摘要
为了提高数控机床加工精度,消除数控机床热误差对加工精度的影响,文章提出了基于GA-SVR(遗传算法-支持向量回归机)的数控机床热误差建模方法。为了构建机床的热误差模型,首先采用温度传感器与位置传感器测量机床的温度与对应的机床主轴变形量。其次把获得的数据进行支持向量回归机建模训练,同时使用遗传算法寻找支持向量回归机相关参数的最优值。最后建立机床热误差模型,并验证模型的准确度。结果表明,基于GA-SVR的数控机床热误差建模方法具有精度高和鲁棒性强的特点。
In order to improve the precision of CNC,and eliminate the influence of the thermal error on machining precision of workpiece,GA-SVR(Genetic algorithm-Support vector regression) is used to construct a thermal error model of CNC.To construct the thermal error model of machine tool,lots of experiments were carried out to obtain the data of a CNC,including temperature on different positions and the thermal deformation of the chief axis by temperature sensors and position sensors.The data were trained to construct the thermal error model of NC tool based on SVR,and GA is used to find the optimized parameter of SVR.The thermal error model of CNC is constructed and validated by input data.The result showed that GA-SVR was an effective method for thermal error modeling,which could greatly improve the machining precision.
出处
《组合机床与自动化加工技术》
北大核心
2012年第2期9-11,15,共4页
Modular Machine Tool & Automatic Manufacturing Technique
基金
广东省高等职业技术教育研究会课题(GDGZ155)