摘要
针对复杂曲面镜片加工的困难,将慢刀伺服车削应用于镜片加工中。采用正交试验回归分析法,建立基于刀具圆弧半径、每圈进给量、背吃刀量、主轴转速和离散角度的表面粗糙度指数预测模型。同时引入最小二乘支持向量机(Least squares support vector machine,LS-SVM),建立基于径向基函数的LS-SVM预测模型。该模型对正交试验样本进行训练学习,采用网格搜索和留一法交叉验证确定模型参数。通过验证试验的对比,LS-SVM模型的预测精度明显优于指数模型,其相关系数R2为0.998 85,方均根相对误差为10.95%,平均绝对百分误差为9.28%。正交试验和LS-SVM预测模型的分析结果表明,在主要工艺参数中刀具圆弧半径和每圈进给量对表面粗糙度影响较显著,背吃刀量次之。
Due to the difficulties of processing lenses with complex surface, slow tool servo is applied in the turning of lenses. An exponential model, based on the five main cutting parameters including tool nose radius, feed, depth of cut, spindle speed and discrimination angle, for surface roughness prediction Of lenses is developed by means of orthogonal experiment regression analysis. Meanwhile, a prediction model of surface roughness based on least squares support vector machine （LS-SVM） with radial basis function （RBF） is constructed. And orthogonal experiment swatches are studied, crossed grid search and leave-one-out cross-validation （LOO-CV） is applied to determine the model parameters. The comparison of LS-SVM model and exponential model is also carried out. Predictive LS-SVM model is found to be capable of better predictions for surface roughness and has correlation coefficient Rz of 0.998 85, the root mean square error of 10.95%, and the mean absolute percent error of 9.28%. The experimental results and prediction of LS-SVM model show that effects of tool nose radius and feed are more significant than that of depth of cut on surface roughness of lenses turning.
出处
《机械工程学报》
EI
CAS
CSCD
北大核心
2013年第15期192-198,共7页
Journal of Mechanical Engineering
基金
江苏省普通高校研究生科研创新计划资助项目(CXZZ12_0271)
关键词
镜片
慢刀伺服车削
正交回归分析
最小二乘支持向量机
预测模型
Lense Slow tool servo Orthogonal regression analysis Least squares support vector machine Prediction model
