基于流形结构重建的多目标气动优化算法

doi:10.7527/S1000-6893.2019.23687

飞行器气动外形数值优化与设计专栏

本期目录 | 过刊浏览 | 高级检索

前一篇 |

基于流形结构重建的多目标气动优化算法

宋超, 李伟斌, 周铸, 刘红阳, 蓝庆生

中国空气动力研究与发展中心计算空气动力研究所, 绵阳 621000

收稿日期:2019-11-27 修回日期:2019-12-02 出版日期:2020-05-15 发布日期:2019-12-12
通讯作者: 周铸 E-mail:zhouzhu@tom.com
基金资助:
中国空气动力研究与发展中心风雷青年创新基金

Multi-objective aerodynamic optimization algorithm based on manifold reconstruction

SONG Chao, LI Weibin, ZHOU Zhu, LIU Hongyang, LAN Qingsheng

Computional Aerodynamics Institute, China Aerodynamics Research and Development Center, Mianyang 621000, China

Received:2019-11-27 Revised:2019-12-02 Online:2020-05-15 Published:2019-12-12
Supported by:
FengLei Youth Innovation Fund of China Aerodynamics Research and Development Center

摘要/Abstract

摘要： 在多目标优化中，Pareto解集是一个分段连续的k维流形，这一规律被传统进化算法所忽略。本文提出了一种基于流形结构重建的多目标优化算法，首先利用流形结构重建方法完成解集分布从目标空间到设计空间的映射，建立解集的概率分布，并在目标空间中扩展流形结构，从而借助解集在目标空间的推进来指导优化算法的快速演化。数值算例表明本文算法对于具有不同特征的Pareto前沿具有很好的适应性，能够极大提高算法的收敛效率。多目标气动优化算例验证，本文算法相比于常规多目标进化算法能够减少约80%的计算量，极大程度缩短了气动设计的周期。

关键词: 流形, 气动设计, 分布估计, 多目标, Pareto解集

Abstract: The Pareto set of a multi-objective design problem is a piecewise continuous k-dimensional manifold, and this fact has always been neglected by traditional multi-objective genetic algorithms. A multi-objective optimization algorithm based on manifold reconstruction is proposed in this paper. The manifold reconstruction algorithm is employed for building the mapping between the design space and the objective space, and the probability distribution of the solution set is built. Then the manifold structure in the objective space is extended, enabling the advancing of the solution set in the objective space to optimize the algorithm. The analytic design cases show that the proposed algorithm is adaptive to problems with diverse Pareto structure features, and the optimization efficiency is improved significantly. The proposed algorithm is also verified by multi-objective aerodynamic design problems. The results demonstrated that about 80% computational cost can be saved compared with traditional multi-objective genetic algorithms. The proposed algorithm has the ability to significantly shorten the aerodynamic design cycle.

Key words: manifold, aerodynamic design, estimation of distribution, multi-objective, Pareto set

中图分类号:

V211.3

宋超, 李伟斌, 周铸, 刘红阳, 蓝庆生. 基于流形结构重建的多目标气动优化算法[J]. 航空学报, 2020, 41(5): 623687-623687.

SONG Chao, LI Weibin, ZHOU Zhu, LIU Hongyang, LAN Qingsheng. Multi-objective aerodynamic optimization algorithm based on manifold reconstruction[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(5): 623687-623687.

参考文献 25

[1]	黄江涛, 高正红, 余婧, 等. 大型民用飞机气动外形典型综合设计方法[J]. 航空学报, 2019, 40(2):522369. HUANG J T, GAO Z H, YU J, et al. A typical integrated design method for aerodynamic shape optimization of large civil aircraft[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(2):522369(in Chinese).
[2]	杨慧, 宋文萍, 韩忠华, 等. 旋翼翼型多目标多约束气动优化设计[J]. 航空学报, 2012, 33(7):1218-1226. YANG H, SONG W P, HAN Z H, et al. Multi-objective and multi-constrained optimization design for a helicopter rotor airfoil[J]. Acta Aeronautica et Astronautica Sinica, 2012, 33(7):1218-1226(in Chinese).
[3]	夏露, 高正红, 李天. 飞行器外形多目标多学科综合优化设计方法研究[J]. 空气动力学学报, 2003, 21(3):275-281. XIA L, GAO Z H, LI T. Investigation of integrated multi-disciplinary and multi-objective optimization of the aircraft configuration design method[J]. Acta Aerodynamica Sinica, 2003, 21(3):275-281(in Chinese).
[4]	FONSECA C M, FLEMING P J. Genetic algorithms for multi objective optimization:Formulation discussion and generalization[C]//Proceeding of the Fifth International Conference, 1993:416-423.
[5]	SRINIVAS N, DEB K. Multi objective optimization using nondominated sorting in genetic algorithms[J]. Evolutionary Computation, 1994, 2(3):221-248.
[6]	DEB K, PRATAP A, AGARWAL S, et al. A fast and elitist multiobjective genetic algorithm:NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2):182-197.
[7]	李倩, 詹浩, 朱军. 基于Pareto遗传算法的机翼多目标优化设计研究[J]. 西北工业大学学报, 2010, 28(1):134-137. LI Q, ZHAN H, ZHU J. Exploring combination of Pareto Genetic Algorithm(GA) with aerodynamic analysis software for multi-objective optimization of wing[J]. Journal of Northwestern Polytechnical University, 2010, 28(1):134-137(in Chinese).
[8]	李权, 郭兆电, 雷武涛, 等. 基于工程环境的气动多目标优化设计平台研究[J]. 航空学报, 2016, 37(1):255-268. LI Q, GUO Z D, LEI W T, et al. Engineering environment-based multi-objective optimization platform for aerodynamic design[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(1):255-268(in Chinese).
[9]	MARLER R T, ARORA J S. Survey of multi-objective optimization methods for engineering[J]. Structural and Multidisciplinary Optimization, 2004, 26(6):369-395.
[10]	TAN K C, LEE T H, KHOR E F. Evolutionary algorithms for multi-objective optimization:Performance assessments and comparisons[J]. Artificial Intelligence Review, 2002, 17(4):251-290.
[11]	KIM H J, LIOU M S. Aerodynamic optimization using a hybrid moga-local search method[C]//51st AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference. Reston:AIAA, 2010:1-23.
[12]	LAUMANNS M, RUDOLPH G, SCHWEFEL H P. Mutation control and convergence in evolutionary multi-objective optimization[C]//Proceedings of the 7th International Conference on Soft Computing, 2001:24-29.
[13]	LARRANAGA P, LOZANO J A. Estimation of distribution algorithms:A new tool for evolutionary computat-ion[M]. Berlin:Springer Science & Business Media, 2001.
[14]	ZHOU A, ZHANG Q, JIN Y, et al. A model-based evolutionary algorithm for bi-objective optimization[C]//2005 IEEE Congress on Evolutionary Computation. Piscataway, NJ:IEEE Press, 2005:2568-2575.
[15]	ZHOU A, JIN Y, ZHANG Q, et al. Combining model-based and genetics-based offspring generation for multi-objective optimization using a convergence criterion[C]//2006 IEEE International Congress on Evolutionary Computation. Piscataway, NJ:IEEE Press, 2006:3234-3241.
[16]	ZHANG Q, ZHOU A, JIN Y. RM-MEDA:A regularity model-based multi-objective estimation of distribution algorithm[J]. IEEE Transactions on Evolutionary Computation, 2008, 12(1):41-63.
[17]	KUHN H W, TUCKER A W. Nonlinear programming[M]. Boston:Birk-Hauser, 2014:247-258.
[18]	KAMBHATLA N, LEEN T K. Dimension reduction by local principal component analysis[J]. Neural Computation, 19979(7):1493-1516.
[19]	詹炜. 求解高维多目标优化问题的流形学习算法研究[D]. 武汉:中国地质大学, 2013. ZHAN W. Research on manifold learning algorithm for high-dimensional multi-objective optimization problems[D]. Wuhan:China University of Geosciences, 2013(in Chinese).
[20]	YANG D D, JIAO L C, GONG M G. Hybrid multi-objective estimation of distribution algorithm by Local Linear Embedding and an immune inspired algorithm[C]//2009 IEEE Congress on Evolutionary Computation. Piscataway, NJ:IEEE Press, 2009:463-470.
[21]	LARRANAGA P, LOZANO J A. Estimation of distribution algorithms. A new tool for evolutionary computat-ion[M]. Boston:Kluwer Academic Publishers, 2002.
[22]	孟德宇, 徐晨, 徐宗本. 基于ISOMAP的流形结构重建方法[J]. 计算机学报, 2010, 33(3):545-555. MENG D Y, XU C, XU Z B. A new manifold reconstruction method based on ISOMAP[J]. Chinese Journal of Computers, 2010, 33(3):545-555(in Chinese).
[23]	REYES S M, COELLO C A C. A study of fitness inheritance and approximation techniques for multi-objective particle swarm optimization[C]//2005 IEEE Congress on Evolutionary Computation. Piscataway:IEEE Press, 2005, 1:65-72.
[24]	KULFAN B M. Universal parametric geometry representation method[J]. Journal of Aircraft, 2008, 45(1):142-158.
[25]	SELIG M, DETERS R, WILIAMSON G. Wind tunnel testing airfoils at low Reynolds numbers[C]//49th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition. Reston:AIAA, 2011:1-32.

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于流形结构重建的多目标气动优化算法

Multi-objective aerodynamic optimization algorithm based on manifold reconstruction

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 25

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王传云, 苏阳, 王琳霖, 王田, 王静静, 高骞. 面向反制无人机集群的多目标连续鲁棒跟踪算法[J]. 航空学报, 2024, 45(7): 329017-329017.
[2]	李广佳, 王红波, 张凯, 仪志胜. 临近空间太阳能无人机增升减阻技术综述[J]. 航空学报, 2024, 45(5): 529644-529644.
[3]	杨晓飞, 孙太璐, 孟德君, 尹海宝, 王咏梅. 兼顾多模式的核心机驱动风扇级气动设计方法[J]. 航空学报, 2024, 45(2): 128625-128625.
[4]	杨倩, 郑皓冉, 程显达, 董威. 基于引气控制的热气防冰优化设计方法[J]. 航空学报, 2023, 44(S2): 729285-729285.
[5]	李春鹏, 钱战森, 孙侠生. 远程民机变弯度机翼后缘外形变形矩阵气动设计[J]. 航空学报, 2023, 44(7): 127335-127335.
[6]	赵欢, 高正红, 夏露. 基于新型多可信度代理模型的多目标优化方法[J]. 航空学报, 2023, 44(6): 126962-126962.
[7]	张旭辉, 解春雷, 刘思佳, 闫溟, 邢思远. 智能变形飞行器发展需求及难点分析[J]. 航空学报, 2023, 44(21): 529302-529302.
[8]	王晓峰, 屈峰, 付俊杰, 王泽宇, 刘超宇, 白俊强. 基于离散伴随的高超内转式进气道气动优化设计[J]. 航空学报, 2023, 44(19): 128352-128352.
[9]	董杰忠, 楚武利, 张皓光, 罗波, 晏松. 基于因果网络分析的扩压叶栅波浪形前缘控制机理[J]. 航空学报, 2023, 44(19): 128336-128336.
[10]	苑玉彬, 吴一全, 赵朗月, 陈金林, 赵其昌. 基于深度学习的无人机航拍视频多目标检测与跟踪研究进展[J]. 航空学报, 2023, 44(18): 28334-028334.
[11]	毕文豪, 周久力, 段晓波, 张安, 徐双飞. 基于多要素改进NSGA-Ⅱ的小直径制导炸弹空面打击最优火力分配方法[J]. 航空学报, 2023, 44(17): 328116-328116.
[12]	梁超, 杨力, 潘成胜, 戚耀文. 卫星网络动态资源图多QoS约束路由算法[J]. 航空学报, 2023, 44(1): 326422-326422.
[13]	李昊歌, 杨华, 杨雨欣, 陈伟芳. 高超声速升力体迎风面精细化降热优化设计[J]. 航空学报, 2022, 43(S2): 124-137.
[14]	邹子缘, 陈琪锋. 基于决策树搜索的空间飞行器集群对抗目标分配方法[J]. 航空学报, 2022, 43(S1): 726910-726910.
[15]	孙刚, 彭双, 陈浩, 伍江江, 李军. 面向测控数传资源一体化场景的卫星地面站资源多目标优化方法[J]. 航空学报, 2022, 43(9): 326114-326114.