基于EM-IKF协同算法的滚动轴承剩余寿命预测  

Remaining life prediction of rolling bearings based on an EM-IKF collaborative algorithm

作　　者：李军星 朱文进 邱明[1] 傅惠民[4] LI Junxing;ZHU Wenjin;QIU Ming;FU Huimin(School of Mechatronics Engineering,Henan University of Science and Technology,Luoyang Henan 471003,China;Collaborative Innovation Center of Machinery Equipment Advanced Manufacturing of Henan Province,Henan University of Science and Technology,Luoyang Henan 471003,China;Collaborative Innovation Center of Henan Province for High-End Bearing,Henan University of Science and Technology,Luoyang Henan 471003,China;School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China)

机构地区：[1]河南科技大学机电工程学院,河南洛阳471003 [2]河南科技大学机械装备先进制造河南省协同创新中心,河南洛阳471003 [3]河南科技大学高端轴承河南省协同创新中心,河南洛阳471003 [4]北京航空航天大学航空科学与工程学院,北京100191

出　　处：《航空动力学报》2025年第2期251-258,共8页Journal of Aerospace Power

基　　金：国家自然科学基金(52005159);河南省科技研发计划联合基金青年科学家项目(225200810073);河南省科技研发计划联合基金应用攻关项目(232103810043);河南省高校科技创新人才支持计划资助(24HASTIT043);河南省青年托举人才项目(2023HYTP050);河南省高校青年骨干教师培养计划(2021GGJS048);河南省科技攻关项目(222102220061)。

摘　　要：针对滚动轴承性能退化过程具有平稳和退化两阶段的特点,提出基于EM-IKF(expectation maximization-incremental Kalman filter)协同算法的滚动轴承剩余寿命预测方法。对于平稳阶段,利用西沃兹信息准则(SIC)进行轴承健康状态变点识别,确定轴承的初始退化点;对于退化阶段,建立基于Wiener过程的性能退化表征模型。为了克服传统卡尔曼滤波方法忽略相邻时刻参数的波动性问题,建立基于增量卡尔曼滤波(IKF)算法的状态空间方程;同时为了充分开发利用历史数据和在线监测数据,以便准确确定状态空间方程初始参数,提出基于EM-IKF协同算法的参数自适应更新方法,从而实现轴承剩余寿命自适应在线预测。通过滚动轴承工程实例验证与分析,结果表明:与传统方法相比,本文方法预测精度至少可以提高24.64%。In view of the characteristics reflecting the two-stage performance degradation process of rolling bearings,a remaining life prediction method of rolling bearings was proposed based on an EM-IKF algorithm.In the stationary stage,to determine the initial degradation point of the bearing,the Schwarz information criterion(SIC)was used to identify the change point of bearing health state.In the degradation stage,a performance degradation characterization model was established based on Wiener process.To overcome the problem that the traditional Kalman filtering method ignored the parameter’s volatility between the adjacent times,the state space equation was established based on an incremental Kalman filter(IKF)algorithm.Meanwhile,to fully develop and utilize the historical data and the online monitoring data,and accurately determine the initial parameters of the state-space equation,a parameter adaptive updating method was proposed based on an EM-IKF collaborative algorithm.Then,the adaptive online prediction of bearing remaining life was realized.Finally,the effectiveness of the proposed method was verified and analyzed by an engineering example involving the rolling bearings.The results showed that compared with the traditional method,the prediction accuracy of the proposed method can be improved by at least 24.64%.

关 键 词：滚动轴承 剩余寿命预测 西沃兹信息准则(SIC) 增量卡尔曼滤波(IKF) EM算法 

分 类 号：V229.2[航空宇航科学与技术—飞行器设计] TH133.33[机械工程—机械制造及自动化]