基于半随机滤波-期望最大化算法的剩余寿命在线预测
收稿日期: 2013-12-30
修回日期: 2014-09-15
网络出版日期: 2014-09-19
基金资助
国家自然科学基金(61174030,61304240,61374126,61473094);中国博士后科学基金(2014M552589)
Real-time residual life prediction based on semi-stochastic filter and expectation maximization algorithm
Received date: 2013-12-30
Revised date: 2014-09-15
Online published: 2014-09-19
Supported by
National Natural Science Foundation of China (61174030, 61304240, 61374126, 61473094); China Postdoctoral Science Foundation (2014M552589)
剩余寿命(RL)预测是设备预测维护的关键环节。准确在线预测能够为维护策略的实时安排提供更加精确的技术支持,有效避免失效的发生。工程实际中,反映设备退化过程的性能指标往往不能直接监测,为解决隐含退化过程的剩余寿命在线预测问题,提出一种基于半随机滤波-期望最大化(EM)算法的预测方法。首先以剩余寿命为隐含状态,构建状态空间模型描述直接监测数据与设备剩余寿命间的随机关系。为实现单个设备剩余寿命的在线预测,依据到当前时刻为止的监测数据,采用扩展卡尔曼滤波(EKF)与期望最大化算法相互协作的方法实时估计与更新模型未知参数和剩余寿命分布。最后,将该方法用于惯性测量组合(IMU)剩余寿命在线预测问题,实验结果表明该方法能够提高预测的准确性并减少预测的不确定性。
冯磊 , 王宏力 , 司小胜 , 杨晓君 , 王标标 . 基于半随机滤波-期望最大化算法的剩余寿命在线预测[J]. 航空学报, 2015 , 36(2) : 555 -563 . DOI: 10.7527/S1000-6893.2014.0257
The prediction of residual life (RL) is the key of the predictive maintenance for engineering equipment. Accurate and real-time prediction can provide more effective decision support to the subsequent maintenance schedule and avoid the failure effectively. In engineering practice, the performance index reflecting the degradation process of the equipment is generally not observed directly. To tackle the residual life problem under hidden degradation, a prediction method based on semi-stochastic and expectation maximization (EM) algorithm is proposed in this paper. First, the residual life is taken as the hidden state and the prediction model is constructed by building the stochastic relationship between the residual life and monitoring data. Secondly, based on the monitoring data up to the current time, a collaborative method by the extended Kalman filter (EKF) and expectation maximization algorithm is presented to achieve a real-time estimation and updating of the residual life distribution and unknown model parameters. Finally, the proposed method is validated by the application to the inertial measurement unit (IMU) and the results indicate that the method can improve the accuracy and reduce the uncertainty of the estimated residual life.
[1] Si X S, Wang W B, Hu C H, et al. Remaining useful life estimation—a review on the statistical data driven approaches[J]. Europen Journal of Operational Research, 2011, 213(1): 1-14.
[2] Zio E, Peloni G. Praticle filtering prognostic estimation of the remaining useful life of nonlinear components[J]. Reliability Engineering and System Safety, 2011, 96(3): 403-409.
[3] Ghasemi A, Yacout S, Ouali M S. Evaluating the reliability function and the mean residual life for equipment with unobservable states[J]. IEEE Transactions on Reliability, 2010, 59(1): 45-54.
[4] 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.
[5] Wang W B, Christer A H. Towards a general condition based maintenance model for a stochastic dynamic system[J]. Journal of the Operational Research Society, 2000, 51(2): 145-155.
[6] Wang W B. A prognosis model for wear prediction based on oil-based monitoring[J]. Journal of the Operational Research Society, 2006, 58(7): 887-893.
[7] Wang W B, Zhang W. An asset residual life prediction model based on expert judgments[J]. Europen Journal of Operational Research, 2008, 188(2): 496-505.
[8] Wang W B, Hussin B. Plant residual time modelling based on observed variables in oil samples[J]. Journal of the Operational Research Society, 2009, 60(6): 789-796.
[9] Carr M, Wang W B. Modeling failure modes for residual life prediction using stochastic filtering theory[J]. IEEE Transactions on Reliability, 2010, 59(2): 346-355.
[10] Carr M, Wang W B. An approximate algorithm for prognostic modeling using condition monitoring information[J]. Europen Journal of Operational Research, 2011, 211(1): 90-96.
[11] Wang W B. 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.
[12] Wang Z X. Optimal state estimation and system identification[M]. Xi'an: Northwestern Polytechnical University Press, 2004: 137-141 (in Chinese). 王志贤. 最优状态估计与系统辨识[M]. 西安: 西北工业大学出版社, 2004: 137-141.
[13] Zhou Z J, Hu C H, Yang J B, et al. Online updating belief-rule-based systems using the RIMER approach[J]. IEEE Transactions on Systems, Man and Cybernetics—Part A: Systems and Humans, 2011, 41(6): 1225-1243.
[14] Hu L, Zhou J X, Shi Z G, et al. An EM-based approach for compressed sensing using dynamic dictionaries[J]. Journal of Electronics & Information Technology, 2012, 34(11): 2554-2560 (in Chinese). 胡磊, 周剑雄, 石志广, 等. 利用期望-最大化算法实现基于动态词典的压缩感知[J]. 电子与信息学报, 2012, 34(11): 2554-2560.
[15] Borkar V, Ghosh M, Rangarajan G. Application of nonlinear filtering to credit risk[J]. Operations Research Letters, 2010, 38(6): 527-532.
[16] Hu C H, Ma Q L, Zheng J F. The control technique of missile testing and launching[M]. Beijing: National Defence Industry Press, 2010: 62-74 (in Chinese). 胡昌华, 马清亮, 郑建飞. 导弹测试与发射控制技术[M]. 北京: 国防工业出版社, 2010: 62-74.
[17] Si X S, Wang W B, Hu C H, et al. Remaining useful life estimation based on a nonlinear diffusion degradation process[J]. IEEE Transactions on Reliability, 2012, 61(1): 50-67.
[18] Hu C H, Si X S. Real-time parameters estimation of belief rule base health condition for inertial platform[J]. Acta Aeronautica et Astronautica Sinica, 2010, 31(7): 1454-1465 (in Chinese). 胡昌华, 司小胜. 基于信度规则库的惯性平台健康状态参数在线估计[J]. 航空学报, 2010, 31(7): 1454-1465.
[19] Akaike H. A new lool at the statistical model identification[J]. IEEE Transactions on Automatic Control, 1974, 19(6): 716-722.
[20] Zhang B C, Han X X, Zhou Z J, et al. Construction of a new BRB based for time series forecasting[J]. Applied Soft Computing, 2013, 13(12): 4548-4556.
[21] Feng L, Wang H L, Si X S, et al. A state space based prognostic model for hidden and age-dependent nonlinear degradation process[J]. IEEE Transactions on Automation Science and Engineering, 2013, 10(4): 1072-1086.
/
| 〈 |
|
〉 |
CJA