数控机床主轴热误差建模参数优化

Parameter Optimization of Thermal Error of NC Machine

数控机床主轴系统的热变形所引起热误差是影响其加工质量及效率的主要因素,因此,对机床主轴的热误差进行建模及补偿有着十分重要的意义,而建模的方法多种多样,其中利用最小二乘支持向量机法建模对于非线性系统效果良好并使模型具备更好的决策能力。文章对机床主轴温度场进行了实时的采集,并以此为基础以matlab为平台利用网格搜索法在相对更大的范围内针对最小二乘支持向量机建模时核函数的重要参数对(γ、σ)的选值进行优化,有效的提高了建模精度。

The thermal error of main-shaft is the main factor that effects the machining quality and efficiency of NC machine. The modeling of thermal error of the main-shaft is significant. There are a lot of methods to build the model. The method of least squares support vector machine has good effect on nonlinear system and make the model have good decision-making ability. In this paper, the temperature field of the main-shaft is sampled and the important parameter γ and δ is optimized in a wider range when modeling with the least squares support vector machine by using grid searching method on the Matlab platform. In this way, the modeling accuracy is improved effectively.