基于在线最小二乘支持向量机的数控机床热误差建模与补偿  

Thermal error modeling & compensation of numerical control machine tools based on on-line least squares support vector machine

作　　者：林伟青[1] 傅建中[1] 许亚洲[1] 陈子辰[1] 

机构地区：[1]浙江大学机械工程学系

出　　处：《计算机集成制造系统》2008年第2期295-299,共5页Computer Integrated Manufacturing Systems

基　　金：国家自然科学基金资助项目(50675199);浙江省科技计划资助项目(2005E10049)~~

摘　　要：为消除数控机床热误差对加工精度的影响,提出了基于在线最小二乘支持向量机的数控机床热误差建模方法。为构建机床热误差模型,进行了建模实验,采用智能温度传感器与激光位移传感器分别测量机床温度值与主轴热变形量。将获得的数据进行在线最小二乘支持向量机建模训练,构建机床热误差模型。在根据模型得出误差预测值的同时,可以不断根据在线输入的新数据修正热误差模型本身,运算时间短,适用于在线建模。实验结果表明,基于在线最小二乘支持向量机的数控机床热误差建模方法具有精度高、鲁棒性强和计算时间短的特点。在此基础上,根据在线模型进行热误差补差,可有效消除机床热误差影响,提高数控机床的加工精度。To eliminate the influence of the thermal error on machining precision of workpiece, a modeling method based on On-line Least Squares Support Vector Machine （OLS-SVM） was proposed to implement error compensation. To construct the thermal error model of machine tool, a series of experiments were conducted to obtain the data of a Numerical Control （NC） milling machine, including temperature on different positions and the thermal deformation of spindle. By smart temperature sensors and laser position sensors, the temperature and thermal error of the machine tool were collected respectively. The data were trained to construct the thermal error model of NC tool based on OLS-SVM. The thermal error compensation model was modified recursively according to new input data. The process was very rapid and robust. Results showed that OLS-SVM was an effective method for error modeling which could be used for the on-line thermal error compensation and could greatly improve the machining precision.

关 键 词：在线最小二乘支持向量机 热误差 建模 补偿 

分 类 号：TP205[自动化与计算机技术—检测技术与自动化装置]