摘要
提出一种基于最小二乘支持向量机(LS-SVM)的高速切削温度预测方法。为验证其可行性,首先,构建了基于LS-SVM的高速切削温度预测模型并选取影响切削温度变化的主要加工参数(切削速度、进给量、轴向切深和径向切宽)为模型输入;其次,采用Box-Beknhen实验设计方法在尽可能多地获取的切削温度变化数据的同时减少实验次数。然后,构建了基于MCV850加工中心的高速切削温度测量系统,验证了所建立模型的预测精度。结果表明:模型预测误差<1%;以随机设定的两组不同于实验方案中的切削参数组合为测试数据,预测值偏离测量值百分比分别为0.83%和0.51%,表明所建立预测模型应用于主要加工参数情况下高速切削温度预测的可行性。
A high speed cutting temperature prediction method based on least squares support vector machine （LS - SVM） is proposed. In order to verify the feasibility of the method, firstly, the high speed cutting tem- perature model is established based on LS -SVM, and the major operation parameters （cutting speed, feed rate, axial depth of cut and radial width of cut） are chosen as the model input; secondly, the cut- ting experimental scheme is designed applicating Box -Beknhen experimental design method for gaining more cutting temperature data and less experimental times; then, a high speed cutting temperature measurement system is established based on a MCV850 vertical machining center for testing reliability of model prediction. Experimental results finally show： the prediction error of the model gains less 1%, and taking two groups random parameters as test data which is different from Box - Beknhen experimen- tal parameters designed before, the percentage of prediction data deviation measurement data are 0. 83% and 0. 51% respectively. Demonstrate the feasibility of the established cutting temperature prediction model appling to main processing parameters.
出处
《制造技术与机床》
北大核心
2015年第5期110-114,117,共6页
Manufacturing Technology & Machine Tool
基金
南京工程学院校科研启动基金(YKJ201303)
江苏省自然科学基金资助项目(BK2012476
BK20131341)
南京工程学院校项目:新一代GPS体系下形位稍度评定技术研究(KXJ07028)
关键词
高速切削
最小二乘支持向量机
温度测量与预测
high speed cutting
least squares support vector machine
temperature measurement and prediction
