An improved sequential multi-objective robust optimisation approach considering interval uncertainty reduction under mixed uncertainties

Hua, Wei; Shu, Leshi; Yang, Yang; Zhou, Qi; Zhong, Linjun; Jiang, Ping

doi:10.1080/09544828.2020.1858475

Cited by 6 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, the kriging model has been used to predict the lift coefficient of airfoil (Chen et al, 2019(Chen et al, , 2020Namura et al, 2017). Furthermore, based on kriging, optimization methods including efficient global optimization for single and multiobjective problems and global sensitivity analysis methods (Cheng et al, 2020;Van Steenkiste et al, 2019) have been developed and applied to solve practical problems from aerodynamic (He et al, 2020;Wang et al, 2018) or structural (Wei et al, 2020) design applications. However, the computational cost for tuning sufficiently accurate kriging for high-dimensional applications becomes prohibitive.…”

Section: Introductionmentioning

confidence: 99%

An efficient gradient-enhanced kriging modeling method assisted by fast kriging for high-dimension problems

He,

Tan,

et al. 2023

HFF

View full text Add to dashboard Cite

Purpose The modeling cost of the gradient-enhanced kriging (GEK) method is prohibitive for high-dimensional problems. This study aims to develop an efficient modeling strategy for the GEK method. Design/methodology/approach A two-step tuning strategy is proposed for the construction of the GEK model. First, an auxiliary kriging is built efficiently. Then, the hyperparameter of the kriging model is served as a good initial guess to that of the GEK model, and a local optimal search is further used to explore the search space of hyperparameter to guarantee the accuracy of the GEK model. In the construction of the auxiliary kriging, the maximal information coefficient is adopted to estimate the relative magnitude of the hyperparameter, which is used to transform the high-dimension maximum likelihood estimation problem into a one-dimensional optimization. The tuning problem of the auxiliary kriging becomes independent of the dimension. Therefore, the modeling efficiency can be improved significantly. Findings The performance of the proposed method is studied with analytic problems ranging from 10D to 50D and an 18D aerodynamic airfoil example. It is further compared with two efficient GEK modeling methods. The empirical experiments show that the proposed model can significantly improve the modeling efficiency without sacrificing accuracy compared with other efficient modeling methods. Originality/value This paper developed an efficient modeling strategy for GEK and demonstrated the effectiveness of the proposed method in modeling high-dimension problems.

show abstract