摘要
文章研究了数控直线电机工作台的误差测量、建模及补偿技术。分析了定位平台的误差来源,采用激光干涉仪测量工作台的定位误差,用RBF算法建立神经网络误差模型,根据误差校正值进行误差实时补偿实验。仿真和实验结果表明:经过样本训练的神经网络模型对工作台的误差具有良好的学习能力和泛化能力,工作台定位精度显著提高,并且较好地解决了随机误差对系统的影响。
Studied the error measuring,modeling and compensation techniques for the positioning stage driven by NC linear motors.Analyzed the error source of the positioning stage,measured the positioning errors by the laser interferometer,set up the neural network error model by RBF algorithm and conducted the error compensation experiments.The simulation and experimental results indicate that the RBF neural network error model trained by samples has a good learning ability and a generalization ability,the positioning accuracy was improved significantly,and the effect of random errors on the system was reduced.
出处
《微电机》
北大核心
2011年第3期104-107,共4页
Micromotors
基金
江苏省高校自然科学基础研究项目(08KJB460003)
江苏省"六大人才高峰"高层次人才资助项目(2008163)
先进数控技术江苏省高校重点实验室开放基金项目(KXJ07122)
关键词
直线电机
定位误差
误差建模
误差补偿
径向基函数
linear motor
positioning errors
error modeling
error compensation
radial basis function（RBF）
