Self-adaptive Health Condition Prediction Considering Dynamic Transfer of Degradation Mode
-
摘要: 为了更加精确地在设备退化过程中对其健康状态进行预测,本文深入研究了设备处于不同健康状态时的数据特点,针对现有单一预测方法的特点与不足,引入了退化模式的划分方法,并对不同的预测模型与退化模式的关系进行分析. 进而建立“模式-模型”关联表,并通过关联表优选预测模型,实现了考虑退化模式动态转移的健康状态自适应预测以及剩余寿命估计.最后,以滚动轴承实验为实例,对该轴承进行了健康状态预测与剩余寿命估计.实验结果表明本方法较精确地预测了轴承的剩余寿命,证明了方法的有效性.Abstract: This paper investigates the data characteristics of engineering equipment under different health conditions in order to realize more accurate health state prediction during its degradation process. An approach to classify the degradation modes is introduced to overcome the shortcomings of the single-prediction-method existing in current applications. Based on an analysis on the relationship between different prediction models and degradation modes, an association table "Mode-Model" is established, thereby the self-adaptive health condition prediction and residual life estimation can be achieved by optimal selection of prediction models, which considers the dynamic transfer of degradation mode. Finally, the efficiency of the proposed method is verified by a rolling bearing experiment.
-
[1] Guo Tao-Hong. Discussion on equipment repair system. Railway Freight Transport, 2000, (5): 31-33 (郭韬红. 设备维修制度的探讨. 铁路货运, 2000, (5): 31-33) [2] Sun Bo, Kang Rui, Xie Jin-Song. Research and application of the prognostic and health management system. Systems Engineering and Electronics, 2007, 29(10): 1762-1767 (孙博, 康锐, 谢劲松. 故障预测与健康管理系统研究和应用现状综述. 系统工程与电子技术, 2007, 29(10): 1762-1767) [3] Si Xiao-Sheng, Hu Chang-Hua, Zhou Dong-Hua. Nonlinear degradation process modeling and remaining useful life estimation subject to measurement error. Acta Automatica Sinca, 2013, 39(5): 530-541(司小胜, 胡昌华, 周东华. 带测量误差的非线性退化过程建模与剩余寿命估计. 自动化学报, 2013, 39(5): 530-541) [4] Wu Ming-Qiang, Fang Hong-Zheng, Yi Da-Wei. Fault prognostic approach and application technique research of complex system. Computer Measurement & Control, 2010, 18(1): 70-77 (吴明强, 房红征, 伊大伟. 复杂系统故障预测方法与应用技术研究. 计算机测量与控制, 2010, 18(1): 70-77) [5] Hu You-Tao, Hu Chang-Hua, Kong Xiang-Yu, Zhou Zhi-Jie. Real-time lifetime prediction method based on wavelet support vector regression and fuzzy c-means clustering. Acta Automatica Sinca, 2012, 38(3): 331-340 (胡友涛, 胡昌华, 孔祥玉, 周志杰. 基于WSVR和FCM聚类的实时寿命预测方法. 自动化学报, 2012, 38(3): 331-340) [6] Li Y, Billington S, Zhang C, Kurfess T, Danyluk S, Liang S. Adaptive prognostics for rolling element bearing condition. Mechanical Systems and Signal Processing, 1999, 3(1): 103-113 [7] Li Y, Kurfess T R, Liang S Y. Stochastic prognostics for rolling element bearings. Mechanical Systems and Signal Processing, 2000, 4(5): 747-762 [8] Zhou Dong-Hua, Liu Yang, He Xiao. Review on fault diagnosis techniques for closed-loop systems. Acta Automatica Sinca, 2011, 15(8): 1933-1943 (周东华, 刘洋, 何潇. 闭环系统故障诊断技术综述. 自动化学报, 2013, 39(11): 1933-1943) [9] Jiang Yuan-Yuan, Wang You-Ren, Cui Jiang, Sun Feng-Yan. Research on fault prediction method of power electronic circuits based on least squares support vector machine. Electric Machines and Control, 2011, 15(8): 64-68, 74(姜媛媛, 王友仁, 崔江, 孙凤艳. 基于LS-SVM的电力电子电路故障预测方法. 电机与控制学报, 2011, 15(8): 64-68, 74) [10] Bossaerts P, Hillion P. Implementing statistical criteria to select return forecasting models: What do we learn? Review of Financial Studies, 1999, 12(2): 405-428 [11] Wang W. An adaptive predictor for dynamic system forecasting. Mechanical Systems and Signal Processing, 2007, 21(2): 809-823 [12] Wang, P, Vachtsevanos G. Fault prognostics using dynamic wavelet neural networks. AIEDAM, 2001, 5(4): 349-365 [13] Djurdjanovic D, Lee J, Ni J. Watchdog agent —— an infotronics-based prognostics approach for product performance degradation assessment and prediction. Advanced Engineering Informatics, 2003, 7(3-4): 109-125 [14] Wang W B. A two-stage prognosis model in condition based maintenance. European Journal of Operational Research, 2007, 82(3): 1177-1187 [15] LeBaron B, Weigend A S. A bootstrap evaluation of the effect of data splitting on financial time series. IEEE Transactions on Neural Networks, 1998, 9(1): 213-220 [16] Armano G, Marchesi M, Murru A. A hybrid genetic-neural architecture for stock indexes forecasting. Information Sciences, 2005, 70(1): 3-33 [17] Erdem E, Shi J. ARMA based approaches for forecasting the tuple of wind speed and direction. Applied Energy, 2011, 88(4): 1405-1414 [18] Elman J L. Finding structure in time. Cognitive Science, 1990, 4(2): 179-211
点击查看大图
计量
- 文章访问数: 1825
- HTML全文浏览量: 119
- PDF下载量: 1397
- 被引次数: 0