基于深度信号分离的航空发动机可解释智能诊断方法

doi:10.3901/JME.2024.12.077

机械工程学报 ›› 2024, Vol. 60 ›› Issue (12): 77-89.doi: 10.3901/JME.2024.12.077

• 特邀专栏：可解释可信AI驱动的智能监测与诊断 • 上一篇下一篇

扫码分享

基于深度信号分离的航空发动机可解释智能诊断方法

王义^1,2, 丁嘉凯^1,2, 孙浩然^1,2, 秦毅^1,2, 汤宝平^1,2

1. 重庆大学机械与运载工程学院重庆 400044;
2. 重庆大学高端装备机械传动全国重点实验室重庆 400044

收稿日期:2023-11-20 修回日期:2024-05-10 出版日期:2024-06-20 发布日期:2024-08-23
作者简介:王义(通信作者),男,1989年出生,博士,副教授,博士研究生导师。主要研究方向为非平稳信号处理、微弱信号增强、无键相的瞬时相位估计、旋转机械状态监测、流形学习及深度学习等。E-mail:wycqdx@cqu.edu.cn;丁嘉凯,男,1996年出生,博士研究生。主要研究方向为非平稳信号处理、微弱故障增强、时频分析和变工况下旋转机械故障诊断。E-mail:cqdxdjk@cqu.edu.cn
基金资助:
国家自然科学基金资助项目(52175076)。

Interpretable Intelligent Diagnosis Method for Aero-engines Based on Deep Signal Separation

WANG Yi^1,2, DING Jiakai^1,2, SUN Haoran^1,2, QIN Yi^1,2, TANG Baoping^1,2

1. College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044;
2. State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044

Received:2023-11-20 Revised:2024-05-10 Online:2024-06-20 Published:2024-08-23

摘要/Abstract

摘要： 针对现有时频分析和信号分解等谐波提取方法在进行旋转机械无键相阶次跟踪应用时，存在无法自适应提取具有明确物理意义的转速谐波分量的问题，提出一种基于时频空间深度二值掩蔽模型的可解释性转速谐波信号自适应分离方法。首先构造一系列具有明确物理意义的转速谐波瞬时频率变化的仿真模板信号作为深度二值掩蔽模型的训练样本，然后利用构建的仿真模板信号转速基础谐波和高阶谐波的时频表征生成基础谐波时频空间二值掩蔽模型训练目标，建立起仿真模板信号时频空间和转速基础谐波时频图像之间的深度非线性映射关系，以实现转速基础谐波分量的准确分离提取和高阶谐波分量的可信掩蔽抑制，确保经深度二值掩蔽模型所得到的谐波分量具备明确的物理意义。再将深度分离所得的基础谐波分量经希尔伯特变换得到与转速信号深度非线性映射相关的瞬时相位信息，并将其应用于原始信号等角度重采样中以完成精确的阶次跟踪。综上所述，所提方法克服了传统无键相阶次跟踪方法严重依赖专家经验的问题，可为传动系统的无键相阶次跟踪提供具有明确物理意义的瞬时相位支撑。

关键词: 深度信号分离模型, 时频空间二值掩蔽, 瞬时相位信息, 变转速工况, 无键相阶次跟踪, 可解释深度模型

Abstract: To address the problem that existing harmonic extraction methods such as time-frequency analysis and signal decomposition cannot adaptively extract the rotational speed harmonic components with clear physical meaning when performing tacho-less order tracking(TLOT) applications for rotating machineries, an interpretable rotational speed harmonic signal adaptive separation method based on a time-frequency spatial deep binary mask model is proposed. Firstly, a series of simulated template signals with clear physical meaning of the instantaneous frequency(IF) change of the tacho harmonics are constructed as training samples for the deep binary mask model, and then the time-frequency representation(TFR) of the tacho fundamental harmonics and higher-order harmonics of the constructed simulated template signals are used to generate the training target of the binary mask model in the time-frequency(TF) space of the fundamental harmonics. The non-linear mapping relationship between the TF space of the simulated template signal and the TF image of the tacho fundamental harmonics is established to achieve the accurate separation and extraction of the tacho fundamental harmonic components and the credible masking suppression of the tacho higher-order harmonic components, ensuring that the harmonic components obtained by the deep binary mask model have a clear physical meaning. Then, the instantaneous phase information related to the deep nonlinear mapping of the rotational speed signal is obtained by the Hilbert transform of the fundamental harmonics obtained by deep separation, and applied to the original signal with equal angle resampling to accomplish accurate order tracking. In summary, the proposed method overcomes the problem that the traditional TLOT method relies heavily on expert experience, which can provide instantaneous phase support with clear physical meaning for TLOT of the transmission system.

Key words: deep signal separation model, time-frequency spatial binary mask, instantaneous phase information, variable speed condition, tacho-less order tracking, interpretable deep model

中图分类号:

王义, 丁嘉凯, 孙浩然, 秦毅, 汤宝平. 基于深度信号分离的航空发动机可解释智能诊断方法[J]. 机械工程学报, 2024, 60(12): 77-89.

WANG Yi, DING Jiakai, SUN Haoran, QIN Yi, TANG Baoping. Interpretable Intelligent Diagnosis Method for Aero-engines Based on Deep Signal Separation[J]. Journal of Mechanical Engineering, 2024, 60(12): 77-89.

参考文献

[1] 曹明，王鹏，左洪福，等. 民用航空发动机故障诊断与健康管理现状、挑战与机遇Ⅱ：地面综合诊断、寿命管理和智能维护维修决策[J]. 航空学报，2022，43(9)：34-73. CAO Ming，WANG Peng，ZUO Hongfu，et al. Current status，challenges and opportunities of civil aero-engine diagnostics and health management Ⅱ：Comprehensive off-board diagnosis，life management and intelligent condition based MRO[J]. Acta Aeronautica et Astronautica Sinica，2022，43(9)：34-73.
[2] 张忠强，张新，王家序，等. 基于重加权谱峭度方法的航空发动机故障诊断[J]. 航空学报，2022，43(9)：140-149. ZHANG Zhongqiang，ZHANG Xin，WANG Jiaxu，et al. Re-weighted kurtogram for aero-engine fault diagnosis[J]. Acta Aeronautica et Astronautica Sinica，2022，43(9)：140-149.
[3] 《航空发动机设计手册》总编委会. 航空发动机设计手册：第12册[M]. 北京：航空工业出版社，2002. Editorial Board for Aeroengine Design Manual. Aeroengine design manual：Vol. 12[M]. Beijing：Aviation Industry Press，2002.
[4] 曹明，黄金泉，周健，等. 民用航空发动机故障诊断与健康管理现状、挑战与机遇Ⅰ：气路、机械和FADEC系统故障诊断与预测[J]. 航空学报，2022，43(9)：21-33. CAO Ming，HUANG Jinquan，ZHOU Jian，et al. Current status，challenges and opportunities of civil aero-engine diagnostics and health management Ⅰ：Diagnosis and prognosis of engine gas path，mechanical and FADEC [J]. Acta Aeronautica et Astronautica Sinica，2022，43(9)：21-33.
[5] 杨语. 航空发动机附件机匣传动齿轮失效分析研究[D].重庆：重庆大学，2016. YANG Yu. Failure analysis of aero-engine accessory gearbox[D]. Chongqing：Chongqing University，2016.
[6] 史妍妍. 基于热分析的附件机匣若干可靠性问题研究[D]. 沈阳：东北大学，2009. SHI Yanyan. Research on some reliability problems of accessory casing based on thermal analysis[D]. Shenyang：Northeastern University，2009.
[7] ANTONI J. Cyclic spectral analysis of rolling-element bearing signals: Facts and fictions[J]. Journal of Sound and Vibration，2007，304(3-5)：497-529.
[8] LEI Y，LIN J，ZUO M J，et al. Condition monitoring and fault diagnosis of planetary gearboxes：A review[J]. Measurement，2014，48(2)：292-305.
[9] 郭瑜，秦树人. 无转速计旋转机械升降速振动信号零相位阶比跟踪滤波[J]. 机械工程学报，2004，40(3)：50-54. GUO Yu，QIN Shuren. Tacholess order tracking filtering for run-up or coast down vibration signal of rotating machinery based on zero-phase distortion digital filtering[J]. Chinese Journal of Mechanical Engineering，2004，40(3)：50-54.
[10] 汤宝平，何启源，魏玉果，等. 基于角加速度的复合计算阶次跟踪方法[J]. 机械工程学报，2008，44(8)：143-147. TANG Baoping，HE Qiyuan，WEI Yuguo，et al. Hybrid computed order tracking method based on angular acceleration[J]. Chinese Journal of Mechanical Engineering，2008，44(8)：143-147.
[11] RÉMOND D，ANTONI J，RANDALL R. Editorial for the special issue on instantaneous angular speed (IAS) processing and angular applications[J]. Mechanical Sys-tems and Signal Processing，2014，44(1-2)：1-4.
[12] WANG Y，TANG B P，QIN Y，et al. Rolling bearing fault detection of civil aircraft engine based on adaptive estimation of instantaneous angular speed[J]. IEEE Transactions on Industrial Informatics，2019，16(7)：4938-4948.
[13] BLOUGH J R. Development and analysis of time variant discrete Fourier transform order tracking[J]. Mechanical Systems and Signal Processing，2003，17(6)：1185-1199.
[14] BONNARDOT F，EL BADAOUI M，RANDALL R B，et al. Use of the acceleration signal of a gearbox in order to perform angular resampling (with limited speed fluctuation)[J]. Mechanical Systems and Signal Processing，2005，19(4)：766-785.
[15] WANG Y，PETER W T，TANG B P，et al. Order spectrogram visualization for rolling bearing fault detection under speed variation conditions[J]. Mechanical Systems and Signal Processing，2019，122(5)：580-596.
[16] PEETERS C，LECLERE Q，ANTONI J，et al. Review and comparison of tacholess instantaneous speed estimation methods on experimental vibration data[J]. Mechanical Systems and Signal Processing，2019，129(3)：407-436.
[17] ZHAO M，LIN J，XU X Q，et al. Tacholess envelope order analysis and its application to fault detection of rolling element bearings with varying speeds[J]. Sensors，2013，13(8)：10856-10875.
[18] COMBET F，GELMAN L. An automated methodology for performing time synchronous averaging of a gearbox signal without speed sensor[J]. Mechanical Systems and Signal Processing，2007，21(6)：2590-2606.
[19] RANDALL R B，SAWALHI N，COATS M. Separation of gear and bearing fault signals from a wind turbine transmission under varying speed and load[M]. Berlin：Springer，2012.
[20] FENG Z P，CHU F L，ZUO M J. Time-frequency analysis of time-varying modulated signals based on improved energy separation by iterative generalized demodulation[J]. Journal of Sound and Vibration，2011，330(6)：1225-1243.
[21] ZHAO M，LIN J，WANG X F，et al. A tacho-less order tracking technique for large speed variations[J]. Mechanical Systems and Signal Processing，2013，40(1)：76-90.
[22] LI X，CHENG J，SHAO H D，et al. A fusion CWSMM-based framework for rotating machinery fault diagnosis under strong interference and imbalanced case[J]. IEEE Transactions on Industrial Informatics，2021，18(8)：5180-5189.
[23] CHENG Y W，HU K，WU J，et al. Autoencoder quasi-recurrent neural networks for remaining useful life prediction of engineering systems[J]. IEEE/ASME Transactions on Mechatronics，2021，27(2)：1081-1092.
[24] ILIADIS M，SPINOULAS L，KATSAGGELOS A K. Deepbinarymask：Learning a binary mask for video compressive sensing[J]. Digital Signal Processing，2020，96：102591.
[25] MICHELSANTI D，TAN Z H，SIGURDSSON S，et al. Deep-learning-based audio-visual speech enhancement in presence of Lombard effect[J]. Speech Communication，2019，115(8)：38-50.
[26] ANTONI J，GRIFFATON J，ANDRÉ H，et al. Feedback on the Surveillance 8 challenge: Vibration-based diagnosis of a Safran aircraft engine[J]. Mechanical Systems and Signal Processing，2017，97(10)：112-144.
[27] 张光耀，王义，李晓蒙，等. 基于自适应谐波分量提取的航空发动机附件传动系统变速故障诊断方法[J]. 仪器仪表学报，2023，44(5)：10-20. ZHANG Guangyao，WANG Yi，LI Xiaomeng，et al. A speed-varying fault diagnosis method for the aero-engine accessory transmission system based on adaptive harmonic components extraction[J]. Chinese Journal of Scientific Instrument，2023，44(5)：10-20.

基于深度信号分离的航空发动机可解释智能诊断方法

Interpretable Intelligent Diagnosis Method for Aero-engines Based on Deep Signal Separation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	郭金道, 赵欢, 王平, 孙丹, 王双. 基于引气封油方式的轴承腔密封间隙油气两相泄漏流动特性数值与试验研究[J]. 机械工程学报, 2024, 60(3): 214-225.
[2]	江平, 刘光磊, 张瑞庭, 鲁锐. 航空弧齿锥齿轮接触印痕高度的一种控制方法[J]. 机械工程学报, 2015, 51(5): 64-70.
[3]	陈薄;陈国定;王涛. 轴承腔中均匀流体/壁面油膜分层流动分析[J]. , 2014, 50(21): 164-173.
[4]	马纲;何军;栗秀花;沈心敏. 柱面气膜密封动力特性系数的数值计算[J]. , 2013, 49(5): 55-62.
[5]	刘雨川;徐万孚;王之栎;沈心敏. 气膜端面密封角向摆动自振稳定性[J]. , 2002, 38(4): 1-6.
[6]	许兆棠;朱如鹏. 直升机复合材料传动轴的主共振分析[J]. , 2006, 42(2): 155-160.
[7]	张延超;陈国定;周连杰;罗健. 指尖密封性能优化的一种新方法[J]. , 2010, 46(10): 156-163.
[8]	徐万孚;刘雨川;李广宇;徐礼富;沈心敏. 螺旋槽干运行非接触气体密封的理论分析与试验[J]. , 2003, 39(4): 124-127.
[9]	刘雨川;王之栎;陆震;沈心敏. 端面气膜密封修正准一维可压流分析[J]. , 1999, 35(6): 10-13.
[10]	徐万孚;刘雨川;王之栎;沈心敏. 端面流体膜密封角向摆动自振产生及其半频特性的阐释[J]. , 2002, 38(9): 43-46.