The overarching goal of my research is to develop innovative data science methodologies that enable responsive, optimal, and intelligent decision-making in manufacturing. My work focuses on three interconnected research thrusts: (1) online process control and non-destructive evaluation, (2) cost-effective, scalable, and generalizable machine learning, and (3) multi-modal data fusion. By integrating advanced data science tools with physical manufacturing knowledge, my research leverages diverse data sources, including sensor signals, images, and 3D point clouds, to address complex challenges in modern manufacturing.
I have applied these methodologies to a broad spectrum of manufacturing applications, such as materials joining and assembly, additive manufacturing, two-photon lithography, machining, industrial drying, surface and 3D metrology, food processing, remanufacturing, and human-robot collaboration. The societal and industrial impacts of my work span multiple critical areas, including automotive, electrification and decarbonization, biomanufacturing, equity, rail, sustainability and energy, food, pulp and paper, and the Industrial Internet of Things (IIoT).