In order to predict the remaining useful life (RUL) for a degraded system with partially observed information, the historical lifetime data and performance degradation data are fused together. Firstly, the hidden Markov model (HHM) is used for state evaluation to get the transition probability matrix and observation probability matrix of the system. Secondly, the Bayesian method is used to renew continually the conditional probability distribution of the equipment’s state. Then, a proportional hazards model (PHM) is used for reliability analysis to get the failure rate and reliability functions of the system. The remaining useful life distribution for the equipment is thus obtained. Case study indicates that the method can improve prediction precision effectively, which can help provide logistics personnel with a scientific basis for maintenance decision making.
SHANG Yongshuang
,
LI Wenhai
,
LIU Changjie
,
SHENG Pei
. Prediction of Remaining Useful Life for Equipment with Partially Observed Information[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2012
, (5)
: 848
-854
.
DOI: CNKI:11-1929/V.20120201.0944.010
[1] Banks J, Reichard K, Drake M. System reliability and condition based maintenance. 2008 Reliability and Maintainability Symposium. 2008: 423-428.
[2] Banjevic D, Jardine A K S. Calculation of reliability function and remaining useful life for a Markov failure time process. IMA Journal of Management Mathematics, 2006, 17(2): 115-130.
[3] Yang J, Zhao Y, Li X J, et al. Comprehensive evaluation of mean residual life of complex system. Acta Aeronautica et Astronautica Sinica, 2007, 28(6): 1351-1354. (in Chinese) 杨军, 赵宇, 李学京, 等. 复杂系统平均剩余寿命综合评估方法. 航空学报, 2007, 28(6): 1351-1354.
[4] Hu H F, An M C, Qin G J, et al. Study on fault diagnosis and prognosis methods based on hidden semi-Markov model. Acta Armamentraii, 2009, 3(1): 69-75. (in Chinese) 胡海峰, 安茂春, 秦国军, 等. 基于隐半Markov模型的故障诊断和故障预测方法研究. 兵工学报, 2009, 3(1): 69-75.
[5] Zhang L, Li X S, Yu J S, et al. A fault prognostic algorithm based on Gaussian mixture model particle filter. Acta Aeronautica et Astronautica Sinica, 2009, 30(2): 319-324. (in Chinese) 张磊, 李行善, 于劲松, 等. 一种基于高斯混合模型粒子滤波的故障预测算法. 航空学报, 2009, 30(2): 319-324.
[6] Ghasemi A, Yacout S, Ouali M S. Evaluating the reliability function and the mean residual life for equipment with unobservable states. IEEE Transactions on Reliability, 2010, 59(1): 45-54.
[7] Ma L, Kang J S, Zhao Q. Implementation of equipment residual life prediction framework based on hidden Markov model. Computer Simulation, 2010, 27(5): 88-91. (in Chinese) 马伦, 康建设, 赵强. 基于HMM的设备剩余寿命预测框架及其实现. 计算机仿真, 2010, 27(5): 88-91.
[8] Wang J X. The equipment’s remaining life prediction based on GMDH. Wuhan: Computer Science and Technology College, Wuhan University of Science and Technology, 2010. (in Chinese) 王佳兴. 基于GMDH方法的设备剩余寿命预测. 武汉: 武汉科技大学计算机科学与技术学院, 2010.
[9] Li Z G, Kott G. Predicting remaining useful life based on the failure time data with heavy-tailed behavior and user usage patterns using proportional hazards model. 2010 Ninth International Conference on Machine Learning and Applications. 2010: 623-628.
[10] Ivy J, Pollock S. Marginally monotonic maintenance policies for a multi-state deteriorating machine with probabilistic monitoring and silent failures. IEEE Transactions on Reliability, 2005, 54(3): 489-497.
[11] Grall A, Berenguer C, Dieulle L. A condition-based maintenance policy for stochastically deteriorating systems. Reliability Engineering and System Safety, 2002, 76(2): 167-180.
[12] Lin D, Jardine A. Using principal components in a proportional hazards model with application in condition-based maintenance. Journal of the Operational Research Society, 2006, 57(8): 910-919.
[13] Atlas L, Ostendorf M, Bernard G D. Hidden Markov models for monitoring machining tool-wear. IEEE International Conference on Acoustics, Speech, and Signal Processing. 2000: 3887-3890.
[14] Zeng Q H, Qiu J, Liu G J, et al. Research on equipment degradation state recognition and fault prognostics method based on KPCA-hidden semi-Markov model. Chinese Journal of Scientific Instrument, 2009, 30(7): 1341-1346. (in Chinese) 曾庆虎, 邱静, 刘冠军, 等. 基于KPCA_HSMM设备退化状态识别与故障预测方法研究. 仪器仪表学报, 2009, 30(7): 1341-1346.
[15] Makis V, Jardine A K S. Computation of optimal policies in replacement models. IMA Journal of Management Mathematics, 1991, 3(3): 169-175.
CJA