September 14, 2021
September 14, 2021
Presenter: Xiaowei Yue, PhD
Virginia Polytechnic Institute & State University
Topic: Stochastic Surrogate Models: Method, Algorithm, and Engineering Applications
Time: 5 pm EST
Abstract: Surrogate models have been widely used in advanced design and manufacturing to tackle the high computational cost in high-fidelity simulation and digital twin. Due to sensing errors, actuating errors, and computational errors, uncertainties inevitably exist in engineering systems. With incorporating the influence of uncertainties, stochastic surrogate modeling has become an emerging field. We developed two stochastic surrogates: (1) Neural Process Aided Ordinary Differential Equation (NP-ODE); (2) Neural network Gaussian process considering input uncertainty. We show the relationships between deep neural networks, Gaussian process, and differential equations, and use their relationships to develop new physics-informed data analytics methods. We also demonstrate their applications in engineering simulations such as Finite Element simulation, Digital Twin, and Materials Science simulation.
Bio: Dr. Xiaowei Yue is an assistant professor at the Department of Industrial and Systems Engineering, Virginia Tech. He got his Ph.D. degree in industrial engineering, M.S. in Statistics from Georgia Tech. His research interests focus on machine learning for advanced manufacturing. He has published 23 papers in top-tier journals, 8 of these papers won the best paper awards/finalists. He obtained two best dissertation awards. He is a recipient of FTC Early Career Award from ASQ. He is a DoD MEEP Faculty Fellow. The methods Dr. Yue and his collaborators developed have been applied to nanomanufacturing, aerospace manufacturing, materials science, etc. Dr. Yue serves as an associate editor for the IISE Transactions and the Journal of Intelligent Manufacturing.
For questions contact: Dr. Weihong (Grace) Guo at firstname.lastname@example.org or Dr. Aziz Ezzat at email@example.com.