微铣削表面粗糙度预测模型的研究.pdfVIP

中国科技论文在线 微铣削表面粗糙度预测模型的研究# 王鑫鑫，卢晓红，贾振元，贾旭，李光俊，武文毅** （大连理工大学机械工程学院，辽宁 大连 116024） 5 摘要：微铣削表面粗糙度是衡量加工过程的一个重要性能指标，建立预测精度较高的微铣削 表面粗糙度预测模型，准确地预测和控制零件微铣削加工后的表面粗糙度，对于合理选择工 艺参数指导零件的实际加工意义重大。本文结合目前微铣削表面粗糙度预测模型的研究现 状，针对黄铜件分别采用响应曲面法（RSM ）和支持向量机（SVM ）回归建立关于刀具悬 伸量、主轴转速、每齿进给量、轴向切深四个切削参数的微铣削表面粗糙度预测模型，并通 10 过微铣削加工试验对两种方法建立的预测模型进行对比验证，结果表明SVM 预测模型预测 均方误差仅为RSM 预测模型的 17.9%，预测精度较高，能够较好的预测微铣削表面粗糙度 的大小和变化规律。因此，SVM 预测模型更适合于微铣削表面粗糙度的预测。 关键词：微铣削；表面粗糙度；预测模型；响应曲面法；支持向量机回归 中图分类号：TH16 15 Research on the prediction model of Micro-milling surface roughness Wang Xinxin, Lu Xiaohong, Jia Zhenyuan, Jia Xu, Li Guangjun, Wu Wenyi (School of Mechanical Engineering, Dalian University of Technology, LiaoNing DaLian 116024) 20 Abstract: Surface roughness is an important performance indication for micro-milling processing. Establishing a roughness-prediction model with high-precision is helpful to select the cutting parameters for micro-milling.Two prediction models are established by RSM (Response surface method) and SVM (Support Vector Machine Regression) in this paper. Four cutting parameters are involved in the models (extended length of micro-milling tool, spindle speed, feed per tooth, 25 and cutting depth in the axial direction). The models are established for material of brass. Experiments are carried out to verify the accuracy of the models. The results show that SVM prediction model has higher prediction accuracy, predict the variation law of micro-milling surface roughness better than RSM. Keywo