Hassel and Marianne Ledbetter MatSE Colloquium - "Towards autonomous in situ synchrotron solidification metallurgy: developing capabilities for rapidly mapping solidification transformation pathways and kinetics"

Metal-based additive manufacturing (AM) is a highly promising advanced manufacturing technique, but control of the resulting crystal structures and microstructural distributions has been a longstanding open challenge. I will present early prototyping results of an autonomous in situ AM test bed for high speed synchrotron-based measurement of phase and microstructure evolution during the highly non-equilibrium conditions induced by laser melting in metal additive manufacturing process. The main theme of the presentation is development of scientific machine learning capabilities for obtaining compact and structured scientifically relevant information from complex multimodal data, which is currently a common limitation across the emerging field of self-driving materials and chemistry labororatories. I present novel algorithms for multi-phase Bravais lattice determination and phase identification and subsequent quantitative analysis of the temporal evolution of the phase distribution. The phase evolution behavior determined by these measurements enables a dynamic experiment planning loop that uses active learning methods to efficiently map solidification kinetics information as a function of alloy composition and processing. I will discuss the potential acceleration for alloy and processing design and the opportunities for fusing this measurement capability with other structural and property characterization modalities. This research highlights important aspects of the challenges in automated characterization and symbolic hypothesis representation that are needed to advance self-driving laboratory systems from optimization harnesses to scientific hypothesis evaluation machines.