Research on intelligent optimal design method of wind tunnel test scheme
-
摘要: 我国的航空航天装备发展已经进入了自主创新的崭新阶段，新一代飞行器气动设计的探索创新、优化定型需要高水平的风洞试验能力作为支撑。先进飞行器研制需要快速获取正确的气动外形关键数据，其高性能、高精度的发展趋势对风洞试验的数量和质量提出了更高要求。传统风洞试验方案设计和数据分析模式已经越来越不能满足需求，亟待有所突破。本文以飞行器地面试验分析为背景，应用支持向量机模型对试验数据进行建模分析，发展风洞试验方案优化设计方法和试验数据智能分析方法，探索气动数据与飞行器几何参数之间新的内在关联，构建风洞试验辅助设计和分析系统，提高风洞试验效率和试验数据的正确率，为先进飞行器气动设计提供技术支撑。Abstract: Advanced aircraft research requires rapid acquisition of correct-key data on the aerodynamic shape. The development of our country's aerospace equipment has gradually entered a stage of independent innovation. The exploration, innovation, and optimization of the aerodyna-mic design for a new generation of aircraft need to be supported by matching wind tunnel test capabilities. The development trend of high-performance and high-precision advanced aircraft has put forward higher requirements on the “quantity” and “quality” of wind tunnel test data, which means the design of traditional wind tunnel test schemes and data analysis modes have become increasingly unsatisfactory. It is necessary to make breakthroughs in wind tunnel test design and test data analysis technology. Based on aircraft ground test analysis, this paper uses the support vector machine（SVM） to model and analyze the test data, develop wind tunnel test plan optimization, design methods and test data intelligent analysis methods, and explore the new internal correlation between the aerodynamic data and aircraft geometric parameters. Building a wind tunnel test auxiliary design and analysis system to improve the efficiency of wind tunnel test and the accuracy of test data provides technical support for the aerodynamic design of high-performance aircraft.
-
Key words:
- artificial intelligence /
- aerodynamics /
- wind tunnel test /
- SVM /
- BP
-
表 1 核函数对模型性能的影响
Table 1. The effect of nuclear functions on model performance
核函数类型 线性 多项式 RBF Sigmoid 模
型
性
能训
练
集E 0.0178 0.0061 0.0001 0.0109 R2 0.8982 0.9568 0.9991 0.8958 测
试
集E 0.0419 0.0270 0.0010 0.0296 R2 0.8997 0.8464 0.9920 0.8799 
下载: 导出CSV
表 2 验证点试验数据与模型间的误差
Table 2. Verification point error between wind tunnel test and prediction
变量 ERMS R2 CN 0.0034 1.0222 CZ 0.0016 1.0468 CA 0.0043 1.0253 MXG1 0.0069 1.0199 MYG1 0.0087 1.0063 MZG1 0.0022 1.0032
下载: 导出CSV
-
[1] TSIEN H S. Similarity laws of hypersonic flows[J]. Journal of Mathematics and Physics,1946,25(1-4):247-251. doi: 10.1002/sapm1946251247 [2] BERTIN J J,CUMMINGS R M. Fifty years of hypersonics: where we've been,where we're going[J]. Progress in Aerospace Sciences,2003,39(6-7):511-536. doi: 10.1016/S0376-0421(03)00079-4 [3] WALTERMIRE S. A view from the world’s largest wind tunnel[J]. High Mach,2020,67(3):2,6. [4] 罗月培,孙宗祥,孙杭义,等. 美国高超声速风洞试验能力发展综述[J]. 飞航导弹,2021(6):33-41. doi: 10.16338/j.issn.1009-1319.20210826 [5] 范洁川. 风洞试验手册[M]. 北京: 航空工业出版社, 2002.FAN J C. Handbook of wind tunnel test[M]. Beijing: Aviation industry press, 2002. [6] HICKS B. NFAC test next-generation military helicopter[J]. High Mach,2019,66(19):1,5. [7] SCHAIRER E T, KUSHNER L K, HEINECK J T, et al. Measurements of parachute dynamics in the world’s largest wind tunnel by stereo photogrammetry[R]. AIAA 2018-3802, 2018. doi: 10.2514/6.2018-3802 [8] ORTIZ D. NFAC test director and team recognized by the vertical flight society[J]. High Mach,2019,66(14):3. [9] BRADLEY H. Craftsmen keep largest wind tunnel in the world running at peak conditions[J]. High Mach,2019,66(21):1,5. [10] HICKS B. NFAC wind tunnel testing demonstrates success-ful integration of refueling, monitoring systems[J]. High Mach,2020,67(5):1,4. [11] SCHAIRER E T, HEINECK J T, KUSHNER L K, et al. Shape and angle-of-attack measurements of ram-air para-chutes by stereo photogrammetry in the national full-scale aerodynamics complex[R]. AIAA 2019-2806, 2019. doi: 10.2514/6.2019-2806 [12] 赵楠,谭惠文. 人工智能技术的发展及应用分析[J]. 中国电子科学研究院学报,2021,16(7):737-740. doi: 10.3969/j.issn.1673-5692.2021.07.016ZHAO N,TAN H W. Development and application analysis of artificial intelligence technology[J]. Journal of China Academy of Electronics and Information Technology,2021,16(7):737-740. doi: 10.3969/j.issn.1673-5692.2021.07.016 [13] VAPNIK V N. The nature of statistical learning theory[M]. New York: Springer New York, 1995. doi: 10.1007/978-1-4757-2440-0 [14] 汪清,钱炜祺,丁娣. 飞机大迎角非定常气动力建模研究进展[J]. 航空学报,2016,37(8):2331-2347. doi: 10.7527/S1000-6893.2016.0072WANG Q,QIAN W Q,DING D. A review of unsteady aerodynamic modeling of aircrafts at high angles of attack[J]. Acta Aeronautica et Astronautica Sinica,2016,37(8):2331-2347. doi: 10.7527/S1000-6893.2016.0072 [15] ADACHI S,OGAWA T. A new system identification method based on support vector machines[J]. IFAC Proceedings Volumes,2001,34(14):181-186. doi: 10.1016/S1474-6670(17)41619-3 [16] 段焰辉,吴文华,范召林,等. 基于本征正交分解的气动优化设计外形数据挖掘[J]. 物理学报,2017,66(22):220203. doi: 10.7498/aps.66.220203DUAN Y H,WU W H,FAN Z L,et al. Proper orthogonal decomposition-based data mining of aerodynamic shape for design optimization[J]. Acta Physica Sinica,2017,66(22):220203. doi: 10.7498/aps.66.220203 [17] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报,2000,26(1):32-42. doi: 10.16383/j.aas.2000.01.005ZHANG X G. Introduction to statistical learning theory and support vector machines[J]. Acta Automatica Sinica,2000,26(1):32-42. doi: 10.16383/j.aas.2000.01.005 [18] 安复兴,李磊,苏伟,等. 高超声速飞行器气动设计中的若干关键问题[J]. 中国科学(物理学 力学 天文学),2021,51(10):2-21. doi: 10.1360/SSPMA-2021-0135AN F X,LI L,SU W,et al. Key issues in hypersonic vehicle aerodynamic design[J]. Scientia Sinica Physica(Mechanica & Astronomica),2021,51(10):2-21. doi: 10.1360/SSPMA-2021-0135 [19] TUKAN M,BAYKAL C,FELDMAN D,et al. On coresets for support vector machines[J]. Theoretical Computer Science,2021,890:171-191. doi: 10.1016/j.tcs.2021.09.008 [20] KOHIYAMA M,OKA K,YAMASHITA T. Detection method of unlearned pattern using support vector machine in damage classification based on deep neural network[J]. Structural Control and Health Monitoring,2020,27(8):e2552. doi: 10.1002/stc.2552 [21] 徐洪学,孙万有,杜英魁,等. 机器学习经典算法及其应用研究综述[J]. 电脑知识与技术,2020,16(33):17-19. doi: 10.14004/j.cnki.ckt.2020.3359XU H X,SUN W Y,DU Y K,et al. Survey on the classic machine learning algorithms and their applications[J]. Computer Knowledge and Technology,2020,16(33):17-19. doi: 10.14004/j.cnki.ckt.2020.3359 [22] 李润泽,张宇飞,陈海昕. “人在回路”思想在飞机气动优化设计中演变与发展[J]. 空气动力学学报,2017,35(4):529-543. doi: 10.7638/kqdlxxb-2017.0076LI R Z,ZHANG Y F,CHEN H X. Evolution and development of “man-in-loop” in aerodynamic optimization design[J]. Acta Aerodynamica Sinica,2017,35(4):529-543. doi: 10.7638/kqdlxxb-2017.0076 [23] 高正红,王超. 飞行器气动外形设计方法研究与进展[J]. 空气动力学学报,2017,35(4):516-528. doi: 10.7638/kqdlxxb-2017.0058GAO Z H,WANG C. Aerodynamic shape design methods for aircraft: status and trends[J]. Acta Aerodynamica Sinica,2017,35(4):516-528. doi: 10.7638/kqdlxxb-2017.0058 [24] 邓凯文,陈海昕. 基于差分进化和RBF响应面的混合优化算法[J]. 力学学报,2017,49(2):441-455. doi: 10.6052/0459-1879-16-285DENG K W,CHEN H X. Hybrid optimization algorithm based on differential evolution and RBF response surface[J]. Chinese Journal of Theoretical and Applied Mechanics,2017,49(2):441-455. doi: 10.6052/0459-1879-16-285 [25] 顾险峰. 人工智能的历史回顾和发展现状[J]. 自然杂志,2016,38(3):157-166. doi: 10.3969/j.issn.0253-9608.2016.03.001GU X F. Historical review and current development of artificial intelligence[J]. Chinese Journal of Nature,2016,38(3):157-166. doi: 10.3969/j.issn.0253-9608.2016.03.001 [26] 乔林,张雄伟,史海宁,等. 第4讲 深度学习应用中的常见模型[J]. 军事通信技术,2016,37(1):98-104. doi: 10.16464/j.cnki.cn32-1289.2016.01.020QIAO L,ZHANG X W,SHI H N,et al. Common network models in deep learning application[J]. Journal of Military Communications Technology,2016,37(1):98-104. doi: 10.16464/j.cnki.cn32-1289.2016.01.020 [27] 张天姣,钱炜祺,周宇,等. 人工智能与空气动力学结合的初步思考[J]. 航空工程进展,2019,10(1):1-11. doi: 10.16615/j.cnki.1674-8190.2019.01.001ZHANG T J,QIAN W Q,ZHOU Y,et al. Preliminary thoughts on the combination of artificial intelligence and aerodynamics[J]. Advances in Aeronautical Science and Engineering,2019,10(1):1-11. doi: 10.16615/j.cnki.1674-8190.2019.01.001 [28] 周盼,辛江慧,丁继才. 非线性系统载荷识别的最小二乘支持向量机法[J]. 噪声与振动控制,2021,41(5):9-13,37. doi: 10.3969/j.issn.1006-1355.2021.05.002ZHOU P,XIN J H,DING J C. Least squares support vector machine method for load identification of nonlinear sys-tems[J]. Noise and Vibration Control,2021,41(5):9-13,37. doi: 10.3969/j.issn.1006-1355.2021.05.002 [29] 钱翼稷. 空气动力学[M]. 北京: 北京航空航天大学出版社, 2004. [30] 张万国. 高等数学[M]. 北京, 高等教育出版社, 2011. -
点击查看大图
图(5) / 表(2)
计量
- 文章访问数: 1744
- HTML全文浏览量: 236
- PDF下载量: 96
- 被引次数: 0
