基于数据驱动的数控机床自适应迭代学习控制  

Dada⁃driven Adaptive Iterative Learning Control for CNC Systems

作　　者：梁建智[1] 邱彪[1] 陈宇燕[1] 杨铭[2] 李廷彦 秦永振 LIANG Jianzhi;QIU Biao;CHEN Yuyan;YANG Ming;LI Tingyan;QIN Yongzhen(Faculty of Intelligent Manufacturing Engineering,Guangxi Electrical Polytechnic Institute,Nanning Guangxi 530007,China;Faculty of Electric Power Engineering,Guangxi Electrical Polytechnic Institute,Nanning Guangxi 530007,China;Nanning Xizhen Electronic Technology Development Co.,Ltd.,Nanning Guangxi 530007,China;Guangxi Shutong Electronics Co.,Ltd.,Nanning Guangxi 530007,China)

机构地区：[1]广西电力职业技术学院智能制造工程学院,广西南宁530007 [2]广西电力职业技术学院电力工程学院,广西南宁530007 [3]南宁市西真电子科技开发有限公司,广西南宁530007 [4]广西数通电子有限公司,广西南宁530007

出　　处：《机床与液压》2021年第8期50-54,共5页Machine Tool & Hydraulics

基　　金：2019年度广西高校中青年教师科研基础能力提升项目(2019KY1486);广西电力职业技术学院高精度数字化探测技术协同创新团队研究成果。

摘　　要：数控机床位置伺服系统受加工环境、零件形状和机床机电特性等变化因素的影响,其零件加工是一个典型的非线性、时变和不确定动力学变化过程,因此,建立其精确机制模型很困难。针对相同零件批量加工过程呈现的重复运行特点,基于被控对象的等价数据模型,提出一种基于数据驱动的自适应迭代学习控制方法。所提控制方法采用沿迭代轴的动态线性化方法,通过最小化控制目标函数,仅利用数控机床位置伺服系统的输入输出数据,实现学习控制增益的自适应更新,克服传统P型迭代学习控制方法固定增益的问题,并经过严格理论分析保证了该方法的收敛特性。仿真结果表明:提出的数据驱动自适应迭代学习控制方法,相比传统P型迭代学习控制方法,平均绝对误差和最大绝对误差分别减小了46%和56%。The manufacturing process of CNC machine tool is a typically nonlinear,time⁃varying and uncertain dynamics vary process because its position servo system is influenced by varying factors,such as machining environment,component shape and mechatronic properties.Therefore,it is challenging to build the precise dynamics model.Based on the equivalent data model of the con⁃trolled object,a data⁃driven adaptive iterative learning control approach was proposed by utilizing the repetitive operating pattern of a batch of same components.Through the dynamic linearization method on the iteration axis,the automatic updating of the learning con⁃trol gain was achieved by minimizing the control objective function with only requirement of the input and output data of the CNC sys⁃tem.The proposed approach overcome the problem of fixed gain for the traditional P-type iterative learning control,its convergence was guaranteed through a rigorous theoretical analysis.The simulation results show that the mean absolute error and maximum absolute error of the data⁃driven adaptive iterative learning control method reduce by 46%and 56%than those of the traditional P-type iterative learning control method.

关 键 词：数控机床位置伺服系统 动态线性化 P型迭代学习控制 自适应迭代学习 数据驱动控制 

分 类 号：TP29[自动化与计算机技术—检测技术与自动化装置]