Transfer prior knowledge from surrogate modelling
A meta-learning approach
- authored by
- Minghui Cheng, Chao Dang, Dan M. Frangopol, Michael Beer, Xian-Xun Yuan
- Abstract
Surrogate modelling has emerged as a useful technique to study complex physical and engineering systems in various disciplines, especially for engineering analysis. Previous studies mostly focused on developing new surrogate models and/or applying existing surrogate models to practical problems. Despite the computational efficiency, the surrogate for a new task is often built from scratch and the knowledge gained from previous surrogate modelling for similar tasks is neglected. As the need for quickly modifying simulation models to reflect design changes has significantly increased, one potential solution is to utilize prior knowledge from surrogate modelling. In this study, a novel meta-learning-based surrogate modelling framework is presented. The framework includes two phases: a meta-training and a few-shot learning phase. A meta-model that represents a family of tasks and the adaptation of this model to a new task with few data points are the results of the first and second phase, respectively. The study specifies the scope of the framework by classifying similar tasks. Applications of the framework to global sensitivity analysis, optimization, and reliability analysis are also addressed. Four numerical experiments are performed to demonstrate the feasibility and applicability of the framework.
- Organisation(s)
-
Institute for Risk and Reliability
- External Organisation(s)
-
University of Liverpool
Tongji University
Lehigh University
Ryerson University
- Type
- Article
- Journal
- Computers and Structures
- Volume
- 260
- ISSN
- 0045-7949
- Publication date
- 02.2022
- Publication status
- Published
- Peer reviewed
- Yes
- ASJC Scopus subject areas
- Civil and Structural Engineering, Modelling and Simulation, Materials Science(all), Mechanical Engineering, Computer Science Applications
- Electronic version(s)
-
https://doi.org/10.1016/j.compstruc.2021.106719 (Access:
Closed)