融合数据自适应BPNN的倾转旋翼机回转颤振边界预测

  • 郑礼雄 ,
  • 陈喆 ,
  • 王鑫 ,
  • 招启军
展开
  • 南京航空航天大学

收稿日期: 2025-04-25

  修回日期: 2025-04-29

  网络出版日期: 2025-05-06

基金资助

国家自然科学基金

Prediction of whirl flutter boundary for tiltrotor aircraft based on BPNN with adaptive data

  • ZHENG Li-Xiong ,
  • CHEN Zhe ,
  • WANG Xin ,
  • ZHAO Qi-Jun
Expand

Received date: 2025-04-25

  Revised date: 2025-04-29

  Online published: 2025-05-06

摘要

针对倾转旋翼机的气弹不稳定性问题,提出了一种基于BP神经网络(BPNN)的倾转旋翼机回转颤振边界预测方法。首先,基于Hamilton原理及多体动力学方法建立了一套倾转旋翼机多模态耦合气弹稳定性分析模型。其次,生成了对系统稳定性表征强相关参数下的最小模态阻尼比数据,搭建了人工神经网络预测模型。最后,提出了一种数据自适应加密方法提高神经网络模型预测精度。结果表明:在训练范围内,计算值与预测值最大误差为3.24%,平均相对误差为0.031%;在训练范围外,最大误差为6.51%,平均相对误差为0.089%;训练后的人工神经网络模型表现出较好的泛化性且拟合精度高,无论训练范围内外,都能以较少的样本数据实现高效高精度的预测;加密方法有效提高了预测精度,特别是在回转颤振临界点的预测中表现突出,尽量避免了明显的峰-峰值波动效应。此外,BPNN为处理大规模复杂数据提供了新的工具和方法,拓展了倾转旋翼机气弹动力学研究和应用的新视角。

本文引用格式

郑礼雄 , 陈喆 , 王鑫 , 招启军 . 融合数据自适应BPNN的倾转旋翼机回转颤振边界预测[J]. 航空学报, 0 : 1 -0 . DOI: 10.7527/S1000-6893.2025.32159

Abstract

To address the aeroelastic instability issues of tiltrotor aircraft, a method for predicting the whirl flutter boundary of tiltrotor aircraft based on Back-propagation Neural Network (BPNN) was proposed. Firstly, a multi-modal coupled aeroelastic stability analysis model for tiltrotor aircraft was established based on Hamilton's principle and multi-body dynamics methods. Secondly, minimal modal damping ratio data under strongly correlated parameters characterizing system stability were generated, and an artificial neural network prediction model was constructed. Finally, an adaptive data refinement method was proposed to enhance the prediction accuracy of the neural network model. The results show that within the training range, the maximum error between the calculated and predicted values is 3.24%, with an average relative error of 0.031%; outside the training range, the maximum error is 6.51%, and the average relative error is 0.089%. The trained BPNN model exhibits good generalization and high fitting accuracy, enabling efficient and high-precision predictions with fewer sample data, both within and outside the training range. The refinement method effectively improves prediction accuracy, particularly excelling in the prediction of the critical point of whirl flutter, significantly mitigating the peak-to-peak fluctuation effects. Furthermore, BPNN provides new tools and methods for handling large-scale complex data, expanding new perspectives for the research and application of aeroelastic dynamics in tiltrotor aircraft.

参考文献

[1] 张卫国, 唐敏, 武杰, 等. 倾转旋翼机风洞试验综述[J]. 航空学报, 2024, 45(09): 530114.
ZHANG W G, TANG M, WU J, et al. Overview of wind tunnel test research on tiltrotor aircraft[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(09):530114 (in Chinese).
[2] KVATERNIK R G. Experimental and analytical studies in tilt rotor aeroelasticity[C]//Presented at the AHS/NASA Ames Specialists’ Meeting on Ro-torcraft Dynamics, Moett Field, C. A., 1974.
[3] YOUNG M I, LYTWYN R T. The influence of blade flapping restraint on the dynamic stability of low disk loading propeller-rotors[C]//Presented at the 23rd Annual National Forum of the American Helicopter Society, Washington D. C., 1967.
[4] JOHNSON W. Dynamics of tilting proprotor aircraft in cruise flight[R]. Ames Research Center and U.S. Army Air Mobility R&D Laboratory Moffett Field, NASA-TN-D-7677, 1974.
[5] SETTLE T B, KIDD, D.L. Evolution and test history of the V-22 0.2-scale aeroelastic model[C]//Presented at the American Helicopter Society National Specialists’ Meet-ing on Rotorcraft Dynamics, Arlington, Texas, 1989.
[6] WILLIAM T Y, JR, RAYMOND G K. A historical overview of aeroelasticity branch and transonic dynamics tunnel contributions to rotorcraft technology and devel-opment[R]. NASA/TM 2001 211054, ARL-TR-2564, 2001.
[7] NIXON M W. Aeroelastic response and stability of tiltrotors with elastically coupled composite rotor blades[D]. Washington: University of Maryland, 1993.
[8] DAVID J P, RAYMOND G K, MARK W. Nixon, and etc. A wind-tunnel parametric investigation of tiltrotor whirl-flutter stability boundaries[C]//Presented at the American Helicopter Society 57th Annual Forum, Wash-ington D. C., 2001.
[9] ACREE C W, JR. Impact of technology on heavy lift tiltrotors[C]//Presented at the American Helicopter Socie-ty 62nd Annual Forum, Phoenix AZ, 2006.
[10] Johnson S C. Design and testing of a small, semi-span, prop-rotor model for whirl flutter stability[D]. State Col-lege: Pennsylvania State University, 2014: 31-65.
[11] KAMBAMPATI S. Optimization of composite tiltrotor wings with extensions and winglets[D]. State College: Pennsylvania State University, 2016: 5-30.
[12] IVANCO T G, KANG H, KRESHOCK A R, et al. Gen-eralized predictive control for active stability aug-mentation and vibration reduction on an aeroelastic tiltrotor model[C]//Proceedings of the AIAA Science and Technology Forum and Exposition, San Diego, 2022.
[13] 徐敏. 倾转旋翼机的发展与关键技术综述[J]. 直升机技术, 2003(02): 40-44.
XU M. Overview of development and key technologies of tiltrotor[J]. Helicopter Technology, 2003(2): 40-44 (in Chinese).
[14] 邓景辉. 高速直升机关键技术与发展[J]. 航空学报, 2024, 45(09): 529085.
DENG J H. Key technologies and development for high-speed helicopters[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(09): 529085 (in Chinese).
[15] 杨卫东, 董凌华. 倾转旋翼过渡状态瞬态响应分析与试验[J]. 航空动力学报, 2005, 20(5): 882-889.
YANG W D, DONG L H. Analysis and experiments of the tiltrotor transient response during transition flight[J]. Journal of Aerospace Power, 2005, 20(5): 882-889 (in Chinese).
[16] 杨卫东, 董凌华. 变转速倾转旋翼机多体系统气弹响应分析[J]. 哈尔滨工业大学学报, 2006, 38(2): 282-286+324.
YANG W D, DONG L H. Multi-body aeroelastic analy-sis of tiltrotor with varying rotor rotational speed[J]. Journal of Harbin Institute of Technology, 2006, 38(2): 282-286+324 (in Chinese).
[17] 董凌华, 杨卫东. 倾转旋翼/机翼耦合系统过渡飞行瞬态响应分析[J]. 南京航空航天大学学报, 2006(03): 361-366.
DONG L H, YANG W D. Transient response analysis of rotor/wing coupled during tiltrotor transition flight[J]. Journal of Nanjing University of Aeronautics and Astro-nautics, 2006(03): 361-366 (in Chinese).
[18] 崔超. 基于机翼控制的倾转旋翼机回转颤振主动抑制研究[D]. 南京航空航天大学, 2019: 9-20.
CUI C. Active suppression on whirl flutter of tiltrotor aircraft by wing controlled[D]. Nanjing: Nanjing Univer-sity of Aeronautics and Astronautics, 2019: 9-20 (in Chi-nese).
[19] 薛立鹏, 张呈林. 前飞状态倾转旋翼机气弹稳定性建模[J]. 航空动力学报, 2009, 24(2): 255-261.
XUE L P, ZHANG C L. Modeling study on tiltrotor's aeroelastic stability in cruise flight[J]. Journal of Aero-space Power, 2009, 24(2): 255-261 (in Chinese).
[20] LI Z Q, XIA P Q. Aeroelastic stability of full-span tiltrotor aircraft model in forward flight[J]. Chinese Journal of Aeronautics, 2017, 30(6): 1885–1894.
[21] 李治权, 夏品奇. 一种改进的前飞时倾转旋翼机非定常气弹动力学模型[J]. 中国科学: 技术科学, 2018, 48(8): 901-907.
LI Z Q, XIA P Q. An improved unsteady aeroelastic model for tiltrotor aircraft in forward flight[J]. Sci Sin Tech, 2018, 48(8): 901-907 (in Chinese).
[22] 邓旭东, 胡和平. 倾转旋翼机螺旋颤振稳定性研究[J]. 空气动力学学报, 2018, 36(6): 1041-1046.
DENG X D, HU H P. Study on whirl-flutter stability of a tiltrotor aircraft[J]. Acta Aerodynamica Sinica, 2018, 36(6): 1041-1046 (in Chinese).
[23] LI H X, QU X J, WANG W J. Multi-body motion mod-eling and simulation for tilt rotor aircraft[J]. Chinese Journal of Aeronautics, 2010, 23(04): 415-422.
[24] RISO C, GHADAMI A, CESNIK C E S, et al. Data-driven forecasting of post-flutter responses of geometri-cally nonlinear wings[J]. AIAA Journal, 2020, 06: 2726-2736.
[25] YUAN H, KOU J, GAO C, et al. Resolvent analysis for flutter boundary prediction in transonic flow[J]. AIAA Journal, 2024, 62(08): 3191-3195.
[26] 郑礼雄, 王博, 招启军, 等. 倾转旋翼机多模态耦合动力学建模和气弹稳定性参数影响[J]. 航空动力学报, 2025, 40(3): 20230445.
ZHENG Lixiong, WANG Bo, ZHAO Qijun, et al. Mul-ti-mode coupling dynamic modeling and influence of aeroelastic stability parameters of tiltrotor aircraft[J]. Journal of Aerospace Power, 2025, 40(3): 20230445 (in Chinese).
[27] TSAI F, SUTHERLAND J, DATTA G A. Develop-ment and whirl flutter test of the Maryland Tiltrotor Rig[J]. Journal of the American Helicopter Society. 2024, 69(01): 1-15.
[28] SU J Y, CHEN Y, ZHANG D B, et al. Full-parameter identification model based on back propagation algorithm for brushless doubly fed induction generator[J]. IEEE Transactions on Power Electronics, 2020, 35(10): 9953-9958.
[29] 马菲, 张琼, 赖培军, 等. 基于BP神经网络的试飞训练安全性量化模型[J]. 航空学报, 2024, 45(05): 417-430.
MA F, ZHANG Q, LAI P J, et al. BP neural network-based quantitative classification model for safety in ex-perimental flight training[J]. Acta Aeronautica et Astro-nautica Sinica, 2024, 45(05): 417-430 (in Chinese).
文章导航

/