基于深度学习的风力机叶片气动优化方法研究

韩旭 ,  陈荣钱 ,  楼锦华 ,  柳家齐 ,  尤延铖

应用力学学报 ›› 2026, Vol. 43 ›› Issue (1) : 38 -48.

PDF (9114KB)
应用力学学报 ›› 2026, Vol. 43 ›› Issue (1) : 38 -48. DOI: 10.11776/j.issn.1000-4939.2026.01.003
航空航天工程专栏

基于深度学习的风力机叶片气动优化方法研究

作者信息 +

Research on the aerodynamic optimization of wind turbine blades using deep learning

Author information +
文章历史 +
PDF (9332K)

摘要

针对传统计算流体力学方法在评估叶片气动性能时计算量大、耗时长的问题,提出了一种基于深度学习的风力机叶片气动优化方法。该方法首先通过构建基于多层感知器的翼型气动力快速预测模型,实现了对风力机翼型气动性能的快速优化,随后,结合叶素动量理论,建立了风力机叶片气动性能的快速计算方法,从而进行风力机叶片的外形优化研究。以某1.5 MW风力机为例,分别针对最大升阻比和年发电量进行了翼型优化和叶片外形优化。研究结果表明,基于多层感知器的翼型气动力预测模型在训练集和测试集上的总体预测准确率超过了99%,通过该方法优化后的风力机叶片,其功率系数提升了13.74%,年发电量提高了4.04%,证明了深度学习在风力机叶片气动优化领域的实用价值。

Abstract

To address the challenges posed by traditional computational fluid dynamics methods, which are computationally demanding and time-consuming in evaluating blade aerodynamic performance, a novel aerodynamic optimization method for wind turbine blades is introduced, leveraging deep learning. First, this method establishes a rapid prediction model for aerodynamic forces on airfoils, utilizing multi-layer perceptrons, to facilitate rapid optimization of wind turbine airfoil performance. Subsequently, a rapid calculation methodology for wind turbine blade aerodynamic performance is formulated, incorporating blade element momentum theory, to enable the exploration of blade shape optimization. Using a 1.5 MW wind turbine as a case study, optimizations targeting both maximum lift-to-drag ratio and annual energy production are made for airfoil and blade shape optimizations, respectively. The results demonstrate that the airfoil aerodynamic force prediction model, grounded in multi-layer perceptrons, achieves an overall prediction accuracy of over 99% on both training and testing datasets. Notably, the optimized wind turbine blades exhibit a significant improvement of 13.74% in power coefficient and a 4.04% increase in annual energy production, thereby proving the practical significance and value of deep learning in the field of wind turbine blade aerodynamic optimization.

关键词

深度学习 / 风力机叶片优化 / 叶素动量理论 / 翼型优化

Key words

deep learning / wind turbine blade optimization / blade element momentum theory / airfoil optimization

引用本文

引用格式 ▾
韩旭,陈荣钱,楼锦华,柳家齐,尤延铖. 基于深度学习的风力机叶片气动优化方法研究[J]. 应用力学学报, 2026, 43(1): 38-48 DOI:10.11776/j.issn.1000-4939.2026.01.003

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

韩忠华, 高正红, 宋文萍, 等. 翼型研究的历史、现状与未来发展[J]. 空气动力学学报, 2021, 39(6): 1-36.

[2]

HAN Zhonghua, GAO Zhenghong, SONG Wenping, et al. On airfoil research and development:history, current status, and future directions[J]. Acta aerodynamica Sinica, 2021, 39(6): 1-36(in Chinese).

[3]

陈进, 汪泉. 风力机翼型及叶片优化设计理论[M]. 北京: 科学出版社, 2013.

[4]

乔志德, 宋文萍, 高永卫. NPU-WA系列风力机翼型设计与风洞实验[J]. 空气动力学学报, 2012, 30(2): 260-265.

[5]

QIAO Zhide, SONG Wenping, GAO Yongwei. Design and experiment of the NPU-WA airfoil family for wind turbines[J]. Acta aerodynamica Sinica, 2012, 30(2): 260-265(in Chinese).

[6]

白井艳, 杨科, 黄宸武, 等. 风力机专用翼型的反设计[J]. 工程热物理学报, 2012, 33(11): 1884-1887.

[7]

BAI Jingyan, YANG Ke, HUANG Chenwu, et al. The inverse design of wind turbine airfoil[J]. Journal of engineering thermophysics, 2012, 33(11): 1884-1887(in Chinese).

[8]

FUGLSANG P, BAK C. Development of the RisØ wind turbine airfoils[J]. Wind energy, 2004, 7(2): 145-162.

[9]

ZHU W J, SHEN W Z, SØRENSEN J N. Integrated airfoil and blade design method for large wind turbines[J]. Renewable energy, 2014, 70: 172-183.

[10]

杨科, 王会社, 徐建中, 等. 基于CFD技术的高性能风力机翼型最优化设计方法[J]. 工程热物理学报, 2007, 28(4): 586-588.

[11]

YANG Ke, WANG Huishe, XU Jianzhong, et al. Optimization and design method research of wind turbine airfoils based on cfd technique[J]. Journal of engineering thermophysics, 2007, 28(4): 586-588(in Chinese).

[12]

琚亚平, 张楚华. 基于人工神经网络与遗传算法的风力机翼型优化设计方法[J]. 中国电机工程学报, 2009, 29(20): 106-111.

[13]

JU Yaping, ZHANG Chuhua. Optimal design method for wind turbine airfoil based on artificial neural network model and genetic algorithm[J]. Proceedings of the CSEE, 2009, 29(20): 106-111(in Chinese).

[14]

FUGLSANG P, MADSEN H A. Optimization method for wind turbine rotors[J]. Journal of wind engineering and industrial aerodynamics, 1999, 80(1/2): 191-206.

[15]

RAJAKUMAR S, RAVINDRAN D. Iterative approach for optimising coefficient of power, coefficient of lift and drag of wind turbine rotor[J]. Renewable energy, 2012, 38(1): 83-93.

[16]

刘欢, 宗学军, 李鹏程. 基于粒子群算法的风力机叶片优化设计[J]. 沈阳化工大学学报, 2022, 36(6): 544-547.

[17]

LIU Huan, ZONG Xuejun, LI Pengcheng. Research on optimization design of wind turbine blade based on particle swarm algorithm[J]. Journal of Shenyang University of Chemical Technology, 2022, 36(6): 544-547(in Chinese).

[18]

胡超, 周丙浩, 马勇, 等. 基于FAST和Simulink的海上风力机叶片扭角和弦长优化设计研究[J]. 太阳能学报, 2021, 42(3): 135-141.

[19]

HU Chao, ZHOU Binghao, MA Yong, et al. Optimization research of twist angle and chord length of offshore wind turbine blade based on FAST and Simulink[J]. Acta energiae solaris Sinica, 2021, 42(3): 135-141(in Chinese).

[20]

王昊, 陆杨, 周欢, 等. 联合Wilson方法与遗传算法的水平轴风力机叶片优化设计[J]. 上海电力学院学报, 2018, 34(4): 325-328.

[21]

WANG Hao, LU Yang, ZHOU Huan, et al. Optimization design of horizontal axis wind turbine blade based on Wilson method and genetic algorithm[J]. Journal of Shanghai University of Electric Power, 2018, 34(4): 325-328(in Chinese).

[22]

SEKAR V, JIANG Q H, SHU C. Fast flow field prediction over airfoils using deep learning approach[J]. Physics of fluids, 2019, 31(5): 057103.

[23]

刘凌君, 周越, 高振勋. 基于神经网络的翼型气动力计算和反设计方法[J]. 气体物理, 2018, 3(5): 41-47.

[24]

LIU Lingjun, ZHOU Yue, GAO Zhenxun. Aerodynamic force calculation and inverse design for airfoil based on neural network[J]. Physics of gases, 2018, 3(5): 41-47(in Chinese).

[25]

陈晨铭, 郭雪岩, 常林森. 基于BP神经网络代理模型的翼型优化及领域自适应研究[J]. 动力工程学报, 2022, 42(7): 657-663.

[26]

CHEN Chenming, GUO Xueyan, CHANG Linsen. Research on airfoil optimization and domain adaptation based on BP neural network surrogate model[J]. Journal of Chinese Society of Power Engineering, 2022, 42(7): 657-663(in Chinese).

[27]

LOU J H, CHEN R Q, LIU J Q, et al. Aerodynamic optimization of airfoil based on deep reinforcement learning[J]. Physics of fluids, 2023, 35(3): 037128.

[28]

LIU J Q, CHEN R Q, LOU J H, et al. Airfoils optimization based on deep reinforcement learning to improve the aerodynamic performance of rotors[J]. Aerospace science and technology, 2023, 143: 108737.

[29]

廖炎平, 刘莉, 龙腾. 几种翼型参数化方法研究[J]. 弹箭与制导学报, 2011, 31(3): 160-164.

[30]

LIAO Yanping, LIU Li, LONG Teng. The research on some parameterized methods for airfoil[J]. Journal of projectiles, rockets, missiles and guidance, 2011, 31(3): 160-164(in Chinese).

[31]

SOBIECZKY H. Parametric airfoils and wings[M]. Notes on numerical fluid mechanics. Berlin,Springer, 1998: 71-88.

[32]

赵振宙, 王同光, 郑源. 风力机原理[M]. 北京: 中国水利水电出版社, 2016.

[33]

汪泉. 风力机叶片气动外形与结构的参数化耦合设计理论研究[D]. 重庆: 重庆大学, 2013.

[34]

GIGUÈRE P, SELIG M S. Design of a tapered and twisted blade for the NREL combined experiment rotor[R]. Golden,CO:National Renewable Energy Laboratory, 1999. NREL/SR-500-26173.

[35]

李争荣, 王理峰, 黄昕玥, 等. 大型风电场风能资源及其利用状况评估[J]. 电子制作, 2018(18): 15-16.

[36]

LI Zhengrong, WANG Lifeng, HUANG Xinyue, et al. Assessment of wind energy resources and utilization status in large-scale wind farms[J]. Practical electronics, 2018(18): 15-16(in Chinese).

[37]

YILMAZ E, GERMAN B. A convolutional neural network approach to training predictors for airfoil performance[C]// 18th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference. Reston, VA, USA: AIAA, 2017: AIAA 2017-3660.

[38]

张强, 缪维跑, 常林森, 等. 基于代理模型的风力机翼型动态失速优化设计[J]. 太阳能学报, 2023, 44(6): 343-350.

[39]

ZHANG Qiang, MIAO Weipao, CHANG Linsen, et al. Optimal design of dynamic stall of wind turbine airfoil based on surrogate model[J]. Acta energiae solaris Sinica, 2023, 44(6): 343-350(in Chinese).

[40]

DEGHOUM K, GHERBI M T, SULTAN H S, et al. Optimization of small horizontal axis wind turbines based on aerodynamic, steady-state, and dynamic analyses[J]. Applied system innovation, 2023, 6(2): 33.

[41]

YIN R, XIE J B, YAO J. Optimal design and aerodynamic performance prediction of a horizontal axis small-scale wind turbine[J]. Mathematical problems in engineering, 2022, 2022(1): 3947164.

[42]

KAVIANI H R, MOSHFEGHI M. Multi-megawatt horizontal axis wind turbine blade optimization based on PSO method[J]. Aerospace, 2023, 10(2): 158.

[43]

RODRIGUEZ C V, CELIS C. Design optimization methodology of small horizontal axis wind turbine blades using a hybrid CFD/BEM/GA approach[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2022, 44(6): 254.

基金资助

福建省科技计划对外合作项目(2020I0004)

AI Summary AI Mindmap
PDF (9114KB)

139

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉