基于BA-WPHM的滚动轴承两阶段剩余寿命预测方法  

Two-stage remaining useful life prediction of rolling bearings based on BA-WPHM

作　　者：王英[1] 顾欣 吕文元[2] Wang Ying;Gu Xin;Lyu Wenyuan(College of Engineering,Northeast Agricultural University,Harbin 150030,China;School of Management,Harbin Institute of Techno-logy,Harbin 150001,China)

机构地区：[1]东北农业大学工程学院,哈尔滨150030 [2]哈尔滨工业大学经济与管理学院,哈尔滨150001

出　　处：《计算机应用研究》2022年第1期96-101,共6页Application Research of Computers

基　　金：十三五科技部国家重点研发计划资助项目(2018YFD0300105);黑龙江省博士后科研启动基金资助项目(LBH-Q13021)。

摘　　要：为了提高滚动轴承剩余寿命预测的准确性,根据滚动轴承运行过程的两阶段性特点,提出了一种基于蝙蝠算法(BA)和威布尔比例风险模型(WPHM)的滚动轴承两阶段剩余寿命预测方法。首先,构建基于WPHM的剩余寿命预测模型;其次,提出了两阶段极大似然估计法,建立新的似然函数,并利用BA算法进行求解,以提高参数估计的准确性;最后,建立BA-WPHM模型对滚动轴承进行剩余寿命预测。案例分析表明,相比于Newton-Raphson算法、自组织分层猴群算法(SHMA)和独特的自适应粒子群算法(UAPSO),提出的方法参数估计的准确性更高,剩余寿命的预测精度优于支持向量回归(SVR)方法,验证了所提方法的有效性,为滚动轴承维修决策的可行性提供了依据。To improve the accuracy of remaining useful life prediction for rolling bearings,based on the two-stage characteristics of rolling bearings operation,this paper proposed a two-stage remaining useful life prediction method based on bat algorithm(BA)and Weibull proportional hazards model(WPHM).Firstly,it constructed a remaining useful life prediction model based on WPHM.Secondly,it put forward the two-stage maximum likelihood estimation method to establish the new likelihood function,and adopted BA to solve it.Finally,it established the BA-WPHM model for rolling bearings remaining useful life prediction.The case analysis shows that the parameters estimation accuracy of the proposed method is superior to that of Newton-Raphson,self-organizing hierarchical monkey algorithm(SHMA),unique adaptive particle swarm optimization(UAPSO),and the prediction accuracy of BA-WPHM is better than that of support vector regression(SVR)method.The results verify the effectiveness of the proposed method,which can provide a basis for the feasibility of rolling bearing maintenance decision-making.

关 键 词：滚动轴承 剩余寿命预测 威布尔比例风险模型 两阶段极大似然估计法 蝙蝠算法 

分 类 号：TH133.33[机械工程—机械制造及自动化] TP391[自动化与计算机技术—计算机应用技术]