基于Hopfield网络的飞机设计

周盛强; 向锦武

基于Hopfield网络的飞机设计

北京航空航天大学航空科学与工程学院, 北京 100083

基金项目: 新世纪优秀人才支持计划资助项目(NCET2042010)

详细信息

作者简介:
周盛强(1975-),男,江西安福人,博士生, zsq@ase.buaa.edu.cn.

中图分类号: TP 183; V 221⁺.6
计量
- 文章访问数: 2883
- HTML全文浏览量: 197
- PDF下载量: 734
- 被引次数: 0
出版历程
- 收稿日期: 2005-06-20
- 网络出版日期: 2006-06-30

Hopfield network based approach to aircraft design

School of Aeronautic Science and Technology, Beijing University of Aeronautics and Astronautics, Beijing 100083, China

摘要

摘要: Hopfield神经网络与增广拉格朗日乘子法相结合来求解非线性约束优化.神经网络作为求解乘子法的子问题的动力学方法,仅需计算一阶导数.引入逐渐衰减的高斯噪声信号构造随机神经网络.同时针对随机网络受初始温度制约,跳出局部极小值能力有限的问题,网络运行采用结合模拟退火的欧拉法.用该方法对某喷气教练机进行总体优化设计,结果表明,算法的数值稳定性较好,求解精度高.并基于拉氏乘子提供的约束敏度信息,做了设计要求权衡.最后研究了某型干线旅客机的机翼气动/结构综合设计问题.
- 神经网络 /
- 拉格朗日乘子 /
- 高斯噪声 /
- 模拟退火 /
- 飞机设计
Abstract: Combining augmented lagrange multiplier(ALM) method to Hopfield neural network(HNN), was proposed to solve nonlinear constrained optimization. HNNis taken as a dynamic approach for minimization subproblem in ALM method, only needing the first derivative of the Lagrange function. The random neural network was extended by adding Gaussian noise gradually reducing with the temperature, whose ablity escapeing from the attraction of the localminimum points was limitedby the initial temperature. Combined with the simulated annealing, an improved algorithm for Euler method was presented for numerical implementation of the network. The approach was applied to jet trainer aircraft preliminary optimization. The results show that the computing process is stable and the optimal result is enough precise. The trade-off of design requirements was studied through the Lagrange multipliers. An aerodynamic/structural design optimization for the wing of a trunkeliner was studied.
- neural network /
- Lagrange multipliers /
- Gaussian noise /
- simulated annealing /
- aircraft design

HTML全文

参考文献(1)

[1] Tsirukis A G, Reklaitis G V. Nonlinear optimization using generalized Hopfield networks[J].Neural Computing and Applications, 1989,1:511-521 [2] Dhingra A K, Rao S S. A neural network based approach to mechanical design optimization[J].Engineering Optimization, 1992,20:187-203 [3] 吴剑国,赵丽萍．工程结构优化的神经网络方法[J]．计算力学学报 ,1998,15(1):69-74 Wu Jianguo,Zhao Liping. Neural network method for structural engineering optimization[J].Chinese Journal of Computational Mechnaics, 1998,15(1):69-74(in Chinese) [4] 丛爽,王怡雯.随机神经网络发展现状综述[J].控制理论与应用,2004,21(6):975-980 Cong Shuang, Wang Yiwen. Survey of current progress in random neural network .Control Theory & Applications, 2004, 21(6) :975-980(in Chinese) [5] 石晓荣,张明廉.一种基于混沌神经网络的拟人智能控制方法[J].北京航空航天大学学报,2004, 30(9):879-892 Shi Xiaorong,Zhang Minglian. Human-imitating control based on chaotic neural networks[J]. Journal of Beijing University of Aeronautics and Astronautics, 2004,30(9):879-892(in Chinese) [6] 叶世伟,郑宏伟,王文杰,等.连续时间Hopfield网络模型数值实现分析 .软件学报,2004,15(6):881-890 Ye Shiwei,Zheng Hongwei,Wang Wenjie, et al. Analysis for numerical implementation of continuous time Hopfield network model[J]. Journal of Software, 2004,15(6):881-890(in Chinese) [7] 方卫国,郦正能．基于全局敏度方程方法的飞机方案优化设计[J]．航空学报,1998,19(3):293-298 Fang Weiguo,Li Zhengneng. Aircraft scheme optimization design based on global sensitivity equation method[J]. Acta Aeronautica et Astronautica Sinica,1998,19(3):293-298(in Chinese) [8] 董波,张晓东,郦正能.干线客机机翼气动/结构综合设计研究[J].北京航空航天大学学报,2002, 28(4):435-437 Dong Bo, Zhang Xiaodong, Li Zhengneng. Integrated aerodynamic/structural design optimization for wing of trunkliner[J]. Journal of Beijing University of Aeronautics and Astronautics,2002, 28(4):435-437(in Chinese)

施引文献

资源附件(0)

访问统计