Title:

Research Progress of Technology Evolution and Artificial Intelligence in Engineering Design

Speaker:

Dr. Guanglu Zhang

Affiliation:

Carnegie Mellon University

When:

Monday, March 7, 2022 at 2:00:00 PM   Add to Calendar

Where:

MRDC Building, Room 4211

Host:

Dr. David Rosen
david.rosen@me.gatech.edu
4048949668

Abstract

This seminar presents my research progress of technology evolution and artificial intelligence (AI) in engineering design. The performance of a technology, such as automobiles, aircrafts, laptops, and smartphones, continuously changes over time. The prediction of the future performance of a technology is critical for designers, investors, and government officials to make sound R&D decisions, invest in promising technologies, and develop effective incentive policies. My research constructs an ecosystem model that predicts future technology performance and quantifies the technology interactions in a complex technology ecosystem with system, component, and fundamental layers. Notably, a significant trickle-down effect is an underlying assumption behind many government incentives, where the impact from an upper layer technology to a lower layer technology is referred to as a trickle-down effect. I use the ecosystem model to quantify the trickle-down effect in the technology ecosystem of passenger aircraft. I find limited trickle-down effect in the technology ecosystem and discuss the implications of the result. For AI in engineering design, my research focuses on identifying effective strategies to facilitate human-AI collaboration. Prior research shows that a well-trained AI can perform a specified design task as good as, or sometimes even better than, human designers. However, when an AI advises human designers to solve a design problem, the impact of AI on human designers are under-studied. I assess the impact of a deep learning AI on the performance, behavior, and perceived workload of human designers through a human subjects study. In another human subjects study, I evaluate the impact of a strategy of deception about the identity of an AI teammate on human designers, where some participants are told that they work with another human participant but in fact they work with an AI teammate. The results of these studies suggest that human-AI interaction and human perception of AI are critical for ensuring an effective human-AI collaboration in engineering design.

Biography

Dr. Zhang is a Research Scientist in the Department of Mechanical Engineering at Carnegie Mellon University. He graduated from Texas A&M University in 2019 with a PhD degree in Mechanical Engineering. He is the recipient of the Best Paper Award of 29th International Design Theory and Methodology Conference in 2017. His research paper also received an Honorable Mention for the 2020 ASME Journal of Mechanical Design Editors' Choice Award. His research interests include technology evolution, artificial intelligence in design, human-AI interaction, inverse problem, design optimization, and design and manufacturing for disability.

Notes

Join virtually - https://bluejeans.com/255573681/6685