一种基于GRU神经网络的航空发动机叶片颤振快速预测方法

姜嘉宇; 黄璜; 陈美宁; 曹博超

doi:10.7638/kqdlxxb-2025.0026

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

一种基于GRU神经网络的航空发动机叶片颤振快速预测方法

研究论文 | 更新时间：2026-05-28

- 一种基于GRU神经网络的航空发动机叶片颤振快速预测方法
- A rapid prediction method for flutter of aero-engine blades based on modal shape decomposition combined with GRU neural network
- 空气动力学学报 2025年43卷第9期页码：28-38
- 作者机构：
  
  1. 复旦大学航天航空系,上海,200433
  2. 天目山实验室,杭州,311115
  3. 中国航发商用航空发动机有限责任公司,上海,200241
- 作者简介：
  
  姜嘉宇（1998—），四川成都人，硕士研究生，研究方向：叶片颤振分析. E-mail：jiangjiayu_202@163.com
  曹博超*，副教授，研究方向：空气动力学、实验流体力学、强化学习. E-mail：cbc@fudan.edu.cn
- 基金信息：
  
  航空发动机及燃气轮机基础科学中心项目（P2023-B-Ⅱ-001-001）;教育部“春晖计划”合作科研项目（202200745）
- DOI：10.7638/kqdlxxb-2025.0026
  中图分类号： V215.3+4;O352;TP181
- 纸质出版：2025
- 稿件说明：
移动端阅览
姜嘉宇, 黄璜, 陈美宁, 等. 一种基于GRU神经网络的航空发动机叶片颤振快速预测方法[J]. 空气动力学学报, 2025, 43(9): 28−38.

JIANG Jiayu, HUANG Huang, CHEN Meining, et al. A rapid prediction method for flutter of aero-engine blades based on modal shape decomposition combined with GRU neural network[J]. 2025, 43(9): 28-38.
姜嘉宇, 黄璜, 陈美宁, 等. 一种基于GRU神经网络的航空发动机叶片颤振快速预测方法[J]. 空气动力学学报, 2025, 43(9): 28−38. DOI： 10.7638/kqdlxxb-2025.0026

JIANG Jiayu, HUANG Huang, CHEN Meining, et al. A rapid prediction method for flutter of aero-engine blades based on modal shape decomposition combined with GRU neural network[J]. 2025, 43(9): 28-38. DOI： 10.7638/kqdlxxb-2025.0026.

摘要

航空发动机叶片颤振是由气动弹性失稳引发的重大安全隐患，其传统预测方法需要进行大量非定常流场仿真。为此，本文提出了一种基于模态振型分解并结合门控循环单元（gated recurrent unit

GRU）神经网络模型的发动机叶片气动载荷计算方法，并将其应用于发动机叶片气动阻尼的快速估算及颤振分析。首先对发动机叶片的固有振型模态进行弯扭分解并计算出弯曲模态和扭转模态对应的气动模态力，然后通过时序GRU神经网络分别建立弯曲模态和扭转模态气动模态力与弯扭广义运动变量之间的映射，并将该映射关系应用于一定频率范围内不同弯扭比叶片气动阻尼的计算，进而预测颤振。以NASA Rotor67转子模型为例，对弯扭气动模态力模型进行了验证，并实现了不同弯扭比模态下叶片的颤振分析。结果表明，该模型可以在一定频率范围内对发动机叶片的非定常气动载荷进行较准确的估计，并能针对具有不同弯扭比振型模态的叶片进行快速气动阻尼估算。本文发展的方法能够显著加快航空发动机叶片的颤振设计过程。

Abstract

Aeroengine blade flutter poses a critical safety hazard induced by aeroelastic instability

with traditional prediction methodologies requiring extensive unsteady flow field simulations that entail substantial computational time. This paper proposes a method for calculating aerodynamic loads on aero-engine blades based on modal shape decomposition combined with a gated recurrent unit (GRU) neural network model

and applies it to rapid estimation of aerodynamic damping and flutter analysis of aero-engine blades. We first perform bending-torsion decomposition on the blade's natural vibration modes and calculate corresponding aerodynamic modal forces for both bending and torsion modes. Subsequently

temporal GRU neural networks are employed to establish mapping relationships between aerodynamic modal forces and generalized motion variables for both bending and torsion modes. These established mappings are then applied to compute aerodynamic damping and predict flutter for blades with different bending-torsion ratios within specific frequency ranges. Using the NASA Rotor67 rotor model as a case study

the proposed aerodynamic modal force model for bending-torsion modes is validated

and flutter analysis is implemented for blades with varying bending-torsion ratio modes. Results demonstrate that the model can accurately estimate unsteady aerodynamic loads on aero-engine blades within certain frequency ranges and enable efficient aerodynamic damping estimation for blades with different bending-torsion ratio vibration modes. The method developed in this study significantly accelerates the flutter design process of aero-engine blades.

关键词

Keywords

references

GAMBEL J, PEITSCH D, SCHNEIDER S. Experimental investigations on aeroelastic stability of combined plunge-pitch mode shapes in a linear compressor cascade[J]. Journal of Turbomachinery, 2024, 146(12): 121010. doi: 10.1115/1.4065946

SHU G G, CHENG J, ZHANG X Y, et al. Structural integrity analysis of heavy-duty gas turbine[J]. Journal of Chinese Society of Power Engineering, 2022, 42(12): 11 (in Chinese). doi: 10.19805/j.cnki.jcspe.2022.12.007

TIAN X, ZHENG Y. The time domain aeroelastic analysis of airfoil flutter[J]. Science Technology and Engineering, 2010, 10(19): 4704−4708 (in Chinese). doi: 10.3969/j.issn.1671-1815.2010.19.022

XI Z Y, DAI Y T, HUANG G J, et al. Airfoilstall flutter prediction based on DeepONet[J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(3): 626-634 (in Chinese). doi: 10.6052/0459-1879-23-522

WAITE J J, KIELB R E. Physical understanding and sensitivities of low pressure turbine flutter[J]. Journal of Engineering for Gas Turbines and Power, 2015, 137: 012502. doi: 10.1115/1.4028207

YU P, HU Z Y, HU J X, et al. Numerical studies on the aeroelasticity of a shipboard helicopter rotor during engagement and disengagement with ship motions using CFD/CSD coupling approach[J]. Aerospace Science and Technology, 2023, 141: 108559. doi: 10.1016/j.ast.2023.108559

HUANG J, YAO W X, JIANG Z P, et al. CFD/CSD fully implicit tightly coupled studyon limit cycle flutter of wing[J]. Journal of Vibration, Measurement Diagnosis, 2020, 40(3): 494-500, 624-625 (in Chinese). doi: 10.16450/j.cnki.issn.1004-6801.2020.03.010

BENDIKSEN O, FRIEDMANN P. Coupled bending-torsion flutter in cascades[J]. AIAA Journal, 1980, 18(2): 194−201. doi: 10.2514/3.50748

CLARK S T. Design for coupled-mode flutter and non-synchronous vibration in turbomachinery[D]. USA, Durham: Duke University, 2013. doi: 10.1611/7190

ANANTH S M, KUSHARI A. Quasi-steady prediction of coupled bending-torsion flutter under classic surge[J]. Journal of Applied Mechanics, 2013, 80(5): 051010. doi: 10.1115/1.4023617

SUN Y C, SHI J H, YANG Y, et al. Extended influence coefficient method for meshing stiffness evaluation of spur gears considering rotor flexibility[J]. Mechanical Systems and Signal Processing, 2025, 224: 112075. doi: 10.1016/j.ymssp.2024.112075

ZHANG C, SUN S, HAN Y H. Research on mechanical flutter detection of wind turbine blades under parameter coupling[J]. Automation Instrumentation, 2024, 39(1): 102−106(in Chinese). doi: 10.19557/j.cnki.1001-9944.2024.01.022

VAHDATI M, CUMPSTY N. Aeroelastic instability in transonic fans[J]. Journal of Engineering for Gas Turbines and Power, 2016, 138(2): 022604. doi: 10.1115/1.4031225

HUANG J, YAO W X, JIANG Z P, et al. Influence of radial inflow distortion on flutter characteristics of gas turbine compressor blades[J]. Journal of Chinese Society of Power Engineering, 2024, 44(9): 1361−1369 (in Chinese). doi: 10.19805/j.cnki.jcspe.2024.240194

BESEM F M, KIELB R E. Influence of the tip clearance on a compressor blade aerodynamic damping[J]. Journal of Propulsion and Power, 2017, 33(1): 227−233. doi: 10.2514/1.b36121

CONG J Q, JING J P, DAI Z Z, et al. Influence of circumferential grooves on the aerodynamic and aeroelastic stabilities of a transonic fan[J]. Aerospace Science and Technology, 2021, 117: 106945. doi: 10.1016/j.ast.2021.106945

DUAN X B, CONG J Q, DAI Z Z, et al. Influence mechanism and quantificational evaluation of key factors affecting flutter stability of a transonic fan[J]. Aerospace Science and Technology, 2023, 138: 108312. doi: 10.1016/j.ast.2023.108312

ABDUKHAKIMOV F A, VEDENEEV V V, KOLOTNIKOV M E, et al. Numerical investigation of the effect of design parameters on the blade flutterr prediction[J]. Journal of Machinery Manufacture and Reliability, 2019, 48(2): 111−118. doi: 10.3103/S105261881902002X

DONG X, ZHANG Y F, ZHANG Y J, et al. Numerical simulations of flutter mechanism for high-speed wide-chord transonic fan[J]. Aerospace Science and Technology, 2020, 105: 106009. doi: 10.1016/j.ast.2020.106009

VOGT D M, FRANSSON T H. Experimental investigation of mode shape sensitivity of an oscillating low-pressure turbine cascade at design and off-design conditions[J]. Journal of Engineering for Gas Turbines and Power, 2007, 129(2): 530−541. doi: 10.1115/1.2436567

ISOMURA K. The effect of blade vibration mode on a flutter in a transonic fan[M]//Unsteady Aerodynamics and Aeroelasticity of Turbomachines. Dordrecht: Springer Netherlands, 1998: 725-732. doi: 10.1007/978-94-011-5040-8_47

MANNARINO A, MANTEGAZZA P. Nonlinear aeroelastic reduced order modeling by recurrent neural networks[J]. Journal of Fluids and Structures, 2014, 48: 103−121. doi: 10.1016/j.jfluidstructs.2014.02.016

LIU Y P, LI Y Z, LI L L, et al. A fast prediction model of blade flutter in turbomachinery based on graph convolutional neural network[J]. Aerospace Science and Technology, 2024, 148: 109119. doi: 10.1016/j.ast.2024.109119

CHO K, VAN MERRIENBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder–decoder for statistical machine translation[C]// 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar. Stroudsburg, PA, USAACL, 2014: 1724-1734. doi: 10.3115/v1/d14-1179

AGARAP A F M. A neural network architecture combining gated recurrent unit (GRU) and support vector machine (SVM) for intrusion detection in network traffic data[C]// 2018 10th International Conference on Machine Learning and Computing, Macao, China. ACM, 2018. doi: 10.1145/3195106.3195117

LI Y F, CHANG J T. Research on time sequence prediction of supersonic cascade flow field based on compressed sensing artificial neural network[J]. Aerospace Science and Technology, 2023, 142: 108684. doi: 10.1016/j.ast.2023.108684

HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504−507. doi: 10.1126/science.1127647

REN J, HUANG H, WANG D X, et al. An efficient coupled-mode flutter analysis method for turbomachinery[J]. Aerospace Science and Technology, 2020, 106: 106215. doi: 10.1016/j.ast.2020.106215

STRAZISAR A J, POWELL J A. Laser anemometer measurements in a transonic axial flow compressor rotor[J]. Journal of Engineering for Power, 1981, 103(2): 430−437. doi: 10.1115/1.3230738

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于多支微射流的超声速射流主动控制

无人机气动/风能获取一体化设计

基于稀疏神经核的多保真度代理模型

基于柔性智能蒙皮的翼型流场预测和重建方法

数据驱动的升力体飞行器表面热流快速预测