基于EM-KF算法的直升机主减速器剩余寿命预测方法

孙磊; 贾云献; 蔡丽影; 王卫国; 林国语

doi:10.13224/j.cnki.jasp.2015.02.022

基于EM-KF算法的直升机主减速器剩余寿命预测方法

doi: 10.13224/j.cnki.jasp.2015.02.022

1. 军械工程学院装备指挥与管理系, 石家庄 050003;
2. 总参陆航研究所一室, 北京 100121;
3. 军械工程学院军械技术研究所, 石家庄 050003;
4. 军械工程学院科研部, 石家庄 050003

基金项目:

预研项目(51327020101)

详细信息

作者简介:
孙磊(1985-),男,河北石家庄人,助理研究员,博士,主要从装备维修理论及其应用研究.

中图分类号: V328.5;TH17
计量
- 文章访问数: 1063
- HTML浏览量: 5
- PDF量: 788
- 被引次数: 0
出版历程
- 收稿日期: 2013-09-07
- 刊出日期: 2015-02-28

Remaining useful life estimation method of helicopter's main retarder based on EM-KF algorithm

1. Department of Equipment Command and Management, Ordnance Engineering College, Shijiazhuang 050003, China;
2. 1st Laboratory, Ariation Research Institude for the Headquarters of General Staff, Beijing 100121, China;
3. Ordnance Technique Research Institution, Ordnance Engineering College, Shijiazhuang 050003, China;
4. Department of Research, Ordnance Engineering College, Shijiazhuang 050003, China

摘要

摘要: 为解决间接状态监测数据下直升机主减速器剩余寿命预测难以估算的难题,提出了一种卡尔曼滤波和期望最大化算法相结合的剩余寿命预测方法.该方法可以根据不断更新振动信号特征值迅速且有效地估计出模型参数,进而预测不同运行时间主减速器的剩余寿命分布,最后对主减速器试验数据进行了案例分析.结果表明:该方法能够有效估计主减速器的剩余寿命分布,通过与主减速器剩余寿命准确值对比发现,剩余寿命准确值绝大多数落于剩余寿命预测值的95%置信区间内,表明该方法具有好的准确性,进而避免故障的发生.
- 卡尔曼滤波 /
- 期望最大化算法 /
- 参数估计 /
- 剩余寿命预测 /
- 主减速器
Abstract: A remaining useful life prediction method was proposed based on Kalman filter and expectation-maximization algorithm to solve the estimation problem of remaining useful life of helicopter's main retarder with introduction of indirect condition information. The proposed method can estimate the model parameters rapidly and effectively by updating characteristic value of vibration signal, and then remaining useful life distribution of main retarder was estimated at different working times. Finally, the case analysis was conducted through the test data of main retarder. The results demonstrate that the proposed method can effectively estimate the remaining useful life distribution of main retarder. Through comparison of real remaining useful life and estimated remaining useful life of main retarder, it is found that the estimated remaining useful life is mainly contained within 95% confidence interval, showing the proposed method has well accuracy, which can avoid the occurrence of the fault.
- Kalman filter /
- expectation-maximization algorithm /
- parameter estimation /
- remaining useful life estimation /
- main retarder

HTML

参考文献(15)

[1]	黄中华,尹泽勇,丁文强.直升机减速器故障齿轮振动信号特征研究[J].长沙航空职业技术学院学报,2007,7(3):36-39. HUANG Zhonghua,YIN Zeyong,DING Wenqiang.Research on vibration signal feature of helicopter gearbox's fault gear[J].Changsha Aeronautical Vocational and Technical Colledge Journal,2007,7(3):36-39.(in Chinese)
[2]	Sikorska J Z,Hodkiewicz M,MA Lin.Prognostic modelling options for remaining useful life estimation by industry[J].Mechanical Systems and Signal Processing,2011,25(5):1803-1836.
[3]	Heng Aiwina,ZHANG Sheng,Andy C C.Rotating machinery prognostics:state of the art,challenges and opportunities[J].Mechanical Systems and Signal Processing,2009,23(3):724-739.
[4]	王新峰,邱静,刘冠军.基于离散粒子群优化算法的直升机减速器齿轮故障特征选择[J].航空动力学报,2005,20(6):969-972. WANG Xinfeng,QIU Jing,LIU Guanjun.Discrete particle swarm optimization algorithm for gearbox fault symptom selection[J].Journal of Aerospace Power,2005,20(6):969-972.(in Chinese)
[5]	Jardine A K S,LIN Daming.A review on machinery diagnostics and prognostics implementing condition-based maintenance[J].Mechanical Systems and Signal Processing,2006,20(7):1483-1510.
[6]	Chinnam R B,Baruah P.A neuro-fuzzy approach for estimating mean residual life in condition-based maintenance systems[J].International Journal of Materials and Product Technology,2004,20(1/2/3):166-179.
[7]	Kacprzynski G J,Sarlashkar A,Roemer M J.Predicting remaining life by fusing the physics of failure modeling with diagnostics[J].Journal of Metal,2004,56(3):29-35.
[8]	SI Xiaosheng,WANG Wenbin,HU Changhua.Remaining useful life estimation:a review on the statistical data driven approaches[J].European Journal of Operational Research,2011,213(1):1-14.
[9]	Patrick-Aldaco R.A model based framework for fault diagnosis and prognosis of dynamical systems with an application to helicopter transmissions[D].Atlanta:Georgia Institute of Technology,2007.
[10]	Orchard M E,Vachtsevanos G J.A particle-filtering approach for on-line fault diagnosis and failure prognosis[J].Transactions of the Institute of Measurement and Control,2009,31(4):221-224.
[11]	Bechhoefer E,Clark S,He D.A state-space model for vibration based prognostics[R].Portland:Annual Conference of The Prognostics and Health Management Society,2010.
[12]	Harvey A,Koopman S J,Shephard N.State space and unobserved component models:theory and applications[M].Cambridge:Cambridge University Press,2004.
[13]	Andrieu C,Doucet A.Online expectation-maximization type algorithms for parameter estimation in general state space models[R].Vancouver,Canada:IEEE International Conference of Acoustics,Speech and Signal Processing,2003.
[14]	Achmad W,Bo-Suk Y.Application of relevance vector machine and survival probability to machine degradation assessment[J].Expert Systems with Applications,2011,38(3):2592-2599.
[15]	Achmad W,Bo-Suk Y.Machine health prognostics using survival probability and support vector machine[J].Expert Systems with Applications,2011,38(7):8430-8437.