基于最小二乘支持向量机的数控机床热误差预测

Thermal error prediction of numerical control machine tools based on least squares support vector machines

为实现数控机床热误差的补偿控制,提出基于最小二乘支持向量机进行数控机床热误差建模预测的方法.根据最小二乘支持向量机回归预测的原理,优化选择最小二乘支持向量机参数,对数控车床热误差进行最小二乘支持向量机建模.通过测量数控车床主轴温升值与主轴热变形量,将获得的数据进行最小二乘支持向量机建模训练,以建立机床热误差预测模型.实验结果表明,该模型能有效描述热动态误差,与最小二乘法建模进行比较,结果显示,基于最小二乘支持向量机的数控机床热误差预测模型精度高、泛化能力强;采用最小二乘支持向量机得到的预测模型可用于数控机床热误差实时补偿,以提高机床的加工精度..

A new thermal error prediction methodology for machine tool based on least squares support vector machines （LS-SVM） was presented to realize compensation for the thermal error of numerical control （NC） machine. The LS-SVM model was used to track the nonlinear time-varying thermal error by selecting the parameters of LS-SVM. The temperature variations of the NC lathe and the thermal errors of the spindle were measured, and the data were trained to construct the prediction model of NC thermal error on LS-SVM. Experimental results showed that LS-SVM is an effective method for error prediction. Comparison indicates that the LS-SVM performs better than the multi-variable least squares regression analysis in terms of model accuracy and robustness. The thermal deformation can be compensated using the constructed thermal error model.