基于性能退化数据融合的航空发动机剩余寿命预测方法  

Aeroengine Remaining Life Prediction Method Based on Performance Degradation Data Fusion

作　　者：刘君强[1] 谢吉伟 LIU Junqiang;XIE Jiwei(College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Nanjing 21106,China)

机构地区：[1]南京航空航天大学民航学院,南京211106

出　　处：《武汉理工大学学报（交通科学与工程版）》2020年第6期994-998,1003,共6页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：国家自然科学基金项目(U1533128,60939003);中国博士后面上基金(2012M521081);中国博士后基金特别项目(2013T60537);江苏省高校哲学社会科学研究项目(2014SJD041)资助。

摘　　要：针对当前仅使用性能退化数据而导致发动机剩余寿命预测精度不高的问题,研究了融合无失效数据与现场性能退化数据的航空发动机个体剩余寿命预测模型.该模型使用随机参数的Wiener过程对航空发动机性能退化进行建模并使用bootstrap方法对性能退化样本进行自助抽样,根据Bayes方法得到模型参数在性能退化数据与无失效数据下的后验分布,用马尔科夫链蒙特卡洛方法(MCMC)方法对参数进行抽样估计,最终实现对航空发动机个体的剩余寿命预测.实验结果表明:该模型能提高剩余寿命预测精度,并为航空公司的计划维修提供依据.Aiming at the problem that the prediction accuracy of engine remaining life was not high because only performance degradation data was used at present,a prediction model of aero-engine individual remaining life was studied,which combined non-failure data with field performance degradation data.In this model,Wiener process with random parameters was used to model aero-engine performance degradation,and bootstrap method was used to self-sample performance degradation samples.According to Bayes method,the posterior distribution of model parameters under performance degradation data and non-failure data was obtained,and the parameters were sampled and estimated by Markov chain Monte Carlo method(MCMC),and finally the remaining life of aero-engine individuals was predicted.The experimental results show that the model can improve the prediction accuracy of remaining life and provide a basis for airlines to plan maintenance.

关 键 词：性能退化数据 无失效数据 剩余寿命 WIENER过程 MCMC方法 

分 类 号：U8[交通运输工程]