一种基于Deep-GBM的航空发动机中介轴承故障诊断方法

田晶; 李有儒; 艾延廷

doi:10.13224/j.cnki.jasp.2019.04.003

一种基于Deep-GBM的航空发动机中介轴承故障诊断方法

doi: 10.13224/j.cnki.jasp.2019.04.003

1.
沈阳航空航天大学辽宁省航空推进系统先进测试技术重点实验室，沈阳 110136
2.
沈阳航空航天大学辽宁省航空推进系统先进测试技术重点实验室，沈阳 110136；北京交通大学信息科学研究所，北京 100044；北京交通大学现代信息科学与网络技术北京市重点实验室，北京 100044

基金项目: 国家自然科学基金（11702177）；辽宁省自然科学基金（20180550650）；中央高校基本科研业务费专项基金（2018YJS032）

计量
- 文章访问数: 1321
- HTML浏览量: 8
- PDF量: 1043
- 被引次数: 0
出版历程
- 收稿日期: 2018-05-28
- 刊出日期: 2019-04-28

Fault diagnosis of aero-engine inter-shaft bearing based on Deep-GBM

摘要

摘要: 针对航空发动机中介轴承故障信号难于识别的特点，提出了一种深度梯度提升模型（Deep-GBM）对振动信号特征进行逐层学习以提高分类模型的准确率。开展某型航空发动机中介轴承故障模拟实验，并采用经验模式分解(EMD)方法对采集的振动信号进行分解，提取内蕴模式函数(IMF)分量非线性动力学参数样本熵作为原始故障特征。采用Deep-GBM对中介轴承内环故障、内环和滚动体综合故障、正常、滚棒剥落、滚棒划伤五种不同状态进行识别。实验结果表明，所提出的Deep-GBM故障诊断准确率达到87%，相对于传统的机器学习模型准确率最高提升了28%，并具有良好的泛化能力。
- 故障诊断 /
- 中介轴承 /
- 样本熵 /
- 机器学习 /
- 梯度提升模型
Abstract: In view of the difficulty in identifying the fault signal of the inter-shaft bearing of the aero-engine, a deep gradient boasting model (Deep-GBM) was proposed to improve the precision score by learning the feature of vibration signal step by step. Fault simulation experiment was conducted on a type of aeroengine intershaft bearing. Vibration fault signal was decomposed through empirical mode decomposition (EMD) method, and intrinsin mode function (IMF) component sample entropy of nonlinear dynamics parameters was collected as base features. With the model proposed, the aero-engine inter-shaft bearing was diagnosed respectively with fault in inner ring, comprehensive fault in inner ring and rolling element, and in normal condition, with stick-spalled fault and stick-scratched fault. The experimental results showed that the fault diagnosis accuracy of the Deep-GBM reached 87%, 28% higher than that of the traditional machine learning model. Besides, the model has been proved to have good generalization ability.
- fault diagnosis /
- inter-shaft bearing /
- sample entropy /
- machine learning /
- deep gradent boosting model(Deep-GBM)

HTML

参考文献(19)

[1]	廖明夫,马振国,刘永泉,等.航空发动机中介轴承的故障特征与诊断方法［J］.航空动力学报,2013,28(12):2752-2758.LIAO Mingfu,MA Zhenguo,LIU Yongquan,et al.Fault characteristics and diagnosis method of intershaft bearing in areo-engine［J］.Journal of Aerospace Power,2013,28(12):2752-2758.(in Chinese)
[2]	田晶,艾延廷,赵明,等.基于声发射信号信息距的滚动轴承故障诊断［J］.航空动力学报,2017,32(1):148-154.TIAN Jing,AI Yanting,ZHAO Ming,et al.Fault diagnosis for rolling element bearings based on information exergy distance of acoustic emission signal［J］.Journal of Aerospace Power,2017,32(1):148-154.(in Chinese)
[3]	孟涛,廖明夫.利用时延相关解调法诊断滚动轴承的故障［J］.航空学报,2004,25(1):41-44.MENG Tao,LIAO Mingfu.Detection and diagnosis of the rolling element bearing fault by the delaied correlation envelope technique［J］.Acta Aeronautica et Astronautica Sinica,2004,25(1):41-44.(in Chinese)
[4]	GLOWACZ A,GLOWACZ W,GLOWACZ Z,et al.Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signals［J］.Measurement,2018,113:1-9.
[5]	邓巍,廖明夫,马振国.航空发动机中介轴承局部故障边带差值诊断法［J］.机械科学与技术,2012,31(2):335-339.DENG Wei,LIAO Mingfu,MA Zhenguo.Sideband difference diagnostics of local defects for aero-engine intershaft bearing［J］.Mechanical Science and Technology for Aerospace Engineering,2012,31(2):335-339.(in Chinese)
[6]	AI Yanting,GUAN Jiaoyue,FEI Chengwei,et al.Fusion information entropy method of rolling bearing fault diagnosis based on n-dimensional characteristic parameter distance［J］.Mechanical Systems and Signal Processing,2017,88:123-136.
[7]	孔亚林.基于振动信号的滚动轴承故障诊断方法研究［D］.大连:大连理工大学,2006.KONG Yalin.Research on fault diagnosis method and application for rolling element bearing based on vibration signal［D］.Dalian:Dalian University of Technology,2006.(in Chinese)
[8]	向丹,岑健.基于EMD熵特征融合的滚动轴承故障诊断方法［J］.航空动力学报,2015,30(5):1149-1155.XIANG Dan,CEN Jian.Method of roller bearing fault diagnosis based on feature fusion of EMD entropy［J］.Journal of Aerospace Power,2015,30(5):1149-1155.(in Chinese)
[9]	尉询楷,陆波,汪诚,等.支持向量机在航空发动机故障诊断中的应用［J］.航空动力学报,2004,19(6):844-848.WEI Xunkai,LU Bo,WANG Cheng,et al.Applications of support vector machines to aeroengine fault diagnosis［J］.Journal of Aerospace Power,2004,19(6):844-848.(in Chinese)
[10]	程军圣,于德介,杨宇.基于EMD和SVM的滚动轴承故障诊断方法［J］.航空动力学报,2006,21(3):575-580.CHENG Junsheng,YU Dejie,YANG Yu.Fault diagnosis of roller bearings based on EMD and SVM［J］.Journal of Aerospace Power,2006,21(3):575-580.(in Chinese)
[11]	江传尚,樊丁,马冲.小波网络在某型航空发动机故障诊断中的应用［J］.航空动力学报,2009,24(4):892-895.JIANG Chuanshang,FAN Ding,MA Chong.Application of the wavelet network in fault diagnosis for some kind of aero-engine［J］.Journal of Aerospace Power,2009,24(4):892-895.(in Chinese)
[12]	HUANG N E,SHEN Z,LONG S R,et al.The empirical mode decomposition and the Hibert spectrum for nonlinear and non-stationary time series analysis［J］.Mathematical,Physical and Engineering Sciences,1998,454(1971):903-995.
[13]	赵志宏,杨绍普.一种基于样本熵的轴承故障诊断方法［J］.振动与冲击,2012,31(6):136-140,154.ZHAO Zhihong,YANG Shaopu.Sample entropy-based roller bearing fault diagnosis method［J］.Journal of Vibration and Shock,2012,31(6):136-140,154.(in Chinese)
[14]	LECUN Y,BENGIO Y,HINTON G.Deep learning［J］.Nature,2015,521(7553):436-444.
[15]	ZHANG Wei,PENG Gaoliang,LI Chuanhao,et al.A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals［J］.Sensors,2017,17(2):425-446.
[16]	FRIEDMAN J H.Stochastic gradient boosting［J］.Computational Statistics & Data Analysis,2002,38(4):367-378.
[17]	CHEN Tianqi,GUESTRIN C.XGBoost:a scalable tree boosting system［R］.San Francisco:the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2016.
[18]	KE Guolin,MENG Qi,Finley T,et al.LightGBM:a highly efficient gradient boosting decision tree［R］.Long Beach,USA：31st Conference on Neural Information Processing Systems,2017.
[19]	BREIMAN L.Bagging predictors［J］.Machine Learning,1996,24(2):123-140.