利用软计算技术改善圆锥滚子轴承的工作性能  

Using soft computing technology to improve performance of tapered roller bearing

作　　者：卢彦群[1] 侯建伟 Lu Yanqun;Hou Jianwei(Engineering University of Hebei,Handan 056038,China)

机构地区：[1]河北工程大学,河北邯郸057000

出　　处：《哈尔滨轴承》2021年第2期3-14,共12页Journal of Harbin Bearing

基　　金：河北省科技厅重点项目-大智移云应用专项-圆锥滚子轴承双层复合智能化生产线研发:18211832D;河北省教育厅重点项目-面向新工科基于TRIZ的大学生创新能力培养模式研究:2019GJJG250.

摘　　要：双列圆锥滚子轴承主要用于支承具有预紧力的组合式负载,以确保合理的运行状态。因为轴承滚道会出现高接触应力、疲劳剥落或表面点蚀,所以,开发一种工具,以期提前了解预设载荷是否会引发故障,就显得非常重要。为此提出一种基于四类荷载表达值的工况分类方法,首先建立了一种三维有限元(FE:Finite Element)模型;其次,设计了一个实验程序,在降低基于有限元模型的模拟计算成本的同时,提供最大的信息量;随后,将四种载荷条件分别进行实验,用统计分析和机器学习技术创建分类模型,再采用特征变换和约简、算法参数调整以及验证等方法,完成了鲁棒分类模型;最后,在柔性判别与分析的基础上,得到了最佳结果。该方法和最终模型都得到了验证,其准确性也得到公认。Double row-TRB is a mechanical device used to support a combined load with the best preloading force to ensure reasonable operation state.Because of the high contact stress,fatigue spalling,or surface pitting of the raceway,it is important to develop a tool to understand in advance whether a preset load will cause failure.For this purpose,a method of working condition classification based on the expressed values of four kinds of loads is proposed.Firstly,a three-dimensional finite element(FE)model is established;Secondly,an experimental program is designed to reduce the cost of simulation based on finite element model,and at the same time to provide the maximum amount of information;Thirdly,each experiment was carried out under four loading conditions,and the classification model was created by statistical analysis and machine learning techniques;Then,the robust classification model was completed by using the methods of feature transformation and reduction,algorithm parameter adjustment and verification;Finally,the optimal results are obtained on the basis of the discrimination and analysis of flexibility.Both the method and the final model have been verified,and its accuracy has been recognized.

关 键 词：双列圆锥滚子轴承 数据挖掘与分类 有限元 实验设计 模型参数整定与评价 

分 类 号：TH133.332[机械工程—机械制造及自动化] TH164