张卫贞,石慧,石冠男,吴斌

• 1:太原科技大学电子信息工程学院

摘要(Abstract)：

考虑到机械系统实际运行中参数随时间不断演化，以及自身监测样本数据不够，同类系统故障样本缺少等，导致剩余寿命预测时模型结构假设和参数估计不够准确的问题，推导建立了时变系统基于KDE的剩余寿命预测模型。与传统数据驱动方法相比，该方法既可避免预测模型假设不够准确的问题，同时也可以动态地预测未来任意时刻的剩余寿命，从而为系统的未来退化趋势提供先期预警，为设备维护维修提供指导。

关键词(KeyWords)： 时变系统;核密度估计;寿命预测;故障诊断

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(61703297);; 山西省青年科学基金(202203021222214);; 山西省高等学校科技创新计划项目(2022L306);; 太原科技大学校博士启动基金(20222044)

作者(Author): 张卫贞,石慧,石冠男,吴斌

参考文献(References)：

• [1] WANG R,ZHU M,ZHANG X,et al.Lithium-ion battery remaining useful life prediction using a two-phase degradation model with a dynamic change point[J].Journal of Energy Storage,2023,59:106457-106459.
• [2] LEI Y,LI N,GUO L,et al.Machinery health prognostics:A systematic review from data acquisition to RUL prediction[J].Mechanical systems and signal processing,2018,104:799-834.
• [3] FERREIRA C,GON?ALVES G.Remaining Useful Life prediction and challenges:A literature review on the use of Machine Learning Methods[J].Journal of Manufacturing Systems,2022,63:550-562.
• [4] CHEN C,LIU Y,WANG S,et al.Predictive maintenance using cox proportional hazard deep learning[J].Advanced Engineering Informatics,2020,44:101054-101058.
• [5] CHENG Y,HU K,WU J,et al.A convolutional neural network based degradation indicator constructionand health prognosis using bidirectional long short-term memory network for rolling bearings[J].Advanced Engineering Informatics,2021,48:101247-101249.
• [6] YAN M,WANG X,WANG B,et al.Bearing remaining useful life prediction using support vector machine andhybrid degradation tracking model[J].ISA Transactions,2019,98:101261-101267.
• [7] LIU Q,CHEN X,DONG M,et al.A novel health prognosis method for system based on improved degenerated Hidden Markov model[J].Robotics and Computer-Integrated Manufacturing,2022,78:102402-102410.
• [8] ZHANG Z,SI X,HU C,et al.Degradation data analysis and remaining useful life estimation:A review on Wiener-process-based methods[J].European Journal of Operational Research,2018,271(3):775-796.
• [9] LIEWALD M,BERGS T,GROCHE P,et al.Perspectives on data-driven models and its potentials in metal forming and blanking technologies[J].Production Engineering,2022,46(8):1-19.
• [10] BIAN L,GEBRAEEL N,KHAROUFEH J P.Degradation modeling for real-time estimation of residual lifetimes in dynamic environments[J].Iie Transactions,2015,47(5):471-486.
• [11] ZHOU Z,LI T,ZHAO Z,et al.Time-varying trajectory modeling via dynamic governing network for remaining useful life prediction[J].Mechanical Systems and Signal Processing,2023,182:109610-109612.
• [12] LONG J,CHEN C,LIU Z,et al.Stochastic hybrid system approach to task-orientated remaining useful life prediction under time-varying operating conditions[J].Reliability Engineering & System Safety,2022,225:108568-108577.
• [13] ZHANG K,YU X,LIU S,et al.Wind power interval predictionbased on hybrid semi-cloud model and nonparametric kernel density estimation[J].Energy Reports,2022,8:1068-1078.
• [14] XU J,LU C,LIU H M.Real-time life prediction for rolling bearings based on nonparametric Bayesian updating method[C]//Applied Mechanics and Materials.Trans Tech Publications Ltd,2015,764:431-436.
• [15] 王洁.恒定加载条件下气缸疲劳破坏预测[D].成都：电子科技大学，2016.
• [16] 张卫贞.基于核密度估计的系统实时剩余寿命预测研究[D].太原：太原科技大学，2021.
• [17] 邱润之.关于 EWMA 模型的参数研究[J].南京邮电学院学报，1989,12(4):102-105.
• [18] 石慧，曾建潮.考虑突变状态检测的齿轮实时剩余寿命预测[J].振动与冲击，2017,36(21):173-184.