistically leveraging all available experimental and simulation data. In our work, we have designed and demonstrated specific AI/ML-based workflows capable of guiding such explorations in ways that systematically and optimally exploit all of the available toolsets (these typically include a variety of multiscale materials characterization techniques and physics-based simulation tools). The potential benefits of this targeted AI/ML toolset to advanced materials-manufacturing industry will be illustrated in this poster.