scholarly journals A hybrid sequential sampling strategy for sparse polynomial chaos expansion based on compressive sampling and Bayesian experimental design

2021 ◽  
Vol 386 ◽  
pp. 114130
Author(s):  
Bei-Yang Zhang ◽  
Yi-Qing Ni
Keyword(s):  
Experimental Design ◽  
Polynomial Chaos ◽  
Sequential Sampling ◽  
Sampling Strategy ◽  
Polynomial Chaos Expansion ◽  
Compressive Sampling ◽  
Chaos Expansion ◽  
Sparse Polynomial ◽  
Sparse Polynomial Chaos Expansion

scholarly journals Optimized Sparse Polynomial Chaos Expansion With Entropy Regularization

2021 ◽  
Author(s):  
SiJie Zeng ◽  
XiaoJun Duan ◽  
JiangTao Chen ◽  
Liang Yan
Keyword(s):  
Polynomial Chaos ◽  
Uncertainty Propagation ◽  
Entropy Change ◽  
Optimization Method ◽  
Polynomial Chaos Expansion ◽  
Chaos Expansion ◽  
Sparse Polynomial ◽  
Output Uncertainty ◽  
Sparse Polynomial Chaos Expansion ◽  
Fitting In

Abstract Sparse Polynomial Chaos Expansion(PCE) is widely used in various engineering fields to quantitatively analyse the influence of uncertainty, while alleviate the problem of dimensionality curse. However, current sparse PCE techniques focus on choosing features with the largest coefficients, which may ignore uncertainties propagated with high order features. Hence, this paper proposes the idea of selecting polynomial chaos basis based on information entropy, which aims to retain the advantages of existing sparse techniques while considering entropy change as output uncertainty. A novel entropy-based optimization method is proposed to update the state-of-the-art sparse PCE models. This work further develops an entropy-based synthetic sparse model, which has higher computational efficiency. Two benchmark functions and a CFD experiment are used to compare the accuracy and efficiency between the proposed method and classical methods. The results show that entropy-based methods can better capture the features of uncertainty propagation, and the problem of over-fitting in existing sparse PCE methods can be avoided.

Sign in / Sign up

Export Citation Format

Share Document