基于信息融合的航空发动机剩余寿命预测

王华伟; 吴海桥

基于信息融合的航空发动机剩余寿命预测

南京航空航天大学民航学院,南京 210016

基金项目: 国家自然科学基金与民航局联合资助(60879001); 江苏省自然科学基金(BK2009378); 南京航空航天大学基本科研业务费专项项目(NS2010179); 江苏省青蓝工程优秀青年骨干教师计划项目

计量
- 文章访问数: 1491
- HTML浏览量: 7
- PDF量: 1815
- 被引次数: 0
出版历程
- 收稿日期: 2011-11-24
- 刊出日期: 2012-12-28

Residual useful life prediction for aircraft engine based on information fusion

College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

摘要

摘要: 利用航空发动机状态监测信息,考虑到信息本身具有的误差性和随机性等特点,采用贝叶斯线性模型融合了监测信息,实现了综合利用多源信息的进行航空发动机性能衰退评估;以性能衰退评估结果为输入变量,建立基于Gamma随机过程的可靠性评估模型,预测在指定性能可靠性水平下的剩余寿命.通过算例,分析了不同监测参数对剩余寿命预测的影响.该方法能将性能监测与可靠性分析集成到一个框架中,充分利用了多种状态监测信息,结果更加准确,更符合控制航空发动机维修决策风险的实际.
- 剩余寿命预测 /
- 系统可靠性 /
- 性能衰退 /
- 信息融合 /
- 贝叶斯线性模型
Abstract: The monitoring information has been utilized and fused for performance degradation evaluation.In consideration of random and error information, Bayesian linear model has been used for performance degradation evaluation of aircraft engine.The result of the performance degradation evaluation has been seen as input variable, and the reliability evaluation model has been built based on gamma random process which was used for forecasting residual life under predetermined reliability index.For example, the effect of different monitoring parameters on residual useful life prediction was analyzed.The method can integrate performance monitoring with reliability analysis into one framework, which utilizes monitoring information adequately. As a result of above, the goal of an accurate prediction of residual useful life has been achieved, which accords with the demand of maintenance risk control for aircraft engines.
- residual useful life prediction /
- system reliability /
- performance degradation /
- information fusion /
- Bayesian linear model

HTML

参考文献(15)

[1]	Cobel J B.Merging data sources to predict remaining useful life:an automated method to identify prognostic parameters[D].Knoxville:The University of Tennessee,2010.
[2]	Liao H,Zhao W,Guo H.Predicting remaining useful life of an individual unit using proportional hazards model and logistic regression model[C]//Proceedings of the Reliability and Maintainability Symposium(RAMS).California:IEEE Conference Publications,2006:127-132.
[3]	Vlokp J,Wnek M,Zygmunt M.Utilising statistical residual life estimates of bearings to quantify the influence of preventive maintenance actions[J].Mechanical System and Signal Processing,2004,18(4):833-847.
[4]	Wang W.A model to predict the residual life of rolling element bearings given monitored condition information to date[J].IMA Journal of Management Mathematics,2002,13(1):3-16.
[5]	王英,王文彬,方淑芬,等.状态维修两阶段预知模型研究[J].哈尔滨工业大学学报,2007,28(11):1278-1281.WANG Ying,WANG Wenbin,FANG Shufen,et al.A two-stage prediction model research on condition-based maintenance[J].Journal of Harbin Engineering University,2007,28(11):1278-1281.(in Chinese)
[6]	Gebraeel N Z,Lawly M A,Li R,et al.Residual-life distributions from component degradation signals:a Bayesian approach[J].Institute of Industrial Engineers Trans.,2005,37(6):543-557.
[7]	Baruah P,Chinnam R B.HMMs for diagnostics and prognostics in machining process[J].International Journal of Production Research,2003,43(6):1275-1293.
[8]	Camci F.Process monitoring,diagnosis and prognosis using support vector machines and hidden Markov models[D].Detorit:Graduate School of Wanye State University,2005.
[9]	Li Y G,Nilkitsaranont P.Gas turbine performance prognostic for condition-based maintenance[J].Applied Energy,2009,86(10):2152-2161.
[10]	Yam R C M,Tse P W,Li L,Tu P.Intelligent predictive decision support system for condition-based maintenance[J].Int. J Adv. Manuf. Technology,2001,17(5):383-391.
[11]	Byington C S,Watson M,Edwards D.Data-driven network methodology to remaining life predictions for aircraft actuator components[C]//Proceedings of the IEEE Aerospace Conf.MT(USA):IEEE Conference Publications,2004:3581-3589.
[12]	Gebraeel N Z,Lawley M A.A neural network degradation model for computing and updating residual life distributions[J].IEEE Transactions on Automation Science and Engineering,2008,5(1):387-401.
[13]	Przytula K W,Choi A.Reasoning framework for diagnosis and prognosis[C]//Proceedings of 2007 IEEE Aerospace conference.Big Sky,MT(USA):IEEE Conference Publications,2007:3-10.
[14]	Dong M.Yang Z B.Dyanmic Bayesian network based prognosis in machining process[J].Journal of Shanghai Jiaotong University,2008,13(3):318-322.
[15]	Goldstein M,Wooff D.Bayes linear statistics,theory & methods[M].USA:Wiley Publiser,2007.