基于数据驱动的进给系统跟随误差预测

Data-driven Feed System Following Error Prediction

近年来,随着信息技术的发展,智能制造成为了未来制造业发展的必然趋势,而数字孪生作为实现智能的关键使能技术,也越来越受到重视。其应用潜力也得到越来越多的关注。在数控机床领域,速度、加速度与数控机床进给系统的跟随误差密切相关,同时间隙、摩擦等因素对跟随误差的影响也不容忽视,需要对数控机床伺服系统的跟随误差进行建模分析。目前,传统的基于数学模型的建模方法难以完全表征数控机床伺服系统实际的物理特性,而机电联合仿真的建模方法计算过程复杂且计算量过大。为此,基于数字孪生技术对私服系统跟随误差进行建模预测,根据跟随误差预测结果对进给系统的孪生模型进行修正,构建了进给系统的高保真数字孪生模型,为进给系统提供了前馈误差补偿参考。

In recent years,with the development of information technology,intelligent manufacturing has become an inevitable trend in the future development of manufacturing industry,and digital twins,as the key enabling technology to achieve intelligence,receive more and more attention.Its application potential is also getting more and more attention.In the field of CNC machine tool,the speed and acceleration are closely related to the following error of CNC machine tool feed system,and the influence of clearance,friction and other factors on the following error can not be ignored.At present,the traditional modeling method based on mathematical model is difficult to fully represent the actual physical characteristics of the CNC servo system,and the modeling method of electromechanical co-simulation is complicated and computationally too large.In order to solve the above problems,the following error is modeled and predicted based on the digital twin technology,and the twin model of the feed system is modified according to the prediction results of the following error,and the high-fidelity digital twin model of the feed system is constructed,which provides the corresponding reference for the actual feed forward error compensation.