针对水翼的全局优化需大量的计算流体动力学（CFD）模拟进而增加计算成本的问题,提出一种基于生成对抗网络（GAN）和CFD的水翼优化设计框架,利用GAN根据现有翼型库对水翼设计进行参数化,由于GAN的高维生成能力,这种参数化方法仅使用少量的参数即可生成大量光滑逼真的水翼,降低了水翼参数的维度。该优化框架结合Python脚本和OpenFOAM自动完成水翼的网格生成和流体仿真,可得到具有更高升阻比的水翼,优化总时间成本为69.8 h,提高优化效率和精度。此外,将优化水翼应用于潮流能水轮机叶片的设计,结果表明,优化水翼Optc建模的水轮机叶片最佳获能系数提升15.56%,显著提高水轮机的获能性能。
Abstract
To address the issue that global optimization of hydrofoils requires extensive computational fluid dynamics (CFD) simulations, leading to increased computational costs, the hydrofoil optimization design framework based on generative adversarial networks (GAN) and CFD is proposed. GAN is utilized to parameterize hydrofoil designs based on the existing airfoil library. Due to the high-dimensional generation capability of GAN, this parameterization method can generate a large number of smooth and realistic hydrofoils using only a small number of parameters, thereby reducing the dimensions of the hydrofoil parameterization. This optimization framework combines Python scripts and OpenFOAM to automatically complete the mesh generation and fluid simulation of the hydrofoil, resulting in a hydrofoil with a higher lift-to-drag ratio. The total optimization time cost is 69.8 hours, which improves optimization efficiency and accuracy. Furthermore, the optimized hydrofoils are applied to the design of tidal turbine blades. The results indicate that the optimal power coefficient of the tidal turbine blades modeled using the optimized hydrofoil Optc increases by 15.56%, enhancing the energy capture performance of the turbine.
关键词
水翼 /
生成对抗网络 /
潮流能 /
计算流体动力学 /
水轮机叶片 /
获能系数
Key words
hydrofoil /
generative adversarial networks /
tidal energy /
computational fluid dynamics /
turbine blades /
power coefficient
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 朱恩龙, 冯聪聪, 申振腾, 等. 基于机器视觉的风力机叶片故障检测技术研究[J]. 太阳能学报, 2023, 44(4): 209-215.
ZHU E L, FENG C C, SHEN Z T, et al.Research on wind turbine blade fault detection technology based on machine vision[J]. Acta energiae solaris sinica, 2023, 44(4): 209-215.
[2] 李伟, 文飞, 陈光荣, 等. 风电机组叶片结冰的光纤感知及厚度分布估计[J]. 太阳能学报, 2023, 44(3): 77-83.
LI W, WEN F, CHEN G R, et al.Optical fiber sensing and thickness distribution estimation of icing state on wind turbine blades[J]. Acta energiae solaris sinica, 2023, 44(3): 77-83.
[3] 胡振辉, 袁鹏, 司先才, 等. 数据驱动的潮流能水轮机叶片翼型性能保真替代计算模型对比研究[J]. 太阳能学报, 2022, 43(12): 495-502.
HU Z H, YUAN P, SI X C, et al.Comparative study of surrogate calculation models for performance of blade hydrofoil of tidal turbine based on data-driven[J]. Acta energiae solaris sinica, 2022, 43(12): 495-502.
[4] GU Y J, LIU H W, LI W, et al.Integrated design and implementation of 120-kW horizontal-axis tidal current energy conversion system[J]. Ocean engineering, 2018, 158: 338-349.
[5] LI Z Q, LI G N, DU L, et al.Optimal design of horizontal axis tidal current turbine blade[J]. Ocean engineering, 2023, 271: 113666.
[6] FINNEGAN W, JIANG Y D, MEIER P, et al.Numerical modelling, manufacture and structural testing of a full-scale 1 MW tidal turbine blade[J]. Ocean engineering, 2022, 266: 112717.
[7] WANG X J, SONG B W, WANG P, et al.Hydrofoil optimization of underwater glider using Free-Form Deformation and surrogate-based optimization[J]. International journal of naval architecture and ocean engineering, 2018, 10(6): 730-740.
[8] CHEN X, DIEZ M, KANDASAMY M, et al.High-fidelity global optimization of shape design by dimensionality reduction, metamodels and deterministic particle swarm[J]. Engineering optimization, 2015, 47(4): 473-494.
[9] MELIANI M, BARTOLI N, LEFEBVRE T, et al. Multi-fidelity efficient global optimization: methodology and application to airfoil shape design[C]//Proceedings of the AIAA Aviation2019 Forum. Dallas,Texas, 2019: AIAA2019-3236.
[10] VISWANATH A, FORRESTER A I J, KEANE A J. Dimension reduction for aerodynamic design optimization[J]. AIAA journal, 2011, 49(6): 1256-1266.
[11] HUI X Y, BAI J Q, WANG H, et al.Fast pressure distribution prediction of airfoils using deep learning[J]. Aerospace science and technology, 2020, 105: 105949.
[12] WANG L Y, XU J, LUO W, et al.A deep learning-based optimization framework of two-dimensional hydrofoils for tidal turbine rotor design[J]. Energy, 2022, 253: 124130.
[13] KHARAL A, SALEEM A.Neural networks based airfoil generation for a given using Bezier-PARSEC parameterization[J]. Aerospace science and technology, 2012, 23(1): 330-344.
[14] SUN G, SUN Y J, WANG S Y.Artificial neural network based inverse design: Airfoils and wings[J]. Aerospace science and technology, 2015, 42: 415-428.
[15] VISWANATH A, FORRESTER A I J, KEANE A J. Constrained design optimization using generative topographic mapping[J]. AIAA journal, 2014, 52(5): 1010-1023.
[16] GHOREISHI S F, FRIEDMAN S, ALLAIRE D L.Adaptive dimensionality reduction for fast sequential optimization with Gaussian processes[J]. Journal of mechanical design, 2019, 141(7): 071404.
[17] QIU Y S, BAI J Q, LIU N, et al.Global aerodynamic design optimization based on data dimensionality reduction[J]. Chinese journal of aeronautics, 2018, 31(4): 643-659.
[18] JANIESCH C, ZSCHECH P, HEINRICH K.Machine learning and deep learning[J]. Electronic markets, 2021, 31(3): 685-695.
[19] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al.Generative adversarial nets[J]. Advances in neural information processing systems, 2014, 27.
[20] ACHOUR G, SUNG W J, PINON-FISCHER O J, et al. Development of a conditional generative adversarial network for airfoil shape optimization[C]//Proceedings of the AIAA Scitech2020 Forum. Orlando,FL, 2020: AIAA2020-2261.
[21] KEDWARD L J, ALLEN C B, RENDALL T C S. Gradient-limiting shape control for efficient aerodynamic optimization[J]. AIAA journal, 2020, 58(9): 3748-3764.
[22] LI J C, ZHANG M Q, MARTINS J R R A, et al. Efficient aerodynamic shape optimization with deep-learning-based geometric filtering[J]. AIAA journal, 2020, 58(10): 4243-4259.
[23] CHEN W, CHIU K, FUGE M D.Airfoil design parameterization and optimization using Bézier generative adversarial networks[J]. AIAA journal, 2020, 58(11): 4723-4735.
[24] SOMERS D M.Design and experimental results for the S809 airfoil[R]. National renewable energy lab.(NREL), Golden, CO(United States), 1997.
[25] DU Q W, LIU T Y, YANG L K, et al.Airfoil design and surrogate modeling for performance prediction based on deep learning method[J]. Physics of fluids, 2022, 34(1): 015111.
[26] REN Y R, LIU B W, ZHANG T T, et al.Design and hydrodynamic analysis of horizontal axis tidal stream turbines with winglets[J]. Ocean engineering, 2017, 144: 374-383.
基金
国家重点研发计划（2018YFB1501903）
PDF(3622 KB)
