基于粒子群优化的WNN飞行数据气动力建模

Abstract

Abstract: To accurately describe the dynamic characteristics of a flight vehicle by means of an aerodynamic model, a wavelet neural network (WNN) aerodynamic modeling method from flight data based on an improved particle swarm optimization (IPSO) algorithm is proposed. To address the deficiencies of the standard PSO(SPSO) algorithm, the closest particle information and mutation operation are introduced in this method to improve the global searching ability of WNN parameters and overcome premature convergence. Then, in light of the aerodynamic modeling flow from flight data for flight vehicles, a WNN model trained by the IPSO algorithm is established. Experimental results show that the proposed aerodynamic modeling method is characterized by high forecast precision, fast convergence speed and effective suppression of premature convergence. It is valid and feasible for aerodynamic modeling from flight data.

Key words: wavelet, neural network, particle swarm optimization algorithm, aerodynamic model, premature convergence

CLC Number:

GAN Xusheng, DUANMU Jingshun, MENG Yuebo, CONG Wei. Aerodynamic Modeling from Flight Data Based on WNN Optimized by Particle Swarm[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2012, 33(7): 1209-1217.

References

[1] Linse D J, Strengel R F. Identification of aerodynamic coefficients using computational neural networks. Journal of Guidance, Control and Dynamics, 1993, 16(6): 1018-1025.
[2] Rokhsaz K, Steck J E. Application of artificial neural networks in nonlinear aerodynamics and aircraft design. Journal of Aerospace, 1993, 12(2): 1790-1798.
[3] Peterson G, Bond W, Germann R, et al. Using neural networks for aerodynamic parameter modeling. 1995 American Control Conference, 1995: 1360-1361.
[4] Raol J R, Jategoankar R V. Aircraft parameter estimation using recurrent neural networks-a critical appraisal. AIAA-1995-3504, 1995.
[5] Peyada N K, Ghosh A K. Longitudinal aerodynamic parameter estimation using neural network and Gauss Newton method. Journal of Aerospace Sciences and TechnologGanguli R, Omkar S N, et al. Rotorcraft parameter estimation from real time flight data using radial basis function networks. Journal of Aircraft, 2008, 45 (1): 333-341.
[7] Youssef H M, Juang J C. Estimation of aerodynamic coefficients using neural networks. AIAA-1993-3639, 1993.
[8] Jategaonkar R V. Flight vehicle system identification: a time domain methodology. Progress in Astronautics and Aeronautics Series, Reston, VA: AIAA Press, 2006.
[9] Hess R A. On the use of back propagation with feed forward neural networks for the aerodynamic estimation problem. AIAA-1993-3638, 1993.
[10] Singh S, Ghosh A K. Parameter estimation from flight data of a missile using maximum likelihood and neural network method. 2006 AIAA Flight Mechanics Conference and Exhibit, 2006: 21-24.
[11] Malmathanraj R, Thamarai Selvi S E. Prediction of aerodynamic characteristics using neural networks. Asian Journal of Information Technology, 2008, 7(1): 19-26.
[12] Li J P, Wang F T, Yang B. Fast training algorithm of BP wavelet neural network. System Engineering and Electronics, 2001, 23(8): 72-75. (in Chinese) 李金屏, 王风涛, 杨波. BP小波神经网络快速学习算法研究. 系统工程与电子技术, 2001, 23(8): 72-75.
[13] Dong F G, Zhang S Y, Tan Z F, et al. Application for electricity price forecasting using improved wavelet neural networks based on GA. Computer Engineering, 2005, 31(4): 32-33. (in Chinese) 董福贵, 张世英, 谭忠富, 等. 基于遗传算法的小波神经网络在边际电价预测中的应用. 计算机工程,2005, 31(4): 32-33.
[14] Yang D W, Li S H, Shen Y T. Wavelet neural network learning algorithm based on particle swarm optimization. Chinese Journal of Engineering Geophysics, 2007, 4(6): 529-532. (in Chinese) 杨迪威, 李少华, 沈远彤. 基于粒子群优化算法的小波神经网络. 工程地球物理学报, 2007, 4(6): 529-532.
[15] Mao H W, Pan H X, Liu W L. Wavelet neural network based on particle swarm optimization algorithm and its application in fault diagnosis of gear-box. Journal of Vibration and Shock, 2007, 26(5): 133-136. (in Chinese) 毛鸿伟, 潘宏侠, 刘文礼. 基于粒子群优化的小波神经网络及其在齿轮箱故障诊断中的应用. 振动与冲击, 2007, 26(5): 133-136.
[16] Zhang Q H, Benveniste A. Wavelet network. IEEE Transactions on Neural Networks, 1992, 3(6): 889-898.
[17] Zhang Q H. Using wavelet network in nonparametric estimation. IEEE Transactions on Neural Networks, 1997, 8(2): 227-236.
[18] Kennedy J, Eberhart R C. Particle swarm optimization. 1995 IEEE International Conference on Neural Networks, 1995: 1942-1948.
[19] Shi Y, Eberhart R C. Parameter selection in particle swarm optimization. 1998 Annual Conference on Evolutionary Programming, 1998: 591-600.
[20] Clerc M. The swarm and the queen: towards a deterministic and adaptive particle swami optimization. 1999 Congress on Evolutionary Computation, 1999: 1951-1957.
[21] Cai C X, Zhang D X. Particle swarm optimization with information of closest particle. Computer Engineering and Applications, 2009, 45(18): 40-42. (in Chinese) 蔡昌新, 张顶学. 带邻近粒子信息的粒子群算法. 计算机工程与应用, 2007, 45(18): 40-42.
[22] Sun L Y. A new improved particle swarm optimization algorithm. Dalian: Information engineering College, Dalian Maritime University, 2008. (in Chinese) 孙林燕. 一种新的改进粒子群算法. 大连: 大连海事大学信息工程学院, 2008.
[23] Cai J S. Aircraft system identification. Beijing: China Astronautic Publishing House, 1995: 222-231. (in Chinese) 蔡金狮. 飞行器系统辨识. 北京: 宇航出版社, 1995: 222-231.
[24] Zeng Q Y. Weak signal detection. Hangzhou: Zhejiang University Press, 1994: 251-256. (in Chinese) 曾庆勇. 微弱信号检测. 杭州: 浙江大学出版社, 1994: 251-256.
[25] Liu J F, Yang X L. Application of polynomial filter and numerical differentiation method in potentiometric stripping analysis. Instrumentation Analysis Monitoring, 2004(4): 10-14. (in Chinese) 刘建锋, 杨先麟. 多项式滤波及数值微分方法在微分电位溶出分析中的应用. 仪器仪表与分析监测,2004(4): 10-14.

[1]	Shengxiang TONG, Zhiwei SHI, Xi GENG, Lishuang WANG, Zhikun SUN, Qichang CHEN. Combinable samara aircraft and controlled separation technique [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(6): 629590-629590.
[2]	Fei MA, Qiong ZHANG, Peijun LAI, Yidi YUE. BP neural network⁃based quantitative classification model for safety in experimental flight training [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(5): 529957-529957.
[3]	Yude NI, Miaoyu YAN, Ruihua LIU. Short-term prediction of ionospheric TEC based on DOA-BP neural network [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(4): 328707-328707.
[4]	Siji WANG, Yuwei ZHANG, Kaiming HUANG, Biao LYU, Haifeng ZHAO, Hu WANG, Mingfu LIAO. An optimization method for helicopter power turbine rotor system based on improved particle swarm optimization algorithm [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(1): 228608-228608.
[5]	Zhongzhi LI, Jinyi MA, Jianliang AI, Yiqun DONG. Fault detection and classification of aerospace sensors using deep neural networks finetuned from VGG16 [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S1): 727615-727615.
[6]	Wu LIU, Yunyan WU, Wei LIU, Mingming TIAN, Tianpeng HUANG. Re-entry robust fault tolerant attitude control for RLVs considering unknown disturbances [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S1): 727787-727787.
[7]	Chenyang LIU, Dawei WU, Yize GUO, Xinsai LV, Jiani ZHOU, Shuyi SHAO. Robust adaptive attitude control of quadrotor with uncertain strong coupling [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S1): 727645-727645.
[8]	Ximing CUI, Zhipeng QIU, Jia WEI, Chi ZHANG, Kai SONG, Zhe LI, Shupeng WANG. Data-driven method for characterization of structural steel surface stress of magnetic Barkhausen noise [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(8): 427237-427237.
[9]	Zhikai WANG, Sheng CHEN, Wei FAN. Effect of neural network width on combustor emission prediction [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(5): 126816-126816.
[10]	Lei HE, Weiqi QIAN, Kangsheng DONG, Xian YI, Congcong CHAI. Aerodynamic characteristics modeling of iced airfoil based on convolution neural networks [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(5): 126434-126434.
[11]	Honglun WANG, Yanxiang WANG, Yiheng LIU. Recovery trajectory optimization for UAV towed aerial recovery based on trajectory mapping [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(20): 628775-628775.
[12]	Huailu LI, Xu WANG, Xiao WANG, Tong ZHAO, Weiwei ZHANG. Aerodynamic modeling and flight simulation of maneuver flight at high angle of attack [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(19): 128410-128410.
[13]	Xiangwei ZHU, Dan SHEN, Kai XIAO, Yuexin MA, Xiang LIAO, Fuqiang GU, Fangwen YU, Kefu GAO, Jingnan LIU. Mechanisms, algorithms, implementation and perspectives of brain⁃inspired navigation [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(19): 28569-028569.
[14]	Chenglei YUE, Xuechuan WANG, Xiaokui YUE, Ting SONG. A spacecraft rendezvous and docking method based on inverse reinforcement learning [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(19): 328420-328420.
[15]	Yiming LIANG, Guangning LI, Min XU. Method for numerical virtual flight with intelligent control based on machine learning [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(17): 128098-81280986.

Aerodynamic Modeling from Flight Data Based on WNN Optimized by Particle Swarm

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments