基于锁相平均滤波和矩函数神经网络的压气机气动失稳预警方法研究-航空发动机智能控制与健康管理

  • 黄萍 ,
  • 陈禹西 ,
  • 杨明绥 ,
  • 王媛娜 ,
  • 秦攀
展开
  • 1. 中国航发沈阳发动机研究所
    2. 中国航空发动机集团有限公司
    3. 沈阳发动机设计研究所
    4. 大连理工大学

收稿日期: 2026-03-10

  修回日期: 2026-06-01

  网络出版日期: 2026-06-04

Early Warning Method for Compressor Aerodynamic Instability Using Phase-Locked Averaging Filtering and Moment Function Neural Network

  • HUANG Ping ,
  • CHEN Yu-Xi ,
  • YANG Ming-Sui ,
  • WANG Yuan-Na ,
  • QIN Pan
Expand

Received date: 2026-03-10

  Revised date: 2026-06-01

  Online published: 2026-06-04

摘要

航空发动机压气机失稳诊断和预警是目前航空发动机领域的研究热点和难点之一。针对压气机失稳声信号的非整阶次特征成分捕获难、特征维度单一、失稳机理复杂、演化轨迹难以量化等问题,本文以某多级高速压气机为研究对象,提出了一种基于锁相平均滤波和矩函数神经网络的压气机气动失稳预警方法。该方法首先利用锁相平均滤波,实现高负荷状态下非整阶次频率扰动特征的提取;然后构建基于矩函数神经网络的失稳预警模型,该模型采用矩函数捕获失稳全局统计特征和失稳早期微弱信号的不对称分离和间歇性脉冲的局部细节特征;接着引入Box-Cox变换消除不同高阶矩特征间的异质性并采用多层感知机网络层实现对压气机失稳的预警和诊断;最后,基于试验数据开展了不同转速下的失稳预警效果验证,结果表明:所提方法能够精准刻画失稳高阶矩特征空间的演化规律,实现了对失稳先兆和稳态数据的高效可视化辨识和分离,具有较好的失稳识别准确性和鲁棒性。

本文引用格式

黄萍 , 陈禹西 , 杨明绥 , 王媛娜 , 秦攀 . 基于锁相平均滤波和矩函数神经网络的压气机气动失稳预警方法研究-航空发动机智能控制与健康管理[J]. 航空学报, 0 : 1 -0 . DOI: 10.7527/S1000-6893.2026.33560

Abstract

Diagnosis and early warning of compressor instability in aero engines are among the current research hotspots and challenges in the field of aero engines. Addressing challenges such as the difficulty in capturing non-integer order frequency compo-nents in acoustic signals, the singularity of feature dimensions, the complexity of instability mechanisms, and the difficulty in quantifying evolutionary trajectories of compressor instability, this paper proposes a compressor aerodynamic instability early warning method based on phase-locked averaging filter and moment function neural network, using a multi-stage high-speed compressor as the research object. The method first employs phase-locked averaging filter to extract non-integer order frequency disturbance features under high-load conditions. Subsequently, an instability early warning model based on mo-ment function neural network is constructed, which utilizes moment functions to capture global statistical features of instabil-ity and local detail features of asymmetric separation and intermittent pulses in early-stage weak signals. Next, Box-Cox transformation is introduced to eliminate heterogeneity among higher-order moment features, and multi-layer perceptron network layers are adopted to achieve early warning and diagnosis of compressor instability. Finally, the effectiveness of the proposed method is validated through experimental data at different rotational speeds. Results demonstrate that the method accurately characterizes the evolutionary laws of higher-order moment feature spaces, enabling efficient visualization, identi-fication, and separation of instability precursors and steady-state data, with high accuracy and robustness in instability detec-tion.

参考文献

[1]刘大响..航空动力发展的历史性机遇[J]. 航空发动机, 2005(02):1-3.
[2]薛飞, 雷雨宸, 秦宇奇, 等.轴流压气机旋转失速研究进展与展望[J/OL].推进技术, 1-32[2026-03-05].https://link.cnki.net/urlid/11.1813.v.20251117.1555.001.
[3]XUE Fei, LEI Yuchen, QIN Yuqi, WANG Man, XIONG Si, WANG Yangang.Research progress and prospects of rotating stall in axial compressors[J/OL]. Journal of Propulsion Technology., 1-32[2026-03-05]. https://link.cnki.net/urlid/11.1813.v.20251117.1555.001.
[4] 张靖煊.一种捕捉预示压气机失稳预警信号的新方法的研究[J].航空动力学报, 2004(02):270-277.
[5]Zhang Jingxuan.Study of a new method for giving warning signals of instability[J]. Journal of Aerospace Power, 2004(02):270-277.
[6] 李扬, 李应红, 吴云.基于方差分析的某轴流式压气机失速征兆起始检测[J]. 航空计算技术, 2005(01):104-105.
[7]Li Yang, Li Yinghong, Wu Yun.Detection of rotating stall inception precursor if axial flow compressor with variance analysis[J]. Aeronautical Computing Tech-nology, 2005(01):104-105.
[8]李继超, 童志庭, 聂超群等.基于互相关分析的前失速先兆检测分析[J].航空学报, 2013, 34(01):28-36
[9]Li Jichao, Tong Zhiting, Nie Chaoqun, Lin Feng.De-tection and analysis of early stall warning based on cross-correlation[J].Acta Aeronautica et Astronautica Sinica, 2013, 34(01):28-36
[10] 胡竞涛, 吴伟明, 张志博, 等.多级高速压气机喘振失稳的确定学习建模与预警[J/OL].控制理论与应用, 1-10[2026-03-05]. https:/link.cnki.net/urlid/44.1240.TP.20250717.1216.034.
[11]Hu Jingtao, Wu Weiming, Zhang Zhibo, et al.Deter-ministic learning and surge warning for a multi-stage high-speed compressor[J/OL]. Control Theo-ry& Applications, 1-10[2026-03-05]. https:/link.cnki.net/urlid/44.1240.TP.20250717.1216.034.
[12] Liu Y, Du J, Zhao D .Advances in early warning and active control of compressor instabilities for aerospace applications[J].Progress in Aerospace Scienc-es, 2025, 159101156-101156.
[13]Fan Z, Du J, Liu Y, et al.Instability warning method via fast wavelet transform in a high-speed axial flow compressor: from surge precursors to early warn-ing[J].Aerospace Science and Technology, 2026, 168(pe):111124-
[14] Ping Y, Wang M, Zhang X, et al.Centrifugal Compres-sor Instability and the Reverse Propagation Mechanism in Diffusers[J].Journal of Applied Fluid Mechanics, 2025, 18(12).
[15] Chen Y, Yang M, Zhang Z, et al.Study on the Fault Diagnosis Method of Compressor Instability by Fusing Multiple Time Domain Feature Parameters[J].Lecture Notes in Electrical Engineering, 2024:1628-1638.
[16]Wang S, Hao Y, Yadong W U, et al.Research pro-gress on rotating instability of aeroengine compres-sor[J].Acta Aeronautica et Astronautica Sinica, 2024, 45(16):n-u
[17] Zhang K, Park W .The Investigation of Rotating In-stability Under Distortion Based on a Compressor Ro-tor[J].International Journal of Aeronautical and Space Sciences, 2022, 23:471 - 483.
[18] 李育卉.基于多源数据融合的压气机失速预警研究[D].大连理工大学, 2023.
[19]Li Y H.Research on Stall Warning of Compressors Based on Multi-source Data Fusion[D]. Dalian Uni-versity of Technology, 2023.
[20]陈禹西, 杨明绥, 杨国安.压气机气动失稳故障的声学诊断技术研究进展[J].测控技术, 2023, 42(12):1-10
[21]Chen Yuxi, Yang Mingsui, Yang Guoan.Research pro-gress of acoustic diagnosis technology for compressor aerodynamic instability faults[J].Measurement & Control Technology, 2023, 42(12):1-10
[22] 孙晓峰, 胡宗安, 冯毓诚, 等.压气机旋转失速特征参数的一种声学测量方法[J].航空动力学报, 1991, (02):129-130+191.
[23]Sun X F, Hu Z A, Feng Y C, et al.An acoustic method for measuring characteristics if rotating stall in a com-pressor[J]. Journal of Aerospace Pow-er, 1991, (02):129-130+191.
[24] Sundstrom E, Semlitsch B, Mihaescy M.Acoustic sig-nature of flow instabilities in radial compressors. [J]. Journal of Sound and Vibration, 2018, 434:221-26.
[25]Tryfonidis M, Etchevers O, Paduano J D, et al.Prestall Behavior of Several High-Speed Compres-sors[J].Asme J Turbomachinery, 1994, 117(1):V001-T01
[26]Mcdougall N M, Cumpsty N A, Hynes T P.Stall In-ception in Axial Compressors[J].Journal of Tur-bomachinery, 1988, 112(1):116-123
[27]Garnier V H, Epstein A H, Greitzer E M.Rotating Waves as a Stall inception Indication in Axial Com-pressors[J].Trans.asme J.of Turbomachinery, 1991, 113(2):1098-102
[28] Day I J .Stall Inception in Axial Flow Compres-sors[J].Journal of Turbomachinery, 1991, 115(1).
[29]Paduano JD, Greitzer EM, Epstein AH.Compression system stabil ity and active control[J].Annual Review of Fluid Mechanics, 2001, 33(1):491-517
[30]Day IJ.Active suppression of rotating stall and surge in axial com pressors[J].ASME Journal of Turbomachin-ery, 1993, 115(1):40-47
[31]李宏新, 贾博博, 陈禹西, 等.多级高压比压气机气动失稳试验研究[J].航空动力学报, 2025, 40(07):236-243
[32]LI Hongxin, JIA Bobo, CHEN Yuxi, ZHANG Zhibo, et al.Experimental investigation of aerodynamic instabil-ities in a multistage high pressure ratio compressor[J].Journal of Aerospace Power, 2025, 40(07):236-243
[33]王聪, 司文杰, 文彬鹤, 等.轴流压气机旋转失速建模与检测Ⅱ:基于北航低速压气机试验台的实验研究[J].控制理论与应用, 2014, 31(10):1414-1422
[34]Wang C, Si W J, Weng H B, et al.Modeling and detec-tion of rotating stall in axial flow compressors,Ⅱ: experimental study for a low-speed compressor in Beihang University[J].Control Theory & Applications, 2014, 31(10):1414-1422
[35]王聪, 文彬鹤, 司文杰, 等.轴流压气机旋转失速建模与检测:Ⅰ——基于确定学习理论与高阶-模型的研究[J].自动化学报, 2014, 40(07):1265-1277
[36]Wang C, Weng H B, Si W J, et al.Modeling and detec-tion of rotating stall in axial flow compressors,Ⅰ: in-vestigation on high-order M-G Models via determinis-tic learning[J].ACTA AUTOMATICA SINICA, 2014, 40(07):1265-1277
[37]潘若痴, 刘德龙, 孟德君.多级高速压气机失稳模式[J].推进技术, 2025, 46(09):64-73
[38]PAN Ruochi, LIU Delong, MENG Dejun.Instability mode of a multi-stage high-speed compressor[J].Journal of Propulsion Technology, 2025, 46(09):64-73
[39] Tryfonidis M, Etchevers O, Paduano J D, et al.Prestall behavior of several high speed compressors[J].Journal of Turbomachinery, 1994.
[40] Liao S F, Chen J Y, Time frequency analysis of rotating stall by meas of wavelet transform.ASME 96 GT-57, 1996.
[41] Tahara N, Nakajima T, Kurosaki M, et al.Active stall control with practicable stall prediction system using auto-correlation coefficient[J]. 2001.
[42]杜军, 文璧, 刘元是.轴流压气机喘振状态下的声学特征及诊断方法[J].燃气涡轮试验与研究, 2020, 33(05):33-37
[43]DU Jun,WEN Bi,LIU Yuan-shi.Study on acoustic characteristics and diagnostic method of axial com-pressor under surge condition[J].Gas Turbine Exper-iment and Research, 2020, 33(05):33-37
[44] DHINGRA M, NEUMEIER Y, PRASAD J V R, et al.Stall and surge precursors in axial compressors[C]. Huntsville: 39th AIAA/ASME/SAE/ASEE Joint Propul sion Conference and Exhibit, 2003: 4425.
[45]LIU Y, LI J C, DU J, et al.Stall warning strat-egy based on fast wavelet analysis in a multistage ax-ial flow com pressor[J].Journal of Engineering for Gas Turbines and Power, 2022, 144(4):044501-
[46]Fan Z, Du J, Liu Y, et al.Instability warning method via fast wavelet transform in a high-speed axial flow compressor: from surge precursors to early warn-ing[J].Aerospace Science and Technology, 2026, 168(pe):111124-
[47]Li J, Deng Y, Zhang X, et al.Instability prediction under distorted inflow based on deep learning neural networks in an axial flow compressor[J].Physics of Fluids, 2024, 36(12):127163-
[48]范忠岗, 刘洋, 巴顿, 等.周向畸变进气下轴流压气机的失稳预报方法研究[J].推进技术, 2025, 46(04):109-117
[49]Fan Z G, Liu Y, Ba D, et al.Stall warning method in-vestigation in an axial-flow compressor with circum-ferential distortion[J].Journal of Propulsion Technolo-gy, 2025, 46(04):109-117
[50]张海波, 徐植桂.基于压力信号分析的轴流式压气机失速预测[J].南京航空航天大学学报, 2017, 49(05):684-692
[51]Zhang H B, Xu Z G, et al.Study on stall detection of axial compressor through pressure signal analysis[J].Transactions of Nanjing University of Aeronautics and Astronautics, 2017, 49(05):684-692
[52] Chen Y, Yang M, Zhang Z, et al.Study on the Fault Diagnosis Method of Compressor Instability by Fusing Multiple Time Domain Feature Parameters[J].Lecture Notes in Electrical Engineering, 2024:1628-1638.
[53]Li J, Deng Y, Zhang X, et al.Instability prediction under distorted inflow based on deep learning neural networks in an axial flow compressor[J].Physics of Fluids, 2024, 36(12):127163-
[54]Carrattieri L, Cravero C, Marsano D, et al.The Devel-opment of Machine Learning Models for Radial Com-pressor Monitoring With Instability Detec-tion[J].Journal of Turbomachinery; Transactions of the ASME, 2025, 147(5):051004-
[55] 全福祥.航空发动机失稳预测和喘振主动控制研究[D].大连理工大学, 2024.
[56]Quan F X.Instability Prediction and Active Surge Con-trol for The Aviation Engine [D]. Dalian University of Technology, 2023.
[57] 吴家威.基于生成对抗网络的轴流压气机失速预警研究[D].江西理工大学, 2024.
[58]Wu J W.Study on Stall Warning of Axial Flow Based on Generative Adversarial Networks[D]. Jiangxi Uni-versity of Science and Technology, 2024.
[59]邓雨阳, 李继超, 刘景源, 等.基于深度学习神经网络的轴流压气机失速预测[J].推进技术, 2025, 46(08):249-258
[60]Deng Y Y, Li J C, Liu J Y, et al.Stall prediction based on deep learning in axial flow compressor[J].Journal of Propulsion Technology, 2025, 46(08):249-258
[61] 王颖.轴流压气机前失速流动特征及失速预测研究[D].天津大学, 2022.
[62]Wang Y.Study on Front Stall Characteristics and Stall Prediction
[63]for an Axial Compressor.[D]. Tianjin University, 2022.
[64] 司文杰.基于确定学习理论的低速轴流压气机旋转失速检测—仿真与试验研究[D].华南理工大学, 2015.
[65]Si W J .Detection of Rotating Stall in Low-Speed Axi-al Compressors via Deterministic Learning Theory–Simulation and Experimental Study[D]. South China University of Technology, 2015.
[66] 赵宏阳.基于深度学习的轴流压气机旋转失速预测研究[D].大连理工大学, 2021.
[67]Zhao H Y.Research on Stall Prediction of Axial Com-pressors Based on Deep Learning[D]. Dalian Universi-ty of Technology, 2021.
[68] 尼克·坎普施缇.压气机气动力学[M]. 张健,杜辉,董威, 译. 上海交通大学出版社, 2021.
[69]Nick Kempesti Compressor Aerodynamics [M].Trans-lated by Zhang Jian, Du Hui, Dong Wei Shanghai Jiao Tong University Press, 2021.
Options
文章导航

/