考虑运行条件的Elman网络丝杠驱动系统热误差建模  

Modeling on thermal errors of ball screw driving system on Elman network considering operating conditions

作　　者：陈诚[1] 杨传民[1] 张晨阳[1] 谭文斌[2] 李醒飞[2] 

机构地区：[1]天津商业大学机械工程学院,天津300134 [2]天津大学精密测试技术及仪器国家重点实验室,天津300072

出　　处：《光学精密工程》2014年第3期704-711,共8页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.61304243);国家科技支撑资助项目(No.2011BAD24B01)

摘　　要：研究了建立滚珠丝杠副热误差模型的方法,以进一步提高半闭环丝杠驱动系统的定位精度。分析了滚珠丝杠副的热源和温度场的动态特性并考虑丝杠驱动系统运行条件提出了基于Elman神经网络的热误差建模方法。首先,根据滚珠丝杠副的结构特点,确定其内部热源及温度场分布特性。然后,基于丝杠温度分布函数,研究丝杠热变形与其内部热源之间的动态非线性函数关系。最后,综合考虑丝杠驱动系统运行条件对其热误差的影响,建立了基于Elman神经网络的热误差预测模型。实验结果表明,当丝杠驱动系统的运行条件较为复杂时,采用文中提出的预测模型得到的热变形估计残差为-3.1μm^2.4μm。结果显示:考虑运行条件的Elman神经网络比BP和Elman网络(仅考虑温升数据)具有更好的预测精度和鲁棒性,有较强的工程应用前景。The modeling methods for thermal errors of a ball screw tioning precision of a sem closed loop ball screw driving system. sources, temperature fields of the ball screw were analyzed and model based on Elman neural networks and operating conditions heat sources and temperature field distribution characteristics of was researched to improve the posi The dynamic characteristics of heat how to establish the thermal error was proposed. Firstly, the internal the ball screw were determined ac- cording to the structure studied. Then, the dynamic nonlinear functional relationship between the thermal deformation of ball screw and its internal heat sources was researched based on the tempera- ture distribution function. Finally, on the basis of Elman neural networks, the thermal error predic- tion model of ball screw was established in consideration of the effect of operating condition on the thermal error. Experimental results indicate that the estimated residual error of thermal deformation by the proposed model varies from --3.1 μm to 2.4 μm when the ball screw is worked at a complex environment. It concludes that the prediction precision and robustness by the proposed model based on Elman neural network and operating conditions are better than those by the BP and Elman neural net- works （just considering temperature data）, and it shows a powerful engineering application prospect.

关 键 词：滚珠丝杠 热误差 动态神经网络 ELMAN网络 运行条件 

分 类 号：TH161.4[机械工程—机械制造及自动化] TH703