Abstract

In the rapidly evolving landscape of advanced manufacturing, the convergence of physics-based modeling and data-driven techniques is opening new frontiers for process innovation and materials design. This panel brings together leading experts across disciplines to explore the transformative potential of hybrid approaches in manufacturing. Hybrid approaches refer to the convergence of materials, processes, and data science from macro to quantum length scales. Building on Jian Cao’s lecture on the use of machine learning to accelerate the physics-based simulation, active sensing, and process control for different manufacturing processes, the discussion will examine how these methods address complexity in design spaces, enable real-time process control, and extend to broader manufacturing processes and applications. Panelists will consider both the opportunities and the challenges of implementing hybrid frameworks at scale and reflect on how such innovations can shape the future of manufacturing research, education and industry collaboration.

Moderator

• Martin Jun, Professor of Mechanical Engineering - Co-moderator
• Michael Sealy, Associate Professor Of Mechanical Engineering - Co-moderator

Panelists

• Jian Cao, Cardiss Collins Professor of Mechanical Engineering and (by courtesy) Civil and Environmental Engineering and Materials Science and Engineering, Director, Northwestern Initiative for Manufacturing Science and Innovation (NIMSI), and Associate Vice President for Research, Northwestern University
• Ajay Malshe, R. Eugene and Susie E. Goodson Distinguished Professor of Mechanical Engineering
• Byron Pipes, John L. Bray Distinguished Professor of Engineering
• Ali Shakouri, Associate Dean for Research and Innovation, and Professor of Electrical and Computer Engineering