摘要
为了准确预测滚动轴承剩余使用寿命,采用模糊综合评价法解决轴承退化状态难以划分的问题,并借助支持向量机在小样本数据分析方面具有的良好能力,以及差分进化方法高效的并行搜索信息的方式,提出了一种基于支持向量回归和差分进化算法混合的滚动轴承剩余寿命预测模型,该模型采用差分进化算法获得支持向量回归模型的最优参数,结合试验平台采集的加速寿命试验数据。实验结果表明:模糊综合评判方法可以较好地划分轴承退化状态,有利于预测不同退化状态下的剩余寿命。
In order to predict the remaining service life of the rolling bearings,this article uses the fuzzy comprehensive evaluation method solve the problem of bearing degradation state is difficult to divide,with the analysis of support vector machine(SVM)in the small sample data,has a good ability,as well as the method of differential evolution and efficient parallel search information,this paper proposes a hybrid based on support vector regression with differential evolution algorithm is rolling bearing of the residual life prediction model,the model adopts the differential evolution algorithm to obtain the optimal parameters of support vector regression model,combining with the experiment platform of accelerated life test data.The experimental results show that the fuzzy comprehensive evaluation method can better classify the degradation state of the bearing and is helpful to predict the residual life under different degradation state.
作者
隋文涛
张丹
金亚军
邱晓梅
SUI Wen-tao;ZHANG Dan;JIN Ya-jun;Qiu Xiao-mei(School of Mechanical Engineering,Shandong University of Technology,Shandong Zibo 255000,China;School of Electrical and Electronic Engineering,Shandong University of Technology,Shandong Zibo 255000,China)
出处
《机械设计与制造》
北大核心
2022年第12期301-304,共4页
Machinery Design & Manufacture
基金
山东省自然科学基金(ZR2016EEM20)。
关键词
滚动轴承
模糊综合评价法
支持向量机
差分进化算法
退化状态划分
Rolling Bearing
Fuzzy Comprehensive Evaluation Method
Support Vector Machine
Differential Evolution Algorithm
Degenerate State Division
