作者：张鹏, 胡昌华, 白灿, 张优, 张建勋

作者单位：火箭军工程大学, 陕西 西安 710025

关键词：两阶段维纳过程;剩余寿命预测;期望最大化算法;贝叶斯方法

摘要：

针对退化过程呈现两阶段特征的随机退化系统剩余寿命预测问题，建立两阶段维纳过程退化模型，并引入随机效应描述样本间差异性。基于时间-空间变化方法以及变点处退化值的随机特性，给出首达时间意义下系统寿命分布解析表达形式。提出一种基于期望最大化（expectation maximization， EM）算法和贝叶斯理论的模型参数离线辨识和在线更新算法。最后，结合液力耦合器（liquid coupling device， LCD）的实际退化数据，验证所提方法的可行性与有效性，并说明其工程应用价值。

Remaining useful life estimation method for two-phase degradation system with random effects
ZHANG Peng, HU Changhua, BAI Can, ZHANG You, ZHANG Jianxun
Rocket Force University of Engineering, Xi'an 710025, China
Abstract: This paper focuses on estimating the remaining useful life for the stochastic degradation system with two-phase degradation process. The two-phase Wiener process degradation model is established, and the random effects is introduced into the degradation model to describe the difference between samples. Based on the time space variation method and the stochastic characteristics of degenerate value at the change point, the analytic expressions of the system lifetime distribution under the concept of the first passage time is provided. The parameters of the model are estimated by the expectation maximization (EM) algorithm, and the obtained estimates are updated by the Bayesian theory. Finally, the life estimation method is applied to the liquid coupling device (LCD), and the result shows the effectiveness of the method and the value of the engineering application.
Keywords: two-phase Wiener process;remaining useful life estimation;EM algorithm;Bayesian theory
2019, 45(1):1-7  收稿日期: 2018-07-17;收到修改稿日期: 2018-08-14
基金项目: 国家自然科学基金（61573365）
作者简介: 张鹏(1994-),男,陕西西安市人,硕士研究生,专业方向为故障诊断与寿命预测
参考文献
[1] SI X S, WANG W, HU C H, et al. Remaining useful life estimation-a review on the statistical data driven approaches[J]. European Journal of Operational Research, 2011, 213(1):1-14
[2] ZHOU R S, SERBAN N, GEBRAEEL N. Degradation-based residual life prediction under different environments[J]. The Annals of Applied Statistics, 2014, 8(3):1671-1689
[3] WANG X, JIANG P, GUO B, et al. Real-time reliability evaluation for an individual product based on change-point gamma and Wiener process[J]. Quality and Reliability Engineering International, 2014, 30(4):513-525
[4] NG T S. An application of the EM algorithm to degradation modeling[J]. IEEE Transactions on Reliability, 2008, 57(1):2-13
[5] YUAN T, BAE S J, ZHU X. A Bayesian approach to degradation-based burn-in optimization for display products exhibiting two-phase degradation patterns[J]. Reliability Engineering & System Safety, 2016, 155(11):55-63
[6] BAE S J, KVAM P H. A change-point analysis for modeling incomplete burn-in for light displays[J]. ⅡE Transactions, 2006, 38(3):489-498
[7] WANG P, TANG Y, BAE S J, et al. Bayesian analysis of two-phase degradation data based on change-point Wiener process[J]. Reliability Engineering & System Safety, 2018, 170(2):244-256
[8] 王前程, 陈云霞, 康锐. 加速度计加速退化机理模型建模方法[J]. 北京航空航天大学学报, 2012, 38(10):1405-1409
[9] BURGESS W L. Valve regulated lead acid battery float service life estimation using a Kalman filter[J]. Journal of Power Sources, 2009, 191(1):16-21
[10] CHEN N, TSUI K L. Condition monitoring and remaining useful life prediction using degradation signals:Revisited[J]. ⅡE Transactions, 2013, 45(9):939-952
[11] YAN W A, SONG B W, DUAN G L, et al. Real-time reliability evaluation of two-phase Wiener degradation process[J]. Communications in Statistics-Theory and Methods, 2017, 46(1):176-188
[12] BAE S J, YUAN T, NING S, et al. A Bayesian approach to modeling two-phase degradation using change-point regression[J]. Reliability Engineering & System Safety, 2015, 134(2):66-74
[13] LEE M, WHITMORE G. Threshold regression for survival analysis:modeling eventtimes by a stochastic process reaching a boundary[J]. Statistical Science, 2006, 21(3):501-513
[14] SI X S, WANG W, CHEN M Y, et al. A degradation path-dependent approach for remaining useful life estimation with an exact and closed-form solution[J]. European Journal of Operational Research, 2013, 226(1):53-66
[15] SI X S, WANG W, HU C H, et al. A Wiener process based degradation model with a recursive filter algorithm for remaining useful life estimation[J]. Mechanical Systems and Signal Processing, 2013, 35(1/2):219-237
[16] ZHANG J X, HU C H, ZHOU D H, et al. A novel lifetime estimation method for two-phase degrading systems[J]. IEEE Transactions on Reliability, 2018(6):1-21