Support Vector Machine Applied to the Optimal Design of Composite Wing Panels
One of the core technologies in lightweight structures is the optimal design of laminated composite stiffened panels. The increasing tailoring potential of new materials added to the simultaneous optimization of various design regions, leading to design spaces that are vast and non-convex. In order...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/8/11/328 |
| _version_ | 1797511621467176960 |
|---|---|
| author | Rogério Rodrigues dos Santos Tulio Gomes de Paula Machado Saullo Giovani Pereira Castro |
| author_facet | Rogério Rodrigues dos Santos Tulio Gomes de Paula Machado Saullo Giovani Pereira Castro |
| author_sort | Rogério Rodrigues dos Santos |
| collection | DOAJ |
| description | One of the core technologies in lightweight structures is the optimal design of laminated composite stiffened panels. The increasing tailoring potential of new materials added to the simultaneous optimization of various design regions, leading to design spaces that are vast and non-convex. In order to find an optimal design using limited information, this paper proposes a workflow consisting of design of experiments, metamodeling and optimization phases. A machine learning strategy based on support vector machine (SVM) is used for data classification and interpolation. The combination of mass minimization and buckling evaluation under combined load is handled by a multi-objective formulation. The choice of a deterministic algorithm for the optimization cycle accelerates the convergence towards an optimal design. The analysis of the Pareto frontier illustrates the compromise between conflicting objectives. As a result, a balance is found between the exploration of new design regions and the optimal design refinement. Numerical experiments evaluating the design of a representative upper skin wing panel are used to show the viability of the proposed methodology. |
| first_indexed | 2024-03-10T05:47:49Z |
| format | Article |
| id | doaj.art-220fa2ee18f24f51ae4a63f88384a2b4 |
| institution | Directory Open Access Journal |
| issn | 2226-4310 |
| language | English |
| last_indexed | 2024-03-10T05:47:49Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj.art-220fa2ee18f24f51ae4a63f88384a2b42023-11-22T21:57:43ZengMDPI AGAerospace2226-43102021-11-0181132810.3390/aerospace8110328Support Vector Machine Applied to the Optimal Design of Composite Wing PanelsRogério Rodrigues dos Santos0Tulio Gomes de Paula Machado1Saullo Giovani Pereira Castro2Division of Mechanical Engineering, Aeronautics Institute of Technology, São José dos Campos 12228-900, BrazilEmbraer SA, São José dos Campos 12227-901, BrazilFaculty of Aerospace Engineering, Delft University of Technology, 2629 HS Delft, The NetherlandsOne of the core technologies in lightweight structures is the optimal design of laminated composite stiffened panels. The increasing tailoring potential of new materials added to the simultaneous optimization of various design regions, leading to design spaces that are vast and non-convex. In order to find an optimal design using limited information, this paper proposes a workflow consisting of design of experiments, metamodeling and optimization phases. A machine learning strategy based on support vector machine (SVM) is used for data classification and interpolation. The combination of mass minimization and buckling evaluation under combined load is handled by a multi-objective formulation. The choice of a deterministic algorithm for the optimization cycle accelerates the convergence towards an optimal design. The analysis of the Pareto frontier illustrates the compromise between conflicting objectives. As a result, a balance is found between the exploration of new design regions and the optimal design refinement. Numerical experiments evaluating the design of a representative upper skin wing panel are used to show the viability of the proposed methodology.https://www.mdpi.com/2226-4310/8/11/328multi-objective optimizationstiffened panelscomposite winglayout optimizationsizing optimizationbuckling |
| spellingShingle | Rogério Rodrigues dos Santos Tulio Gomes de Paula Machado Saullo Giovani Pereira Castro Support Vector Machine Applied to the Optimal Design of Composite Wing Panels Aerospace multi-objective optimization stiffened panels composite wing layout optimization sizing optimization buckling |
| title | Support Vector Machine Applied to the Optimal Design of Composite Wing Panels |
| title_full | Support Vector Machine Applied to the Optimal Design of Composite Wing Panels |
| title_fullStr | Support Vector Machine Applied to the Optimal Design of Composite Wing Panels |
| title_full_unstemmed | Support Vector Machine Applied to the Optimal Design of Composite Wing Panels |
| title_short | Support Vector Machine Applied to the Optimal Design of Composite Wing Panels |
| title_sort | support vector machine applied to the optimal design of composite wing panels |
| topic | multi-objective optimization stiffened panels composite wing layout optimization sizing optimization buckling |
| url | https://www.mdpi.com/2226-4310/8/11/328 |
| work_keys_str_mv | AT rogeriorodriguesdossantos supportvectormachineappliedtotheoptimaldesignofcompositewingpanels AT tuliogomesdepaulamachado supportvectormachineappliedtotheoptimaldesignofcompositewingpanels AT saullogiovanipereiracastro supportvectormachineappliedtotheoptimaldesignofcompositewingpanels |