Comparative study of dimension reduction methods for efficient design optimization
Efficient aerodynamic shape optimizations are realized in this research utilizing dimension reduction technologies. Several dimension reduction methods such as proper orthogonal decomposition, independent component analysis, kernel principal component regression and deep auto encoder, are investigat...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
The Japan Society of Mechanical Engineers
2023-06-01
|
Series: | Journal of Advanced Mechanical Design, Systems, and Manufacturing |
Subjects: | |
Online Access: | https://www.jstage.jst.go.jp/article/jamdsm/17/3/17_2023jamdsm0036/_pdf/-char/en |
_version_ | 1797755902599626752 |
---|---|
author | Wataru YAMAZAKI Nomin BUYANBAATAR |
author_facet | Wataru YAMAZAKI Nomin BUYANBAATAR |
author_sort | Wataru YAMAZAKI |
collection | DOAJ |
description | Efficient aerodynamic shape optimizations are realized in this research utilizing dimension reduction technologies. Several dimension reduction methods such as proper orthogonal decomposition, independent component analysis, kernel principal component regression and deep auto encoder, are investigated to reduce the dimensionality of design variables space. The number of design variables can be efficiently reduced by the proposed approach while obtained optimization results are comparable with that of a conventional optimization approach. The effect of each dominant mode is clarified in this study. A variable fidelity method is introduced by adopting a low-fidelity performance evaluation in the pre-process of the dimension reduction. By introducing the variable fidelity method, a multi objective aerodynamic shape optimization problem can be efficiently solved. Furthermore, design knowledge with respect to the tradeoff relationship between objective functions can be obtained from the results of dimension reduction. |
first_indexed | 2024-03-12T17:52:52Z |
format | Article |
id | doaj.art-b5e55811c5c140b1b27e77a0660efa2c |
institution | Directory Open Access Journal |
issn | 1881-3054 |
language | English |
last_indexed | 2024-03-12T17:52:52Z |
publishDate | 2023-06-01 |
publisher | The Japan Society of Mechanical Engineers |
record_format | Article |
series | Journal of Advanced Mechanical Design, Systems, and Manufacturing |
spelling | doaj.art-b5e55811c5c140b1b27e77a0660efa2c2023-08-03T00:04:49ZengThe Japan Society of Mechanical EngineersJournal of Advanced Mechanical Design, Systems, and Manufacturing1881-30542023-06-01173JAMDSM0036JAMDSM003610.1299/jamdsm.2023jamdsm0036jamdsmComparative study of dimension reduction methods for efficient design optimizationWataru YAMAZAKI0Nomin BUYANBAATAR1Department of Energy and Environment Science, Nagaoka University of TechnologyDepartment of Energy and Environment Science, Nagaoka University of TechnologyEfficient aerodynamic shape optimizations are realized in this research utilizing dimension reduction technologies. Several dimension reduction methods such as proper orthogonal decomposition, independent component analysis, kernel principal component regression and deep auto encoder, are investigated to reduce the dimensionality of design variables space. The number of design variables can be efficiently reduced by the proposed approach while obtained optimization results are comparable with that of a conventional optimization approach. The effect of each dominant mode is clarified in this study. A variable fidelity method is introduced by adopting a low-fidelity performance evaluation in the pre-process of the dimension reduction. By introducing the variable fidelity method, a multi objective aerodynamic shape optimization problem can be efficiently solved. Furthermore, design knowledge with respect to the tradeoff relationship between objective functions can be obtained from the results of dimension reduction.https://www.jstage.jst.go.jp/article/jamdsm/17/3/17_2023jamdsm0036/_pdf/-char/enaerodynamic shape optimizationmulti-objective optimizationdimension reductionvariable fidelity methodairfoil |
spellingShingle | Wataru YAMAZAKI Nomin BUYANBAATAR Comparative study of dimension reduction methods for efficient design optimization Journal of Advanced Mechanical Design, Systems, and Manufacturing aerodynamic shape optimization multi-objective optimization dimension reduction variable fidelity method airfoil |
title | Comparative study of dimension reduction methods for efficient design optimization |
title_full | Comparative study of dimension reduction methods for efficient design optimization |
title_fullStr | Comparative study of dimension reduction methods for efficient design optimization |
title_full_unstemmed | Comparative study of dimension reduction methods for efficient design optimization |
title_short | Comparative study of dimension reduction methods for efficient design optimization |
title_sort | comparative study of dimension reduction methods for efficient design optimization |
topic | aerodynamic shape optimization multi-objective optimization dimension reduction variable fidelity method airfoil |
url | https://www.jstage.jst.go.jp/article/jamdsm/17/3/17_2023jamdsm0036/_pdf/-char/en |
work_keys_str_mv | AT wataruyamazaki comparativestudyofdimensionreductionmethodsforefficientdesignoptimization AT nominbuyanbaatar comparativestudyofdimensionreductionmethodsforefficientdesignoptimization |