Thomas Han | 19-SI-001
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.
Publications, Presentations, and Patents
Gallagher, T., et al. 2020. "Predicting Compressive Strength of Consolidated Molecular Solids Using Computer Vision and Deep Learning." Materials and Design 190 (108541). doi: 10.1016/j.matdes.2020.108541. LLNL-JRNL-774813
Hiszpanski, A. M., et al. 2020. "Nanomaterial Synthesis Insights from Machine Learning of Scientific Articles by Extracting, Structuring, and Visualizing Knowledge." Journal of Chemical Information Modeling 60 (6): 2876–2887. doi: 10.1021/acs.jcim.0c00199. LLNL-JRNL-779959
Kim, H., et al. 2020. "Machine Vision-Driven Automatic Recognition of Particle Size and Morphology in SEM Images." Nanoscale. LLNL-JRNL-809488
Li, Q., et al. 2020. "MR-GAN: Manifold Regularized Generative Adversarial Networks." Mathematical and Scientific Machine Learning Conference (MSML 2020), July 2020 (online). LLNL-CONF-798660
Zhang, J., et al. 2020. "Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning." LLNL-PRES-811597