多退化变量下基于Copula函数的陀螺仪剩余寿命预测方法
收稿日期: 2013-07-22
修回日期: 2013-09-13
网络出版日期: 2013-09-29
基金资助
国家杰出青年基金（61025014）；国家自然科学基金（61174030，61206007，61174030，61374126）
Multiple Degradation Variables Modeling for Remaining Useful Life Estimation of Gyros Based on Copula Function
Received date: 2013-07-22
Revised date: 2013-09-13
Online published: 2013-09-29
Supported by
National Science Fund for Distinguished Young Scholars (61025014); National Natural Science Foundation of China (61174030, 61206007, 61174030, 61374126)
针对惯性导航系统中陀螺仪多退化变量条件下的剩余寿命（RUL）预测问题，提出了一种基于Copula函数的多退化变量剩余寿命预测方法。首先，针对退化变量间不同的退化轨迹，采用不同的方法进行退化建模，并对于陀螺漂移系数样本标准差数据波动性随时间递增的特性，提出了一种方差时变的正态随机过程退化建模方法，得到了陀螺仪剩余寿命的边缘分布函数。然后，通过Copula函数来描述退化变量之间的相关性，将得到的剩余寿命的边缘分布进行融合，得到了陀螺仪剩余寿命的联合分布函数。最后，通过陀螺仪实例分析验证了方法的适用性和可行性。
张建勋 , 胡昌华 , 周志杰 , 司小胜 , 杜党波 . 多退化变量下基于Copula函数的陀螺仪剩余寿命预测方法[J]. 航空学报, 2014 , 35(4) : 1111 -1121 . DOI: 10.7527/S1000-6893.2013.0391
This paper proposes a model for the remaining useful life (RUL) estimation of gyros with multiple degradation variables based on the Copula function. Frist, because the different degradation variables may have different degradation paths, different models are adopted to obtain a marginal distribution of the RUL. And since the fluctuations of some degradation data increase over time, a normal stochastic process whose variance is the function of time is adopted for describing the degradation process. Then, a RUL joint distribution combining these marginal distributions is obtained based on the characteristics of the Copula function. Finally, the degradation data of gyro drift from a practical experiment are used to illustrate the feasibility and applicability of our model.
[1] Vichare N M, Pecht M G. Prognostics and health management of electronics[J].IEEE Transactions on Components and Packaging Technologies, 2006, 29(1): 222-229.
[2] Shang Y S, Li W H, Liu C J, et al. Prediction of remaining useful life for equipment with partially observed information[J]. Acta Aeronautica et Astronautica Sinica, 2012, 33(5): 848-854. (in Chinese) 尚永爽, 李文海, 刘长捷, 等. 部分可观测信息条件下装备剩余寿命预测[J]. 航空学报, 2012, 33(5): 848-854.
[3] Si X S, Wang W B, 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.
[4] Camci F, Chinnam R B. Health-state estimation and prognostics in machining processes[J]. IEEE Transactions on Automation Science and Engineering, 2010, 7(3): 581-597.
[5] Carr M J, Wang W B. Modeling failure modes for residual life prediction using stochastic filtering theory[J]. IEEE Transactions on Reliability, 2010, 59(2): 346-355.
[6] Peng Y, Dong M. A prognosis method using age-dependent hidden semi-Markov model for equipment health prediction[J]. Mechanical Systems and Signal Processing, 2011, 25(1): 237-252.
[7] Sklar M. Fonctions de répartition à n dimensions et leurs marges[J]. Publications de l'Institut de Statistique de L'Université de Paris, 1959, 8: 229-231. (in France)
[8] Si X S, Wang W B, 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, 2012, 226(1): 53-66.
[9] Huang Z, Li S J, Guo B. General reliability life data fit method based on mixture of gamma distributions[J]. Acta Aeronautica et Astronautica Sinica, 2008, 29(2): 379-386. (in Chinese) 黄卓, 李苏军, 郭波. 基于混合 Gamma 分布的通用可靠性寿命数据拟合方法[J]. 航空学报, 2008, 29(2): 379-386.
[10] Sikorska J Z, Hodkiewicz M, Ma L. Prognostic modelling options for remaining useful life estimation by industry[J]. Mechanical Systems and Signal Processing, 2011, 25(5): 1803-1836.
[11] Si X S, Wang W B, 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, 2012, 35(1-2): 219-237.
[12] Zhou X. An EM algorithm based maximum likelihood parameter estimation method for the G0 distribution[J]. Acta Electronica Sinica, 2013, 41(1): 178-184. (in Chinese) 周鑫. 基于EM算法的G0分布参数最大似然估计[J]. 电子学报, 2013, 41(1): 178-184.
[13] Gibson S, Wills A, Ninness B. Maximum-likelihood parameter estimation of bilinear systems[J]. IEEE Transactions on Automatic Control, 2005, 50(10): 1581-1596.
[14] Zhang B Q, Chen G P, Guo Q T. Solution of model validation thermal challenge problem using a Bayesian method[J]. Acta Aeronautica et Astronautica Sinica, 2011, 32(7): 1202-1209. (in Chinese) 张保强, 陈国平, 郭勤涛. 模型确认热传导挑战问题求解的贝叶斯方法[J]. 航空学报, 2011, 32(7): 1202-1209.
[15] Wu C F J. On the convergence properties of the EM algorithm[J]. The Annals of Statistics, 1983, 11(1): 95-103.
[16] Nelson R B. An introduction to Copulas[M]. New York: Springer, 2006: 9-11.
[17] Fermanian J D. Goodness-of-fit tests for copulas[J]. Journal of Multivariate Analysis, 2005, 95(1): 119-152.
[18] Elwany A, Gebraeel N. Real-time estimation of mean remaining life using sensor-based degradation models[J]. Journal of Manufacturing Science and Engineering, 2009, 131(5): 051005.
[19] Gebraeel N Z, Lawley M A, Li R, et al. Residual-life distributions from component degradation signals: a Bayesian approach[J]. ⅡE Transactions, 2005, 37(6): 543-557.
[20] Wang W B. A two-stage prognosis model in condition based maintenance[J]. European Journal of Operational Research, 2007, 182(3): 1177-1187.
/
| 〈 |
|
〉 |
CJA