基于BAS-BP模型的在机测量系统误差白化建模  

Error Whitening Modeling of On-Machine Measurement System Based on BAS-BP Model

作　　者：杨洪涛[1,2] 马群[1,2] 张梦遥[1,2] 李莉 汪珺 YANG Hong-tao;MA Qun;ZHANG Meng-yao;LI Li;WANG Jun(School of Mechanical Engineering,Anhui University of Science and Technology,Huainan 232001,China;Key Laboratory of Mine Intelligent Equipment and Technology of Anhui Province,Anhui University of Science and Technology,Huainan 232001,China;不详)

机构地区：[1]安徽理工大学机械工程学院,淮南232001 [2]安徽理工大学矿山智能装备与技术安徽省重点实验室,淮南232001 [3]合肥学院先进制造工程学院,合肥230000

出　　处：《组合机床与自动化加工技术》2022年第5期163-167,共5页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：安徽省高校学科拔尖人才学术资助项目(gxbjZD2021049);安徽省重点研究与开发计划(202004a07020046);国家自然科学基金项目(51675004);安徽高校自然科学研究重点项目(KJ2019A0844)。

摘　　要：为了提高数控机床在机测量系统的测量精度,建立精确的、多因素影响下的单项误差白化模型,分析了在机测量系统单项误差的变化特点,提出一种BAS-BP建模方法,优化神经网络的权值和阈值,以空间位置和速度两种影响因素作为输入进行建模。以X轴5项几何误差为例,进行多元回归、BP和BAS-BP神经网络预测建模效果比较。实验结果表明,应用BAS-BP神经网络的预测建模精度最高,均方误差最大仅为0.7153μm。且能实现多因素影响下的几何误差白化建模,更适用于在机测量系统误差精确建模和后续的误差补偿。In order to improve the measurement accuracy of the on-machine measurement system of CNC machine tools,the key is to establish an accurate,single-error whitening model under the influence of multiple factors.Analyzes the variation characteristics of the individual errors of the on-machine measurement system,and proposes a BAS-BP modeling method to optimize the weights and thresholds of the neural network,and use the two influencing factors of spatial position and velocity as input to model.Taking the five geometric errors of the X axis as an example,the effects of multiple regression,BP and BAS-BP neural network prediction modeling are compared.The experimental results show that the prediction modeling accuracy of the BAS-BP neural network is the highest,and the maximum mean square error is only 0.7153μm.And it can realize geometric error whitening modeling under the influence of multiple factors,which is more suitable for accurate modeling of on-machine measurement system error and subsequent error compensation.

关 键 词：在机测量系统 几何误差 BAS-BP神经网络 影响因素 误差建模 

分 类 号：TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]