Efficient Scenario Analysis for Optimal Adaptation of Bridge Networks under Deep Uncertainties through Knowledge Transfer
- Speaker: Dr. Minghui Cheng, Postdoctoral Associate, Systems Engineering, Cornell University
- Time & Date: 14:10-15:30, Friday, October 28, 2022
- Location: Online
- Zoom Link: https://ryerson.zoom.us/j/4612874120
Abstract
Due to deep uncertainties associated with climate change and socioeconomic growth, managing bridge networks faces the challenge to perform optimization for different scenarios. There exist a large number of scenarios when various sources of uncertainties, such as population growth and the increasing magnitude and frequency of natural hazards due to climate change, are compounded. Traditionally, scenarios are analyzed sequentially. However, when optimization for one single scenario is time-consuming, only a limited number of scenarios can be considered. To accelerate scenario analysis, this presentation introduces a novel scheme through knowledge transfer between scenarios. Specifically, after finishing the optimization of a certain number of scenarios, the analyses of any new scenarios are accelerated by utilizing the knowledge obtained from optimization of previous scenarios. The scheme builds on meta-learning-based surrogate modelling (MLSM), previously developed by Dr. Cheng and his colleagues, to realize the concept of knowledge transfer. The presentation first introduces MLSM and shows several applications. A proper definition of similar scenarios for adaptation of bridge networks under deep uncertainties is then given to stipulate the situation when knowledge transfer can occur. A bridge network in Camden County, New Jersey, is used as an illustrative example to demonstrate the computational efficiency of the proposed novel scheme. The full paper covered by the presentation can be found here.
About the Speaker
Dr. Minghui Cheng (Google Scholar Profile) is currently a postdoctoral associate at Systems Engineering, Cornell University. He obtained his Ph.D. in Structural Engineering at Lehigh University, USA, in 2021 under the supervision of Prof. Dan Frangopol. Prior to that, he earned his B.E. in Civil Engineering at Hunan University, China, in 2016. His research is primarily focused on (1) establishing digital twins for bridge networks, (2) optimal life-cycle management of structures and infrastructure systems, (3) realizing knowledge transfer in engineering analysis, and (4) calibrating decision-making models for civil engineering stakeholders. He is the recipient of multiple awards including University Fellowship and P.C. Rossin Doctoral Fellowship at Lehigh Univerisy and National Scholarship (twice) and Chinese Government Scholarship during his time at Hunan University. He has multiple publications in prestigious journals, such as Structural Safety, Reliability Engineering & System Safety, Computers & Structures, Journal of Bridge Engineering, among others. Two of them are selected into the ASCE Bridge Asset Management Collection.