Multifidelity approaches for uncertainty quantification

被引：6
作者：
Biehler J. [1 ]
Mäck M. [2 ]
Nitzler J. [1 ,3 ]
Hanss M. [2 ]
Koutsourelakis P.-S. [3 ]
Wall W.A. [1 ]
机构：
[1] Institute for Computational Mechanics, Technical University of Munich, Munich
[2] Institute of Engineering and Computational Mechanics, University of Stuttgart, Stuttgart
[3] hip of Continuum Mechanics, Technical University of Munich, Munich
来源：
GAMM Mitteilungen | 2019年 / 42卷 / 02期
关键词：
Bayesian; multifidelity; possibilistic; uncertainty quantification;
D O I：
10.1002/gamm.201900008
中图分类号：
学科分类号：
摘要：
The aim of this paper is to give an overview of different multifidelity uncertainty quantification (UQ) schemes. Therefore, different views on multifidelity UQ approaches from a frequentist, Bayesian, and possibilistic perspective are provided and recent developments are discussed. Differences as well as similarities between the methods are highlighted and strategies to construct low-fidelity models are explained. In addition, two state-of-the-art examples to showcase the capabilities of these methods and the tremendous reduction of computational costs that can be achieved when using these approaches are provided. © 2019 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim
引用
收藏
相关论文
共 75 条
[31]  
Robert C., Casella G., Monte Carlo Statistical Methods, (2013)
[32]  
Bourgund U., Bucher C.G., Importance Sampling Procedure Using Design Points (ISPUD)—A User's Manual, (1986)
[33]  
Bucher C.G., Struct. Saf., 5, 2, (1988)
[34]  
Ang G.L., Ang A.H.S., Tang W.H., J. Eng. Mech., 118, (1992)
[35]  
Au S.K., Beck J.L., Struct. Saf., 21, 2, (1999)
[36]  
Au S.K., Beck J.L., Struct. Saf., 25, 2, (2003)
[37]  
Katafygiotis L.S., Zuev K.M., Prob. Eng. Mech., 23, 2, (2008)
[38]  
Au S.K., Beck J.L., Prob. Eng. Mech., 16, 4, (2001)
[39]  
Peherstorfer B., Kramer B., Willcox K., J. Comput. Phys., 341, (2017)
[40]  
Williams C.K.I., Rasmussen C.E., Gaussian Processes for Machine Learning, (2006)
12345678