以Phae Ⅵ风力机为研究对象,采用CFD方法对多种工况风力机的流场进行计算,通过反向动量叶素理论方法提取攻角和翼型的三维气动数据。在此基础上,建立以周速比、实度、攻角、扭角和二维气动参数为输入参数,三维气动参数为输出参数的BP神经网络修正模型。所建BP模型预测的升阻力系数同CFD计算所得结果误差在5%以内。将该模型同动量叶素理论相结合对Phase Ⅵ风力机进行计算,结果表明可显著提高风力机气动性能的预测精度。
Abstract
In this paper the flow field of wind turbine Phase Ⅵ under various operating conditions are calculated via CFD method . The three-dimensional aerodynamic data such as attack angle, lift force and drag force are extracted using the reverse blade element momentum theory method. Based on the above data, a BP neural network correction model is established with circumferential speed ratio, solidity, attack angle, twist angle, and two-dimensional aerodynamic parameters as the input parameters and three-dimensional aerodynamic performance parameters as the output parameters. The error between the predicted lift resistance coefficient of the BP model and the result obtained from CFD calculation is within 5%. The model combining blade momentum element theory with BP neutral network is selected to calculate the aerodynamic performance of Phase Ⅵ wind turbine, and the results showed that it can predict more accurately compared with original BEM method.
关键词
风力机 /
气动失速 /
旋转流动 /
分离 /
攻角 /
神经网络
Key words
wind turbines /
aerodynamic stalling /
rotational flow /
separation /
angle of attack /
neural networks
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 杜朝辉. 旋转对风力涡轮叶片三维边界层影响的数值计算[J]. 太阳能学报, 1999, 20(3): 251-258.
DU Z H.Effect of rotation on blade boundary layer of wind turbine[J]. Acta energiae solaris sinica, 1999, 20(3): 251-258.
[2] 伍艳, 王同光. 三维旋转效应对桨叶气动特性影响的计算[J]. 空气动力学学报, 2006, 24(2): 200-204.
WU Y, WANG T G.Prediction of three-dimensional rotational effect on blade aerodynamic characteristics[J]. Acta aerodynamica sinica, 2006, 24(2): 200-204.
[3] 朱呈勇, 王同光, 邵涛. 水平轴风力机三维旋转效应数值模拟研究[J]. 太阳能学报, 2019, 40(6): 1747-1755.
ZHU C Y, WANG T G, SHAO T.Investigation into three-dimensional rotational effect on hawt with numerical simulations[J]. Acta energiae solaris sinica, 2019, 40(6): 1747-1755.
[4] 赵丹平, 徐宝清. 风力机设计理论及方法[M]. 北京: 北京大学出版社, 2012: 127-128.
ZHAO D P, XU B Q.Theory and Method of Wind Turbine Design[M]. Beijing: Peking University Press, 2012: 127-128.
[5] 杜朝辉. 水平轴风力涡轮设计与性能预估方法的三维失速延迟模型: Ⅱ.模型建立及应用[J]. 太阳能学报, 2000, 21(1): 1-6.
DU Z H.A 3-d stall-delay model for hwat performance prediction: Ⅱ model and its applications[J]. Acta energiae solaris sinica, 2000, 21(1): 1-6.
[6] CHAVIAROPOULOS P K, HANSEN M O L. Investigating three-dimensional and rotational effects on wind turbine blades by means of a quasi-3D navier-stokes solver[J]. Journal of fluids engineering, 2000, 122(2): 330-336.
[7] HU D M, OUYANG H, DU Z H.A study on stall-delay for horizontal axis wind turbine[J]. Renewable energy, 2006, 31(6): 821-836.
[8] LEE H M, WU Y H.An experimental study of stall delay on the blade of a horizontal-axis wind turbine using tomographic particle image velocimetry[J]. Journal of wind engineering and industrial aerodynamics, 2013, 123: 56-68.
[9] 张蕴宁, 叶舟, 李春. 基于改进型升力面自由涡尾迹法的风力机性能研究[J]. 太阳能学报, 2017, 38(5): 1316-1323.
ZHANG Y N, YE Z, LI C.Wind turbine aerodynamic performance simulation based on improved lifting surface free wake method[J]. Acta energiae solaris sinica, 2017, 38(5): 1316-1323.
[10] BANGGA G, HUTOMO G, SYAWITRI T, et al.Enhancing BEM simulations of a stalled wind turbine using a 3D correction model[J]. Journal of physics: conference series, 2018, 974: 012020.
[11] YU G H, SHEN X, ZHU X C, et al.An insight into the separate flow and stall delay for HAWT[J]. Renewable energy, 2011, 36(1): 69-76.
[12] DU Z, SELIG M A.3-D stall-delay model for horizontal axis wind turbine performance predictions[R]. AIAA-98-0021. 1988.
[13] BRETON S P, COTON F N, MOE G.A study on rotational effects and different stall delay models using a prescribed wake vortex scheme and NREL phase VI experiment data[J]. Wind energy, 2008, 11(5): 459-482.
[14] SYED AHMED KABIR I F, NG E Y K. Insight into stall delay and computation of 3D sectional aerofoil characteristics of NREL phase VI wind turbine using inverse BEM and improvement in BEM analysis accounting for stall delay effect[J]. Energy, 2017, 120: 518-536.
[15] HAND M M, SIMMS D A, FINGERSH L J, et al.Unsteady aerodynamics experiment phase vi: wind tunnel test configurations and available data campaigns[R]. NREL/TP-500-29955, 2001.
[16] SNEL H, SCHEPERS J G, MONTGOMERIE B.The MEXICO project(model experiments in controlled conditions): the database and first results of data processing and interpretation[J]. Journal of physics: conference series, 2007, 75: 012014.
[17] 吴友健, 杨艺. 不同湍流模型对风力机叶片翼型气动性能参数计算结果的影响研究[J]. 太阳能, 2020(8): 36-40.
WU Y J, YANG Y.Research on influence of different turbulence models on calculation results of aerodynamic performance parameters of wind turbine blade airfoil[J]. Solar energy, 2020(8): 36-40.
[18] 钟伟, 王同光. SST湍流模型参数校正对风力机CFD模拟的改进[J]. 太阳能学报, 2014, 35(9): 1743-1748.
ZHONG W, WANG T G.Improvement of CFD simulations for wind turbines by calibrating a closure constant of SST turbulence model[J]. Acta energiae solaris sinica, 2014, 35(9): 1743-1748.
[19] ZHANG J C, ZHAO X W.Three-dimensional spatiotemporal wind field reconstruction based on physics-informed deep learning[J]. Applied energy, 2021, 300: 117390.
[20] 段巍, 韩旭, 马良玉, 等. 基于Elman神经网络的风力机风轮子系统故障预警[J]. 太阳能学报, 2021, 42(12): 157-162.
DUAN W, HAN X, MA L Y, et al.Fault prediction of wind turbin wheel subsystem based on Elman neural network[J]. Acta energiae solaris sinica, 2021, 42(12): 157-162.
PDF(1529 KB)
