基于BA-WPHM的滚动轴承两阶段剩余寿命预测方法

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。

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

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.