超声滚挤压轴承套圈的表层性能预测模型建立及工艺参数优化  被引量:12

Establishment on prediction model of surface performance for ultrasonic roll extrusion bearing ring and optimization on process parameters

在线阅读下载全文

作  者:刘志飞 王晓强[1,2] 朱其萍 王排岗 Liu Zhifei;Wang Xiaoqiang;Zhu Qiping;Wang Paigang(College of Mechanical and Electrical Engineering,Henan University of Science and Technology,Luoyang 471003,China;Collaborative Innovation Center of Advanced Manufacturing of Mechanical Equipment,Luoyang 471003,China)

机构地区:[1]河南科技大学机电工程学院,河南洛阳471003 [2]机械装备先进制造河南省协同创新中心,河南洛阳471003

出  处:《锻压技术》2021年第3期118-125,共8页Forging & Stamping Technology

基  金:国家自然科学基金资助项目(U1804145);国家重点研究专项(2018YFB2000405)。

摘  要:采用超声滚挤压技术对轴承套圈进行表面强化,为了提高其表层性能,实现对工艺参数的优化控制,以轴承套圈材料42CrMo钢为研究对象,通过超声滚挤压正交试验,建立了轴承套圈表层性能与加工参数(主轴转速、进给速度、振幅和静压力)之间的径向基(RBF)神经网络预测模型,并采用方差分析法和田口算法分析了工艺参数对表层性能(表面粗糙度、残余应力和硬度)影响的显著性,获取了表层性能的3组最优工艺参数组合,并利用试验和预测模型对最优参数组合进行了验证。结果表明:最优参数组合比正交试验结果中的最大残余压应力和硬度分别增加了0.59%和4.09%,比正交试验结果中的最小表面粗糙度减小了12.9%。In order to improve the surface performance of bearing ring strengthen by ultrasonic roll extrusion technology and realize the optimal control of process parameters,for bearing ring material of 42CrMo steel,the prediction model of radial basis function(RBF)neural network between surface performance and process parameters(rotation speed,feeding speed,amplitude and static pressure) was established by ultrasonic roll extrusion orthogonal test,and the significant influences of process parameters on the surface performance(surface roughness,residual stress and hardness) were analyzed by variance analysis method and Taguchi algorithm. Then,three sets of optimal combinations for process parameters were obtained,and the optimal combinations of process parameters were verified by experiments and prediction models. The results show that compared the optimal parameter combinations with the orthogonal test results,the maximum residual compressive stress and the hardness increase by 0. 59% and 0. 79% respectively,and the minimum surface roughness decreases by 12. 9%.

关 键 词:超声滚挤压 轴承套圈 正交试验 表层性能 径向基神经网络 方差分析 田口算法 

分 类 号:TG376.1[金属学及工艺—金属压力加工]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象