基于非线性预测的机床主轴温升特性快速辨识  

Fast Identification of Machine Tool Spindle Temperature Rise Characteristics Based on Nonlinear Prediction

作　　者：冯刚[1] 夏晨晖[2] 孙磊[2] 傅建中[2] 

机构地区：[1]浙江工业职业技术学院机械工程学院,绍兴312000 [2]浙江大学机械工程学院,杭州310027

出　　处：《农业机械学报》2015年第6期341-348,共8页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金资助项目(51175461)

摘　　要：提出了一种快速辨识数控机床主轴温升特性的方法,该方法通过基于支持向量机回归的非线性预测技术,利用短时间实际采集主轴的温升数据,预测长达数小时的主轴温升曲线,并辨识出主轴的稳态温度、热平衡时间等温升特性参数。该方法可大大缩短数控机床主轴热平衡试验的时间。试验研究表明基于支持向量机回归的非线性预测方法快速辨识的主轴温升特性与热平衡试验结果相吻合,验证了本文方法的有效性与可行性。A new method of fast identifying temperature rise characteristics for machine tool spindle was developed. The nonlinear prediction technology based on support vector machine regression can predict the spindle temperature rise curve for a long time by only using a short period of measurement time. The steady-state temperature and thermal equilibrium time can be easily obtained from temperature prediction.The thermal balance test in the vertical machining center was done,and the method was applied under different working conditions. When spindle was running at 5 000 r / min with room temperature of 18℃,the temperature rise of the selected point was identified in 48 min while the time for obtaining the temperature rise curve from start-up of machine tool to temperature steady-state machine tool in practice can reach 400 min. The root mean square error（ RMSE） between estimated and measured temperature was 0. 184 8℃,and the error between estimated and measured steady-state temperature was 0. 039 2℃.The method can greatly shorten thermal balance test duration. The experimental research illustrated that the method of identifying spindle temperature rise characteristics was fit for thermal balance test. It proved that the novel method was effective and feasible.

关 键 词：机床 温升特性 非线性预测 支持向量机回归 

分 类 号：TG502.15[金属学及工艺—金属切削加工及机床]