基于卷积神经网络的合成双射流控制机翼分离流场识别与参数优化

赵志杰; 罗振兵; 邓雄

doi:10.7638/kqdlxxb-2020.0109

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于卷积神经网络的合成双射流控制机翼分离流场识别与参数优化

专栏——分离流、旋涡和流动控制 | 更新时间：2026-05-28

- 基于卷积神经网络的合成双射流控制机翼分离流场识别与参数优化
- Recognition and parameter optimization of separated flow field in airfoil controlled by dual synthetic jet based on convolutional neural network
- 空气动力学学报 2020年38卷第5期页码：949-956
- 作者机构：
  
  国防科技大学空天科学学院,长沙,410073
- 作者简介：
  
  赵志杰(1997-), 男, 博士研究生, 主要研究方向:智能主动流动控制.E-mail:ji_yo_100@163.com
  罗振兵(1979-), 男, 博士, 教授, 主要研究方向:主动流动控制.E-mail:luozhenbing@163.com
- 基金信息：
  
  国家自然科学基金面上项目（11972369，11872374）
- DOI：10.7638/kqdlxxb-2020.0109
  中图分类号： V211.3;O357.4
- 纸质出版：2020
- 稿件说明：
移动端阅览
赵志杰, 罗振兵, 邓雄. 基于卷积神经网络的合成双射流控制机翼分离流场识别与参数优化[J]. 空气动力学学报, 2020, 38(5): 949-956.

ZHAO Zhijie, LUO Zhenbing, DENG Xiong. Recognition and parameter optimization of separated flow field in airfoil controlled by dual synthetic jet based on convolutional neural network[J]. 2020, 38(5): 949-956.
赵志杰, 罗振兵, 邓雄. 基于卷积神经网络的合成双射流控制机翼分离流场识别与参数优化[J]. 空气动力学学报, 2020, 38(5): 949-956. DOI： 10.7638/kqdlxxb-2020.0109.

ZHAO Zhijie, LUO Zhenbing, DENG Xiong. Recognition and parameter optimization of separated flow field in airfoil controlled by dual synthetic jet based on convolutional neural network[J]. 2020, 38(5): 949-956. DOI： 10.7638/kqdlxxb-2020.0109.

摘要

为进一步拓宽合成双射流（DSJ）技术在翼型分离流动控制领域的工程应用，采用数值模拟的方法，研究了DSJ对分离流的控制机理与控制规律，构建控制参数向量与气动参数之间的RBF神经网络代理模型，通过改进的粒子群算法（PSO）搜索一定约束下所能达到的最佳气动参数，并搭建Inception-V3卷积神经网络模型对平均速度场所对应的控制参数进行识别，以实现根据目标流场调整激励器参数，使其气动性能达到最优的目的。结果表明：DSJ对分离流的控制机理包括：动量注入效应、涡掺混效应、抽吸效应；射流控制参数对控制效果有较大影响，迎角为16°~21°时，无量纲控制频率

在0.5~4.0范围内都具有较好的控制效果，迎角为22°~24°时，最佳无量纲控制频率为3~4，同时动量系数越大，增升减阻效果越明显；RBF神经网络具有良好的泛化能力，测试误差不超过17%；PSO优化结果显示，在16°≤

≤24°、0

4、0

0.0954约束内，翼型所能达到的最大升力系数为1.793，最小阻力系数为0.013；Inception-V3模型在测试算例中的均方误差最大为0.1023，模型预测得出的控制向量所对应的速度场与原始速度场在小失速迎角下一致性较好，在大失速迎角下一致性较差。

Abstract

For broadening the engineering application of dual synthetic jet (DSJ) in the field of separation flow control

the control mechanism and law of the DSJ were studied numerically

and the RBF neural network model was constructed to describe the relationships between the control parameters and the aerodynamic parameters. Moreover

the optimal aerodynamic parameters that could be achieved under certain constraints and control parameters were searched based on improved particle swarm optimization (PSO) algorithm. In addition

Inception-V3 model was established to identify the control parameters based on the average velocity field with the purpose of adjusting the control parameters of the actuators according to the target flow field

then achieving the optimal control effects that can realize the optimal aerodynamic performance of the airfoil. Results show that

the following issues are contained in the control mechanism of the DSJ on separation flow:momentum injection effect

vortex mixing effect and suction effect. The control parameters have a significant impact on the control effects. When the attack angle is in the range of 16°~21° and 22°~24°

the non-dimensional optimal frequency

is in the range of 0.5~4.0 and 3~4

respectively. Meanwhile

the larger the separation zone is

the bigger the non-dimensional optimal frequency

is. A larger momentum coefficient lead to a more significant effects of lift promotion and drag reduction. A great generalization ability is realized by the RBF neural network model

whose maximum test error is less than 17%. The PSO optimization results show that the maximum lift coefficient and the minimum drag coefficient could be realized under different conditions

with the values being 1.793 and 0.013 respectively

with 16° ≤

≤ 24°

and 0

0.0954. The Inception-V3 model

whose maximum mean square error of test cases is less than 0.1023

has the outstanding ability to predict the control parameters. Apart from that

the average velocity field corresponding to the control parameters predicted by the model is greatly consistent with the original velocity field at small attack angles

but the consistency is bad at large attack angles owing to the great sensitivities to the control parameters.

关键词

Keywords

references

GLEZER A, AMITAY M. Synthetic jets[J]. Annual Review of Fluid Mechanics, 2002, 34(1):503-529.

LUO Z B, XIA Z X. Advances in synthetic jet technology and applications in flow control[J]. Advances in Mechanics, 2005, 35(2):221-234. (in Chinese)

ZHANG P F, WANG JJ, FENG L H. Advances in zero-mass flux jet technology and applications[J]. Science in China, 2008, 38(3):321-349. (in Chinese)

LOU B, YE S J, WANG G F, et al. Numerical and experimental research of flow control on an NACA 0012 airfoil by local vibration[J]. Applied Mathematics and Mechanics, 2018, 40(1):1-12.

QIN Y, SONG Y, CHEN F, et al. Active flow control by means of endwall synthetic jet on a high-speed compressor stator cascade[J]. Proceedings of the Institution of Mechanical Engineers, 2018, 232(6):641-659.

LIU X B, ZHANG WW, JIANG Y W, et al. Numerical study on unsteady aerodynamic characteristics of an airfoil with a synthetic jet set in trailing edge[J]. Acta Aerodynamica Sinica, 2012, 30(5):606-612. (in Chinese)

MA Y Y, ZHAO Q J, ZHAO G Q. New combinational active control strategy for improving aerodynamic characteristics of airfoil and rotor[J]. Proceedings of the Institution of Mechanical Engineers, Part G:Journal of Aerospace Engineering, 2020, 234(4):977-996. doi:10.1177/0954410019893193

ZHANG X, HUANG Y, WANG X N, et al. Flow control on a supercritical wing using dielectric barrier discharge plasma actuator[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(6):1733-1742. (in Chinese)

XIA Z X, LUO Z B. Physical factors of primary jet vectoring control using synthetic jet actuators[J]. Applied Mathematics and Mechanics, 2007, 28(7):907-920. doi:10.1007/s10483-007-0708-z

LI BB, YAO Y, GU Y S, et al. PIV experiments on vector deflection control of lowspeed synthetic jet[J]. Acta Aerodynamica Sinica, 2018, 36(1):22-25, 30.(in Chinese) doi:10.7638/kqdlxxb-2015. 0194

LIU Y M, WANG B G, LIU S Y, et al. Influence of synthetic jet actuator arrays on the mixing in coaxial jets[J]. Journal of Aerospace Power, 2009, 24(3):566-572. (in Chinese)

ZHOU Y, XIA Z X, LUO Z B, et al. Effect of three-electrode plasma synthetic jet actuator on shock wave control[J]. Science China Technological Sciences, 2017, 60(1):146-152. doi:10.1007/s11431-016-0248-4

ZHOU Y, XIA Z X, LUO Z B, et al. A novel ram-air plasma synthetic jet actuator for near space high-speed flow control[J]. Acta Astronautica, 2017, 133:95-102. doi:10.1016/j.actaastro.2017.01.016

JIN D, CUI W, LI Y H, et al. Characteristics of pulsed plasma synthetic jet and its control effect on supersonic flow[J]. Chinese Journal of Aeronautics, 2015, 28(1):66-76.

LUO Z B, DENG X, XIA Z X, et al. Flow field and heat transfer characteristics of impingement based on a vectoring dual synthetic jet actuator[J]. International Journal of Heat and Mass Transfer, 2016, 102:18-25.

ZHU H, YANG Z G, WANG G J. Thermal control of LED headlamp based on annular synthetic jet[J]. Journal of Tongji University (Natural Science), 2020, 48(2):257-263. (in Chinese)

GAO S, ZHANG J Z, TAN X M. Experimental study on heat transfer characteristics of synthetic jet driven by piston actuator[J]. Science China Technological Sciences, 2012, 55(6):1732-1738.

ZHANG X, HUANG Y, YANG P Y, et al. Flight test of flow separation control using plasma UAV[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(2):115-122. (in Chinese)

LUO Z B, XIA Z X, LIU B. New generation of synthetic jet actuators[J]. AIAA Journal, 2006, 44(10):2418-2420. doi:10.2514/1. 20747

AMITAY M, HORVATH M, MICHAUX M, et al. Virtual aerodynamic shape modification at low angles of attack using synthetic jet actuators[C]//Proc of the 15th AIAA Computational Fluid Dynamics Conference, Anaheim, CA. Reston, Virginia: AIAA, 2001

CHATLYNNE E, RUMIGNY N, AMITAY M, et al. Virtual aero-shaping of a Clark-Y airfoil using synthetic jet actuators[C]//Proc of the 39th Aerospace Sciences Meeting and Exhibit, Reno, NV. Reston, Virginia: AIAA, 2001

ZHANG P F, WANG J J. Numerical simulation on flow control of stalled NACA0015 airfoil with synthetic jet actuator in recirculation region[J]. Journal of Beijing University of Aeronautics and Astronautics, 2008, 34(4):443-446.(in Chinese)

ZHANG P F, WANG J J. Effect of orifice inclined angle on flow control of the stalled airfoil with synthetic jet actuator[J]. Acta Armamentarii, 2009, 30(12):1658-1662. (in Chinese)

ZHANG P F, YAN B, DAI C F. Lift enhancement method by synthetic jet circulation control[J]. Scientia Sinica Technologica, 2012, 42(9):1046-1053. (in Chinese)

LIU F. Numerical simulation of synthetic jet to control flow separation over airfoil[D]. Hangzhou: Zhejiang University, 2013. (in Chinese)

WANG L, LUO Z B, XIA Z X, et al. Numerical simulation of separated flow control on an airfoil using dual synthetic jets[J]. Acta Aerodynamica Sinica, 2012, 30(3):353-357, 372. (in Chinese)

LI Y J, LUO Z B, DENG X, et al. Experimental investigation on flow separation control of stalled NACA0015 airfoil using dual synthetic jet actuator[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(3):817-825. (in Chinese)

MELISSA B, RICHARD A. Comparison of computation and experiment results for a supercritical airfoil[R]. NASA-TM-4601.

蒋子阳. TensorFlow深度学习算法原理与编程实战[M].北京:中国水利水电出版社, 2019.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

矩形射流口几何构型对合成双射流工作特性影响分析

合成双射流控制水下圆柱绕流流动分离数值模拟研究

基于神经网络的表面热流辨识三维效应修正

某型电动跑车尾翼气动设计的仿真与试验研究

基于Ac-准则的最优输入设计方法