摘要
针对数控机床电主轴复杂的热变形机理,建立了基于径向基函数神经网络的组合预测模型预测其变化趋势。根据测量的电主轴热变形数据,分别采用自回归分析模型、灰色系统模型和智能组合预测模型对主轴热误差进行了预测。结果表明:电主轴热误差组合预测模型的预测准确性优于各单项模型,相对预测精度高出较高单项预测模型3%。
Aiming at the complicated thermal deformation generation mechanisms of motorized spindles of numerical control machines, a combined prediction model based on radial basis function neural network is proposed to forecast their change trends. According to the measured data of thermal deformation of motorized spindles, the thermal errors of spindles are predicted by means of the au- toregressive analysis model, gray system model and combination forecasting model respectively. Ex- perimental results show that the prediction precision of the combined prediction model for motorized spindle thermal errors is the highest among the three kinds of forecasting models, and its relative forecast precision is about 3 % above other single prediction models.
出处
《南京理工大学学报》
EI
CAS
CSCD
北大核心
2012年第6期1021-1025,共5页
Journal of Nanjing University of Science and Technology
基金
国家科技重大专项资助项目(2010ZX04001-032)
甘肃省自然科学基金(1010RJZA043)
兰州理工大学红柳青年教师培养计划(Q201212)
关键词
电主轴
热误差
组合模型
预测
径向基函数
自回归分析
灰色系统
motorized spindles
thermal errors
combined models
forecasting
radial basis function
autoregressive analysis
gray system