涡轮叶片早期裂纹的三维叶尖间隙EEMD能量熵融合诊断方法

黄鑫; 张小栋; 刘洪成

doi:10.13224/j.cnki.jasp.2020.05.003

涡轮叶片早期裂纹的三维叶尖间隙EEMD能量熵融合诊断方法

doi: 10.13224/j.cnki.jasp.2020.05.003

基金项目: 国家自然科学基金(51575436)

计量
- 文章访问数: 411
- HTML浏览量: 7
- PDF量: 559
- 被引次数: 0
出版历程
- 收稿日期: 2019-12-06
- 刊出日期: 2020-05-28

Approach to early crack diagnosis of turbine blade based on EEMD energy entropy fusion of three-dimensional tip clearance

1.
School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China
2.
Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System,Xi’an Jiaotong University,Xi’an 710049,China

摘要

摘要: 为了解决航空发动机涡轮叶片早期裂纹故障信号微弱、难以识别的问题,提出一种基于三维叶尖间隙集成经验模态分解（EEMD）能量熵融合的涡轮叶片早期裂纹诊断方法。采集涡轮叶片三维叶尖间隙信息,利用EEMD分别对三维叶尖间隙各维信号进行处理,得到相应的固有模态函数(IMF),以此计算每一维信号分量EEMD能量熵,构建能表征叶片裂纹状态的不同EEMD能量熵高维矢量集。建立多个堆叠自动编码器(SAE)分别对各高维矢量集进行特征学习并提取所学习的深层特征表达。利用支持向量机算法(SVM)和遗传算法(GA)融合各维深层特征以综合不同维度信息进而充分判定叶片裂纹状态。通过涡轮叶片裂纹诊断试验,结果表明:所提方法能有效提高叶片早期裂纹诊断精度,其平均准确率达到98.415%,标准差仅为0.697%,具有很好的稳定性、泛化性和自适应性。
- 涡轮叶片 /
- 三维叶尖间隙 /
- 信息融合 /
- 集成经验模态分解（EEMD）
Abstract: Considering that the early crack signal of aero-engine turbine blade is weak and difficult to identify, a diagnosis method was proposed based on ensemble empirical modal decomposition (EEDM) energy entropy fusion of three-dimensional tip clearance. Three-dimensional tip clearance signals of turbine blade were collected and decomposed by using the EEMD to obtain corresponding three-dimensional intrinsic mode functions (IMFs) and calculate the EEMD entropy value of each dimensional signal in order to form different high-dimensional vector sets representing the crack fault. Several stacked autoencoders (SAE) were constructed to learn the high-level features from each high-dimensional vector set and further extract the in-depth feature expression acquired by each SAE. The support vector machine (SVM) algorithm and genetic algorithm (GA) were used to fuse these different high-level features in order to confirm adequately the early crack fault of turbine blades. Results show that the proposed method can fully dig out characteristic information of the early crack, and effectively improve the diagnosis accuracy, yielding an average accuracy of 98.415%, and its standard deviation is only 0.697%, showing its good stability, adaptivity and generalization ability.
- turbine blade /
- three-dimensional tip clearance /
- information fusion /
- ensemble empirical modal decomposition (EEMD)

HTML

参考文献(17)

[1]	陶春虎.航空发动机转动部件的失效与预防［M］.北京:国防工业出版社,2000.
[2]	PENG K,FAN D,YANG F,et al.Active generalized predictive control of turbine tip clearance for aero-engines［J］.Chinese Journal of Aeronautics,2013,26(5):1147-1155.
[3]	WITOS M,SZCZEPANIK R.Turbine engine health maintenance status monitoring with use of phase-discrete method of blade vibration monitoring［J］.Solid State Phenomena,2009,147/148/149:530-541.
[4]	赵萍,何清华,李维.某燃气涡轮工作叶片裂纹分析［J］.航空动力学报,2009,24(9):2033-2039. ZHAO Ping,HE Qinghua,LI Wei.Crack analysis of the first stage blade on a gas turbine［J］.Journal of Aerospace Power,2009,24(9):2033-2039.(in Chinese)
[5]	RIGOSI G,BATTIATO G,BERRUTI T M.Synchronous vibration parameters identification by tip timing measurements［J］.Mechanics Research Communications,2017,79:7-14.
[6]	YAMADA M,SONOYA K,SOBAYASHI T,et al.Research on the deformation of turbine blades at machining［J］.Energy and Power Engineering,2016,8(1):1-12.
[7]	滕飞,张小栋,谢思莹.涡轮3维叶尖间隙对典型故障特征的响应特性分析［J］.航空发动机,2017,43(4):90-95. TENG Fei,ZHANG Xiaodong,XIE Siying.Analysis of response characteristics of turbine 3-D tip clearance to typical fault characteristics［J］.Aeroengine,2017,43(4):90-95.(in Chinese)
[8]	ZHANG Xiaodong,WU Bing,XIE Siying.Optical fiber measurement system for 3-D variation of turbine blade tip clearance［J］.Optics and Precision Engineering,2018,26(7):1578-1587.
[9]	RUMELHART D E,HINTON G E,WILLIAMS R J.Learning representations by back-propagating errors［J］.Nature,1986,323(6088):533-536.
[10]	胡昭华,宋耀良.基于Autoencoder网络的数据降维和重构［J］.电子与信息学报,2009,31(5):1189-1192. HU Zhaohua,SONG Yaoliang.Data reduction and reconstruction based on autoencoder network［J］.Journal of Electronics and Information,2009,31(5):1189-1192.(in Chinese)
[11]	HINTON G E.Reducing the dimensionality of data with neural networks［J］.Science,2006,313(5786):504-507.
[12]	HAN J,ZHANG D,WEN S,et al.Two-stage learning to predict human eye fixations via SDAEs［J］.IEEE Trans Cybern,2016,46(2):487-498.
[13]	CORTES C,VAPNIK V N.Support-vector networks［J］.Machine Learning,1995,20(3):273-297.
[14]	雷亚国,何正嘉,訾艳阳.基于混合智能新模型的故障诊断［J］.机械工程学报,2008,44(7):112-117. LEI Yaguo,HE Zhengjia,ZI Yanyang.Fault diagnosis based on new hybrid intelligent model［J］.Journal of Mechanical Engineering,2008,44(7):112-117.(in Chinese)
[15]	于嘉鹏,孙加明,纪福森.航空发动机静叶联调机构运动分析及优化［J］.航空动力学报,2019,34(6):1193-1200. YU Jiapeng,SUN Jiaming,JI Fusen.Motion analysis and optimization of static blade joint adjustment mechanism of aeroengine［J］.Journal of Aerospace Power,2019,34(6):1193-1200.(in Chinese)
[16]	HE Zhengjia,CAI Gaigai,SHEN Zhongjie,et al.Study of operation reliability based on diagnosis information for mechanical equipment［J］.Engineering Sciences,2013,15(1):9-14.
[17]	SAID G.A new ensemble empirical mode decomposition (EEMD) denoising method for seismic signals［J］.Energy Procedia,2016,97:84-91.