基于改进K-SVD字典训练的涡扇发动机气路突变故障稀疏诊断方法

李魁; 胡宇; 孙振生

doi:10.13224/j.cnki.jasp.2020.09.023

基于改进K-SVD字典训练的涡扇发动机气路突变故障稀疏诊断方法

doi: 10.13224/j.cnki.jasp.2020.09.023

李魁¹,
胡宇^1,2,
孙振生¹

基金项目: 国家自然科学基金重大专项（91952110）; 国家自然科学基金（51905540）; 西安市科技计划项目（201805048YD26CG32(2)）; 陕西省自然科学基金（2019JM-186）,

计量
- 文章访问数: 209
- HTML浏览量: 2
- PDF量: 283
- 被引次数: 0
出版历程
- 收稿日期: 2020-03-12
- 刊出日期: 2020-09-28

Turbofan engine abrupt gas path fault diagnosis method based on improved K-SVD dictionary training and sparse theory

1.
School of Missile Engineering,Rocket Force University of Engineering,Xi’an 710025,China
2.
School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China

摘要

摘要: 以典型气路突变故障信号的稀疏特性为基础,通过对涡扇发动机部件特征原子组进行分类,提出了改进K-奇异值分解(K-singular value decomposition,K-SVD)字典训练的稀疏诊断方法,并结合气路典型突变故障开展了仿真实验研究。仿真结果表明:相比于拓展卡尔曼滤波(extended Kalman filter,EKF)和无迹卡尔曼滤波(unscented Kalman filter,UKF)方法,改进K-SVD方法对故障定位准确,无故障部件健康参数变化为0,可有效提高故障部件辨识度,避免误诊断;计算耗时与EKF方法基本相等,仅为UKF方法的03%,是一种有效的航空发动机气路突变故障在线诊断方法。
- 涡扇发动机 /
- 突变故障 /
- 稀疏方法 /
- 正交匹配追踪(OMP) /
- K-奇异值分解(K-SVD)
Abstract: The characteristic atomic group of turbofan engine components was classified and exploited to the K-SVD(K-singular value decomposition) based on the sparse characteristics of gas path abrupt fault signals,then an improved K-SVD dictionary training algorithm was proposed and used for abrupt fault diagnosis. The compared results with EKF(extended Kalman filter) and UKF (unscented Kalman filter) showed that the improved K-SVD method was accurate for fault location,and the change of health parameters of no fault components was 0,which can improve the identification of fault components effectively and avoid misdiagnosis;the calculation time was basically the same as EKF method;under similar accuracy,the time consumption of this method was only 03% of UKF method,which can be adapted for engine gas path parameter tracking and abrupt faults diagnosis.
- turbofan engine /
- abrupt fault /
- sparse method /
- ,orthogonal matching pursuit(OMP) /
- ,K-singular value decomposition(K-SVD)

HTML

参考文献(27)

[1]	宋兆泓.航空发动机典型故障分析［M］.北京:北京航空航天大学出版社,1993.
[2]	RAUSCH R T,GOEBEL K F,EKLUND N H,et al.Integrated in-flight fault detection and accommodation:a model-based study［J］.Journal of Engineering for Gas Turbines and Power,2007,129(4):962-969.
[3]	SBASTIEN J,BORGUET S.Variations on the Kalman filter for enhanced performance monitoring of gas turbine engines［D］.Liège,Belgique:University of Liège,2012.
[4]	张鹏,黄金泉.航空发动机气路故障诊断的平方根UKF方法研究［J］.航空动力学报,2008,23(1):169-173. ZHANG Peng,HUANG Jinquan.SRUKF research on aeroengines for gas path component fault diagnostics［J］.Journal of Aerospace Power,2008,23(1):169-173.(in Chinese)
[5]	KOPYTOV E,LABENDIK V,YUNUSOV S.Expert systems for evaluating the aircraft power plants ‘technical condition［J］.Journal of Transport and Communication,2010,11(1):31-37.
[6]	ROMESSIS C,MATHIOUDAKIS K.Bayesian network approach for gas path fault diagnosis［J］.Journal of Engineering for Gas Turbines and Power,2006,128(1):64-72.
[7]	GANGULI R.Application of fuzzy logic for fault isolation of jet engines［J］.Journal of Engineering for Gas Turbines and Power,2003,125(3):617-623.
[8]	DEMIRCI S,HAJIYEV C,SCHWENKE A.Fuzzy logic-based automated engine health monitoring for commercial aircraft［J］.Aircraft Engineering and Aerospace Technology,2008,80(5):516-525.
[9]	PAN Qiang,LIU Ying,ZHOU Rui,et al.An automatic abrupt signal extraction method for fault diagnosis of aero-engines［J］.Journal of Mechanical Science and Technology,2019,33(4):1633-1640.
[10]	OGAJI S O T,MARINAI S,SAMPATH S,et al.Gas-turbine fault diagnostics:a fuzzy-logic approach［J］.Applied Energy 2005,82(1):81-89.
[11]	WANG Lihui.Rough set based gas turbine fault isolation study［D］.Bedforeshire,UK:Crandfield University,2010.
[12]	MALLAT S,HWANG W L.Singularity detection and processing with wavelets［J］.IEEE Transactions on Information Theory,1992,38(2):617-643.
[13]	HUANG N E,SHEN Z,LONG S R,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis［J］.Proceedings of the Royal Socity of London:Series A Mathematical Physical and Engineering Sciences,1998,454(1971):903-995.
[14]	胡宇,张世英,罗雷,等.基于自适应容积卡尔曼滤波方法的涡扇发动机气路部件故障诊断［J］.航空动力学报,2016,31(5):1260-1266. HU Yu,ZHANG Shiying,LUO Lei,et al.Turbofan engine gas path components fault diagnosis based on adaptive cubature Kalman filter［J］.Journal of Aerospace Power,2016,31(5):1260-1266.(in Chinese)
[15]	胡宇,杨月诚,张世英,等.基于改进平方根无迹卡尔曼滤波方法的涡扇发动机气路状态监控［J］.航空动力学报,2014,29(2):441-450. HU Yu,YANG Yuecheng,ZHANG Shiying,et al.Turbofan engine gas path performance monitoring based on improved square root unscented Kalman filter［J］.Journal of Aerospace Power,2014,29(2):441-450.(in Chinese)
[16]	尹宏鹏,刘兆栋,柴毅,等.压缩感知综述［J］.控制与决策,2013,28(10):1441-1445. YIN Hongpeng,LIU Zhaodong,CHAI Yi,et al.Survey of compressed sensing［J］.Control and Decision,2013,28(10):1441-1445.(in Chinese)
[17]	李虎,徐岩.基于DSKSVD字典学习的语音信号欠定盲源分离算法［J］.计算机工程,2018,44(10):252-257. LI Hu,XU Yan.Underdetermined blind source separation algorithm for speech signal based on DSKSVD dictionary learning［J］.Computer Engineering,2018,44(10):252-257.(in Chinese)
[18]	JIANG Zhuolin,LIN Zhe,DAVIS L S.Label consistent K-SVD:learning a discriminative dictionary for recognition［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(11):2651-2664.
[19]	AHARON M,ELAD M,BRUCKSTEIN A.K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation［J］.IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[20]	白磊,杨磊,胡骏,等.基于特征值和特征向量的测量参数选择［J］.航空动力学报,2019,34(1):195-200. BAI Lei,YANG Lei,HU Jun,et al.Selection of measurement parameters based on eigenvalues and eigenvectors［J］.Journal of Aerospace Power,2019 34(1):195-200.(in Chinese)
[21]	SALLEE G P.Performance deterioration based on existing (historical) data-JT9D jet engine diagnostics program［R］.NASA/CR-135448,1978.
[22]	FENG Lu,HUANG Jinquan,L Yiqiu.Gas path health monitoring for a turbofan engine based on a nonlinear filtering approach［J］.Energies,2013,6(1):492-513.
[23]	SIMON D L,BIRD J,DAVISON C,et al.Benchmarking gas path diagnostic methods:a public approach［R］.ASME Paper GT-2008-51360,2008.
[24]	CHEN S S,SAUNDERS D M A.Atomic decomposition by basis pursuit［J］.Society for Industrial and Applied Mathematics (SIAM) Review,2001,43(1):129-159.
[25]	TROPP J,GILBERT A.Signal recovery from random measurements via orthogonal matching pursuit［J］.IEEE Transactions on Information Theory,2007,53(12):4655-4666.
[26]	石陆友,朱杰堂,胡宇,等.基于改进遗传算法的涡扇发动机气路传感器优化［J］.西北工业大学学报,2017,35(增刊1):1-8. SHI Luyou,ZHU Jietang,HU Yu,et al.Optimization of gas path sensors of turbofan engine based on improved genetic algorithm［J］.Journal of Northwestern Polytechnical University,2019 35(Suppl.1):1-8.(in Chinese)
[27]	张鹏.基于卡尔曼滤波的航空发动机故障诊断技术研究［D］.南京:南京航空航天大学,2009. ZHANG Peng.Aeroengine fault diagnostics based on Kalman filter［D］.Nanjing:Nanjing University of Aeronautics and Astronautics,2009.(in Chinese)