Real-time remaining useful life prediction based on relative density kernel estimation

PDF(2075 KB)

Journal of Vibration and Shock ›› 2022, Vol. 41 ›› Issue (22) : 308-318.

ZHANG Jiangmin, SHI Hui, DONG Zengshou

Author information +

History +

Abstract

To evaluate the real-time residual life of the system more accurately, a modeling method of real-time residual life prediction based on adaptive relative density kernel estimation was proposed. Firstly, the residual life prediction model of nonparametric kernel density estimation was established, and the idea of sample point k-nearest neighbor was introduced to calculate the relative density of sample points for adaptive window width selection to improve the accuracy and rationality of window width selection in sparse and dense regions. Secondly, the relative density kernel differential homomorphic transformation method is established based on the space mapping method to solve the boundary shift problem of kernel estimation in the prediction, so as to improve the prediction accuracy. With the real-time change of monitoring data, the kernel density estimates of the known samples are updated recursively to obtain the kernel density estimates of the new samples. Finally, an example is given to verify the validity and accuracy of the proposed method.
Keywords：relative density; kernel density estimation; differential homeomorphism; residual life prediction

Key words

relative density / kernel density estimation / differential homeomorphism / residual life prediction

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

ZHANG Jiangmin, SHI Hui, DONG Zengshou. Real-time remaining useful life prediction based on relative density kernel estimation[J]. Journal of Vibration and Shock, 2022, 41(22): 308-318

References

[1]周东华,魏慕恒,司小胜.工业过程异常检测、寿命预测与维修决策的研究进展[J].自动化学报,2013,39(06):711-722.
Zhou Donghua, Wei Muheng, Si Xiaosheng.Progress in anomaly detection, life prediction and maintenance decision of industrial process [J]. Acta Automatica Sinica,2013,39(06):711-722.
[2] 裴洪,胡昌华,司小胜等.基于机器学习的设备剩余寿命预测方法综述[J].机械工程学报,2019,55(08):1-13.
Pei Hong, Hu Changhua, Si Xiaosheng et al.Review of Remaining Life Prediction Methods for Equipment Based on Machine Learning [J]. Journal of Mechanical Engineering,2019,55(08):1-13.
[3] 胡昌华,施权,司小胜等.数据驱动的寿命预测和健康管理技术研究进展[J].信息与控制,2017,46(01):72-82.
HU C H, SHI Q, SI X S, et al. Research progress of data-driven life expectancy prediction and health management technology [J].Information and Control,2017,46(01):72-82.
[4] 喻勇,司小胜,胡昌华等.数据驱动的可靠性评估与寿命预测研究进展:基于协变量的方法[J].自动化学报,2018,44(02):216-227.
Yu Yong, Si Xiaosheng, Hu Changhua et al.Research Progress of Data-Driven Reliability Assessment and Life Prediction: A Covariable-Based Approach [J].Acta Automatica Sinica,2018,44(02):216-227.
[5] 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.
[6] Caio B S M , Marcio D C M , Didier Lins I , et al. Remaining Useful Life Estimation by Empirical Mode Decomposition and Support Vector Machine[J]. IEEE Latin America Transactions, 2016, 14(11):4603-4610.
[7] Zhai Q , Ye Z S . RUL Prediction of Deteriorating Products Using an Adaptive Wiener Process Model[J]. IEEE Transactions on Industrial Informatics, 2017, PP(6):1-1.
[8] 刘文溢,刘勤明,周林森.基于高阶隐半马尔科夫模型的设备剩余寿命预测[J/OL].计算机集成制造系统:1-22[2021-03-16].
Liu Wenyi, Liu Qinming, Zhou Linsen.Equipment based on high order half hidden markov model residual life prediction [J/OL]. Computer integrated manufacturing system: 1-22 [2021-03-16].
[9] Zhang J , Wang P , Yan R , et al. Long short-term memory for machine remaining life prediction[J]. Journal of Manufacturing Systems, 2018, 48:78-86.
[10] Xiang Li,Qian Ding,Jian-Qiao Sun. Remaining useful life estimation in prognostics using deep convolution neural networks[J]. Reliability Engineering and System Safety,2018,172.
[11] Chen Longting,Xu Guanghua,Zhang Sicong,Yan Wenqiang,Wu Qingqiang. Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks[J]. Journal of Manufacturing Systems,2020,54(C).
[12] Liang Guo,Naipeng Li,Feng Jia,Yaguo Lei,Jing Lin. A recurrent neural network based health indicator for remaining useful life prediction of bearings[J]. Neurocomputing,2017.
[13] 张继冬,邹益胜,蒋雨良等.基于全卷积变分自编码网络FCVAE的轴承剩余寿命预测方法[J].振动与冲击,2020,39(19):13-18+25.
Zhang Jidong, Zou Yisheng, Jiang Yuliang et al.Prediction method of residual life of bearing based on FCVAE total convolution variational autocoding network [J].Journal of Vibration and Shock,2020,39(19):13-18+25.
[14] 张卫贞,曾建潮,石慧等.基于核密度估计的实时剩余寿命预测[J].计算机集成制造系统,2020,26(07):1794-1801.
Zhang Weizhen, Zeng Jianchao, Shi Hui, et al.Real-time residual life prediction based on kernel density estimation [J]. Computer Integrated Manufacturing Systems,2020,26(07):1794-1801.
[15] Bo H U , Yudun L I , Yang H , et al. Wind speed model based on kernel density estimation and its application in reliability assessment of generating systems[J]. Journal of Modern Power Systems and Clean Energy, 2016.
[16] I.B. Sidibé,A. Khatab,C. Diallo,K.H. Adjallah. Kernel estimator of maintenance optimization model for a stochastically degrading system under different operating environments[J]. Reliability Engineering and System Safety,2016,147
[17] 杨楠,周峥,陈道君等.基于非参数核密度估计的风功率波动性概率密度建模方法[J].太阳能学报,2019,40(07):2028-2035.
Yang Nan, Zhou Zheng, Chen Daojun, et al.Modeling method of wind power fluctuation probability density based on nonparametric kernel density estimation [J]. Acta Energica Sinica,2019,40(07):2028-2035.
[18] 李存华,孙志挥,陈耿等.核密度估计及其在聚类算法构造中的应用[J].计算机研究与发展,2004(10):1712-1719.
LI Cunhua,SUN Zhihui,CHEN Geng,et al.Kernel density estimation and its application to clustering algorithm construction[J].Journal of Computer Research and Development,2004, 41(10):1712-1719.
[19] 赵渊,张夏菲,周家启.电网可靠性评估的非参数多变量核密度估计负荷模型研究[J].中国电机工程学报,2009,29(31):27-33.
Zhao Yuan, Zhang Xiafei, Zhou Jiaqi.Research on Load Model of Non-parametric Multivariable Kernel Density Estimation for Power Grid Reliability Assessment [J]. Proceedings of the Csee,2009,29(31):27-33.
[20] 颜伟,任洲洋,赵霞等.光伏电源输出功率的非参数核密度估计模型[J].电力系统自动化,2013,37(10):35-40.
YAN Wei, REN Zhouyang, ZHAO Xia, et al.Nonparametric Kernel Density Estimation Model for Photovoltaic Power Output [J]. Automation of Electric Power Systems,2013,37(10):35-40.
[21] Silverman Bernard. W.. Density Estimation for Statistics and Data Analysis[M].CRC Press:2018-02-19.
[22] Saoudi S , Ghorbel F , Hillion A . Some Statistical properties of the kernel-diffeomorphism estimator[J]. Applied Stochastic Models in Business & Industry, 2010, 13(1):39-58.
[23] Jones M.C.,Sheather S.J. Using non-stochastic terms to advantage in kernel-based estimation of integrated squared density derivatives[J]. Statistics & Probability Letters,1991,11(6).
[24] 周世波,徐维祥.一种基于相对密度和决策图的聚类算法[J].控制与决策,2018,33(11):1921-1930.
Zhou Shibo, Xu Weixiang.A Clustering Algorithm Based on Relative Density and Decision Graph [J]. Control and Decision,2018,33(11):1921-1930.
[25] Breunig M M , Kriegel H P , Ng R T , et al. LOF: Identifying Density-Based Local Outliers[C]// Acm Sigmod International Conference on Management of Data. ACM, 2000.
[26] Malec P, Schienle M. Nonparametric Kernel Density Estimation Near the Boundary[J]. Computational Statistics & Data Analysis, 2014, 72(C):57-76.