高速铣削TC4表面粗糙度预测模型研究  

Research on Surface Roughness Prediction Model for High-Speed Milling TC4

作　　者：张宝磊[1] 熊艺文[1] 王为庆[2] 朱帅玲[2] 

机构地区：[1]桂林航天工业学院建筑环境与能源工程系,广西桂林541004 [2]桂林航天工业学院机械工程系,广西桂林541004

出　　处：《组合机床与自动化加工技术》2015年第3期108-110,共3页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：桂林航天工业学院院级基金项目(YJ1307)

摘　　要：零件表面粗糙度的影响因素具有复杂性和不确定性,切削参数是能够人为控制并对零件的表面质量有较大影响的因素之一。为了优选合适的切削参数以达到提高零件表面加工质量的目的,通过设计正交试验并在此基础上建立了钛合金TC4高速铣削表面粗糙度的GRNN广义回归神经网络预测模型和经验回归模型,对其预测误差进行了比较分析。结果表明:所建立的GRNN预测模型较回归预测模型有更高的预测精度,能够更好的对表面粗糙度进行动态控制。The factors influencing the workpiece surface roughness is complexity and uncertainty,the cutting parameters are one factor of ones that have great influences on machined surface quality which can be controlled artificially. In order to choose appropriate cutting parameters to get better machined surface quality,the paper design orthogonal experimental and establish TC4 Empirical regression prediction model and generalized regression neural networks（ GRNN） for prediction of surface roughness when high speed milling TC4 and compare the predicting error. Results showthat the established GRNN prediction mode has better prediction precision which can be used to control the surface roughness dynamically.

关 键 词：GRNN 预测 粗糙度 TC4 

分 类 号：TH16[机械工程—机械制造及自动化] TG506[金属学及工艺—金属切削加工及机床]