2021
DOI: 10.1016/j.compstruct.2021.113715
|View full text |Cite
|
Sign up to set email alerts
|

Progressive design of gradually stiffer metamaterial using surrogate model

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
4
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
2

Relationship

2
7

Authors

Journals

citations
Cited by 13 publications
(4 citation statements)
references
References 40 publications
0
4
0
Order By: Relevance
“…For the parametric optimization of chiral metamaterials based on the surrogate model, first, a reasonable sample space was designed. The sampling points were initially selected as input variables in the sample space using the Latin hypercube sampling method [ 42 ]. Each sampling point was distributed as uniformly as possible in the sample space to ensure the global validity of the surrogate model throughout the entire design space.…”
Section: Parametric Optimization Of Chiral Metamaterialsmentioning
confidence: 99%
“…For the parametric optimization of chiral metamaterials based on the surrogate model, first, a reasonable sample space was designed. The sampling points were initially selected as input variables in the sample space using the Latin hypercube sampling method [ 42 ]. Each sampling point was distributed as uniformly as possible in the sample space to ensure the global validity of the surrogate model throughout the entire design space.…”
Section: Parametric Optimization Of Chiral Metamaterialsmentioning
confidence: 99%
“…Following the recent advances in the data-driven and machine learning (ML) technological elds, it has been now technically feasible to use surrogate models for computationally expensive optimization (Kim & Boukouvala, 2020;Luo et al, 2019). Recently, a variety of ML models have been employed for surrogates (e.g., radial basis function networks, arti cial neural networks, kriging model), replacing timeor resource-intensive numerical simulations or physical experiments, such as experiments for progressive design of gradually stiffer metamaterial and aerodynamic design based on computational uid dynamic (CFD) simulations, and then drive the EAs for iterative optimization (Jin et al, 2019;Ye et al, 2021). According to whether new data is allowed to be actively generated by the EAs, data-driven is divided into o ine and online methodologies.…”
Section: Introductionmentioning
confidence: 99%
“…It is difficult to complete a complex model description of porous acoustic metamaterials using conventional acoustic materials. Therefore, this study improves the traditional optimization design method and proposes a full-cycle interactive progressive (FIP) design scheme for porous acoustic metamaterials [ 10 , 11 ]. FIP design is a full-cycle optimization method that seeks the optimal design in a gradient and interactively adjusts the design direction [ 12 ].…”
Section: Introductionmentioning
confidence: 99%