A surrogate accelerated multicanonical Monte Carlo method for uncertainty quantification

JOURNAL OF COMPUTATIONAL PHYSICS

卷:321

Article

Wu, Keyi¹  Li, Jinglai^2,3 

[1] Shanghai Jiao Tong Univ, Zhiyuan Coll, Dept Math, Shanghai 200240, Peoples R China

[2] Shanghai Jiao Tong Univ, Inst Nat Sci, Dept Math, Shanghai 200240, Peoples R China

[3] Shanghai Jiao Tong Univ, MOE Key Lab Sci & Engn Comp, Shanghai 200240, Peoples R China

关键词: Gaussian processes;    Multicanonical Monte Carlo;    Uncertainty quantification;   

DOI  :  10.1016/j.jcp.2016.06.020

来源: Elsevier

【 摘 要 】

In this work we consider a class of uncertainty quantification problems where the system performance or reliability is characterized by a scalar parametery y. The performance parameter y is random due to the presence of various sources of uncertainty in the system, and our goal is to estimate the probability density function (PDF) of y. We propose to use the multicanonical Monte Carlo (MMC) method, a special type of adaptive importance sampling algorithms, to compute the PDF of interest. Moreover, we develop an adaptive algorithm to construct local Gaussian process surrogates to further accelerate the MMC iterations. With numerical examples we demonstrate that the proposed method can achieve several orders of magnitudes of speedup over the standard Monte Carlo methods. (C) 2016 Elsevier Inc. All rights reserved.

【 授权许可】

Free