Project Grant 2151667

This $255,934 National Science Foundation Technology, Innovation, and Partnerships grant will support Exlattice, Inc.'s development of machine learning-powered additive manufacturing simulation software. Under the SBIR Phase I Project Grant, Exlattice will create a proof-of-concept for 3-5 orders of magnitude faster process simulation software to predict manufacturing failures from high temperature, residual distortion, and residual stresses. The proposed hybrid data-driven and physics-based simulation framework includes developing feature-driven and process parameter-based transfer learning deep learning models. These models will couple with finite element methods to replace the most time-consuming steps in traditional part-scale additive manufacturing simulation, implementing a one-step approach. The project also aims to apply and benchmark hybrid datasets from additive manufacturing physical modeling, 3D scanning, and in-situ monitoring to train and scale the models. Exlattice will demonstrate technological advantages through pilot testing and developing streamlined user interfaces and application programming interfaces under this August 15, 2022 award, which concludes on July 31, 2023.