scholarly journals On the Combined Effect of Design-space Dimensionality Reduction and Optimization Methods on Shape Optimization Efficiency

2018 ◽  
Author(s):  
Danny D'Agostino ◽  
Andrea Serani ◽  
Matteo Diez
Keyword(s):  
Dimensionality Reduction ◽  
Shape Optimization ◽  
Design Space ◽  
Optimization Methods ◽  
Combined Effect ◽  
Optimization Efficiency

scholarly journals A GAN-based dimensionality reduction technique for aerodynamic shape optimization

2021 ◽  
Author(s):  
Jun Zhang ◽  
Wenzheng Wang ◽  
Qiuyu Wu ◽  
Liwei Hu
Keyword(s):  
Dimensionality Reduction ◽  
Shape Optimization ◽  
Design Space ◽  
Reduction Technique ◽  
Aerodynamic Shape Optimization ◽  
Generative Adversarial Network ◽  
Aerodynamic Shape ◽  
Adversarial Network ◽  
Dimensionality Reduction Technique ◽  
Dynamics Simulations

Abstract Aerodynamic shape optimization (ASO) based on computational fluid dynamics simulations is extremely computationally demanding because a search needs to be performed in a high-dimensional design space. One solution to this problem is to reduce the dimensionality of the design space for aircraft optimization. Hence, in this study, a dimensionality reduction technique is designed based on a generative adversarial network (GAN) to facilitate ASO. The novel GAN model is developed by combining the GAN with airfoil curve parameterization and can directly produce realistic and highly accurate airfoil curves from input data of aerodynamic shapes. In addition, the respective interpretable characteristic airfoil variables can be obtained by extracting latent codes with physical meaning, while reducing the dimensionality of the airfoil design space. The results of simulation experiments show that the proposed technique can significantly improve the optimization convergence rate of the ASO process.

scholarly journals An Efficient Surrogate-Based Optimization Method for BWBUG Based on Multifidelity Model and Geometric Constraint Gradients

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Daiyu Zhang ◽  
Bei Zhang ◽  
Zhidong Wang ◽  
Xinyao Zhu
Keyword(s):  
Shape Optimization ◽  
Optimization Methods ◽  
Optimization Method ◽  
Geometric Constraints ◽  
Geometric Constraint ◽  
High Fidelity ◽  
Surrogate Based Optimization ◽  
Parameterized Model ◽  
Effectiveness And Efficiency ◽  
Optimization Efficiency

Performing shape optimization of blended-wing-body underwater glider (BWBUG) can significantly improve its gliding performance. However, high-fidelity CFD analysis and geometric constraint calculation in traditional surrogate-based optimization methods are expensive. An efficient surrogate-based optimization method based on the multifidelity model and geometric constraint gradient information is proposed. By establishing a shape parameterized model, deriving analytical expression of geometric constraint gradient, constructing multifidelity surrogate model, the calculation times of high-fidelity CFD model and geometric constraints are reduced during the shape optimization process of BWBUG, which greatly improve the optimization efficiency. Finally, the effectiveness and efficiency of the proposed method are verified by performing the shape optimization of a BWBUG and comparing with traditional surrogate-based optimization methods.

scholarly journals Stochastic Shape Optimization via Design-Space Augmented Dimensionality Reduction and RANS Computations

2019 ◽  
Author(s):  
Andrea Serani ◽  
Matteo Diez ◽  
Jeroen Wackers ◽  
Michel Visonneau ◽  
Frederick Stern
Keyword(s):  
Dimensionality Reduction ◽  
Shape Optimization ◽  
Design Space

scholarly journals Assessing the Interplay of Shape and Physical Parameters by Unsupervised Nonlinear Dimensionality Reduction Methods

2019 ◽  
Author(s):  
Andrea Serani ◽  
Danny D’Agostino ◽  
Emilio Fortunato Campana ◽  
Matteo Diez
Keyword(s):  
Dimensionality Reduction ◽  
Shape Optimization ◽  
Design Space ◽  
Mean Squared Error ◽  
Physical Parameters ◽  
Nonlinear Dimensionality Reduction ◽  
Data Set ◽  
Reduced Dimensionality ◽  
Nonlinear Design ◽  
Reduction Methods

The article presents an exploratory study on the application to ship hydrodynamics of unsupervised nonlinear design-space dimensionality reduction methods, assessing the interaction of shape and physical parameters. Nonlinear extensions of the principal component analysis (PCA) are applied, namely local PCA (LPCA) and kernel PCA (KPCA). An artificial neural network approach, specifically a deep autoencoder (DAE) method, is also applied and compared with PCA-based approaches. The data set under investigation is formed by the results of 9000 potential flow simulations coming from an extensive exploration of a 27-dimensional design space, associated with a shape optimization problem of the DTMB 5415 model in calm water at 18 kn (Froude number, <inline-formula><mml:math><mml:mrow><mml:mtext>Fr</mml:mtext><mml:mo>=</mml:mo><mml:mn>.25</mml:mn></mml:mrow></mml:math><inline-graphic xlink:href="JOSR09180056inf1.tif"/></inline-formula>). Data include three heterogeneous distributed and suitably discretized parameters (shape modification vector, pressure distribution on the hull, and wave elevation pattern) and one lumped parameter (wave resistance coefficient), for a total of <inline-formula><mml:math><mml:mrow><mml:mn>9000</mml:mn><mml:mtext> </mml:mtext><mml:mo>×</mml:mo><mml:mtext> </mml:mtext><mml:mn>5101</mml:mn></mml:mrow></mml:math><inline-graphic xlink:href="JOSR09180056inf2.tif"/></inline-formula> elements. The reduced-dimensionality representation of shape and physical parameters is set to provide a normalized mean squared error smaller than 5%. The standard PCA meets the requirement using 19 principal components/parameters. LPCA and KPCA provide the most promising compression capability with 14 parameters required by the reduced-dimensionality parametrizations, indicating significant nonlinear interactions in the data structure of shape and physical parameters. The DAE achieves the same error with 17 components. Although the focus of the current work is on design-space dimensionality reduction, the formulation goes beyond shape optimization and can be applied to large sets of heterogeneous physical data from simulations, experiments, and real operation measurements.

scholarly journals Оптимизация алюминиевой крышки люкового закрытия сухогрузного судна

2020 ◽  
Author(s):  
G.B. Kryzhevich ◽  
A.R. Filatov
Keyword(s):  
Shape Optimization ◽  
Parametric Optimization ◽  
Optimization Methods ◽  
Topological Optimization ◽  
Design And Technology ◽  
Bulk Carrier ◽  
Material Consumption ◽  
Considerable Decrease ◽  
Bulk Carriers ◽  
Cargo Transportation

Объектом исследования является крышка люкового закрытия сухогрузного судна, служащая для обеспечения непроницаемости грузовых помещений и перевозки на ней грузов и обеспечивающая безопасность сухогрузных судов и осуществляемой на них морской перевозки грузов. Большая материалоемкость крышек снижает экономическую эффективность судна, ведет к необходимости использования мощных и массогабаритных средств подъема крышек (для съемных люковых закрытий), либо поворота и передвижения крышек (для шарнирно-откидных закрытий). Целью статьи является существенное снижение материалоемкости крышек люкового закрытия за счет рационального выбора их материала и конструктивного оформления при одновременном обеспечении требуемого уровня их надежности. Параметрическая оптимизация традиционной стальной крышки люкового закрытия сухогрузного судна проекта RSD59 может привести к снижению ее массы не более чем на 15-17. Поэтому для достижения цели работы решается задача оптимизации конструкции алюминиевой крышки на основе комплексного подхода, состоящего в последовательном использовании топологических и параметрических оптимизационных методов и выполнении на последней стадии работы снижения уровня концентрации напряжений путем оптимизации формы узлов крышки. При этом на стадии выбора конструктивно-силовой схемы крышки применяются приёмы топологической оптимизации, на стадии выбора толщин и параметров силовых элементов способы параметрической оптимизации, а на стадии конструктивно-технологического оформления узлов методы оптимизации формы. Выполненные расчетные исследования привели к следующим основным результатам: к выявлению прогрессивных конструктивно-силовых схем и конструктивно-технологических решений, обеспечивающих значительное снижению массы крышек люковых закрытий при умеренных затратах на их изготовление к высоким оценкам эффективности использования современных алюминиевых сплавов для изготовления люковых закрытий, способствующим существенному снижению их материалоемкости (примерно двукратному и более по сравнению с использованием стали), улучшению условий их функционирования и проведения погрузочно-разгрузочных работ на сухогрузных судах к выводу об эффективности использования разработанных конструкторских решений для крышек люковых закрытий при создании перспективных сухогрузных судов.A bulk carrier hatch cover, which provides cargo compartments impermeability and cargo transportation on the cover, as well as safety of bulk carriers and sea cargo transportation in them, is studied. Cover high material consumption decreases vessel profitability, causes the necessity to use either powerful and mass-dimensional cover lifting devices (for removable hatch covers) or covers rotation and movement (for hinged covers). The purpose of this paper consists in considerable decrease of hatch cover material consumption through rational selection of covers material and design at provision of the required covers reliability level. Parametric optimization of a conventional steel cover of RSD59 project bulk carrier could result in cover mass decrease by more than 15 to 17. Therefore, to achieve the work purpose, a problem of aluminum cover structural optimization was solved based on a comprehensive approach that consisted in successive use of topologic and parametric optimization methods and decrease of the stress concentration level at the last step via cover assemblies shape optimization. At that topological optimization methods were applied at the stage of selecting cover structural arrangement parametric optimization methods were applied at the stage of selecting load-carrying elements thickness and parameters, and shape optimization methods were used at the stage of structural and technology design of assemblies. The performed calculation studies resulted in the following: revealing the advanced structural arrangements and design and technology solutions that provide considerable hatch covers mass decrease at reasonable costs for their manufacture high assessment of using advanced aluminum alloys for manufacturing hatch covers that promote considerable decrease of their material consumption (approximately up to twofold or greater in comparison with steel), improving conditions of cover functioning and handling operation in bulk carriers conclusion on effectiveness of using developed design solutions for hatch covers when creating prospective bulk carriers.

Sign in / Sign up

Export Citation Format

Share Document