ISE Seminar Series - Conrad Tucker

Title: Artificial Intelligence and its Impact on Engineering Design and Manufacturing

Abstract:
AI has the potential to automate the main time/cost drivers of the engineering design and manufacturing process. The features of a product inform the form, function and behavior of the resulting design concept that can be subsequently created using traditional manufacturing/additive manufacturing methods. While there exists a wide range of computer aided design tools that seek to generate 3D design concepts, they are primarily parametric in nature and rely extensively on designers’ expertise, which may not always be readily available. The emergence of Generative AI has the potential to rapidly generate 3D engineering design concepts at scale. However, there is more to a design than simply its 3D form, as the design must perform a function and operate in an environment where its behavior may/may not perform as intended. Towards this end, physics-informed AI models are being developed that approximate real-world physics, hereby enabling engineering concepts to be evaluated in simulation environments in an efficient manner. As AI continues to advance in multiple dimensions across engineering, the fundamental question is what will be the role of human engineering designers in the future and how should engineering education curricula adapt?

Bio
Professor Conrad Tucker is the former Director of Carnegie Mellon University-Africa (CMU-Africa) and Associate Dean for International Programs-Africa. He is a Fellow of the American Society of Mechanical Engineers (ASME) and a Trustee Professor of Mechanical Engineering at Carnegie Mellon University. He holds courtesy appointments in Machine Learning, Robotics, Biomedical Engineering, and CyLab Security and Privacy. 

 Professor Tucker applies AI and machine learning to engineering design, manufacturing, and digital health. His data-driven, physics-aware methods use graph models and generative neural networks for three-dimensional design and validation. In additive manufacturing, he uses video and sensor data for real-time security, thermal prediction, and defect detection. His work has appeared high impact journals including Nature Communications, Materials & Design, and the Journal of Mechanical Design, with a recent project resulting in a U.S. patent.

 Professor Tucker has led approximately $5 million in research funded by the National Science Foundation, DARPA, AFOSR, ARL, ONR, and industry and philanthropic partners. His work has earned best-paper awards, influential publications, and academic and industrial adoption. He co-chaired the National Academy of Engineering (NAE) committee on digital-twin research and served on other NAE committees. He also served on the U.S. Chamber of Commerce AI Commission and is a member of the OECD expert group on AI risk and accountability.