We are using computer vision, machine learning, and data analysis approaches to identify critical attributes of manufacturing feedstock materials, including those for advanced manufacturing, and then correlating those attributes to component performance to develop a system for predicting the performance of batches of materials. This new capability will significantly shorten feedstock-optimization cycles and accelerate the overall qualification and deployment process.
Han, T., et al. 2019. "Predicting Compressive Strength of Consolidated Solids from Features Extracted from SEM Images." TMS 2020 Annual Meeting and Exhibition, San Diego, CA. LLNL-ABS-779499.
Liu, S., et al. 2019. "Generative Counterfactual Introspection for Explainable Deep Learning." 7th IEEE Global Conference on Signal and Information Processing (GlobalSIP), Ottawa, Canada, October 2019. LLNL-PROC-779784.
Lawrence Livermore National Laboratory • 7000 East Avenue • Livermore, CA 94550
Operated by Lawrence Livermore National Security, LLC, for the Department of Energy's National Nuclear Security Administration.