变工况下基于迁移学习融合域内对齐的机床主轴热误差模型  

Thermal error model of machine tool spindle based on in-domain alignment and transfer learning under variable working conditions

作　　者：郑悦 付国强 雷国强 周琳丰 朱思佩 Zheng Yue;Fu Guoqiang;Lei Guoqiang;Zhou Linfeng;Zhu Sipei(School of Mechanical Engineering,Southwest Jiaotong University,Chengdu 610031,China)

机构地区：[1]西南交通大学机械工程学院,成都610031

出　　处：《仪器仪表学报》2023年第5期33-43,共11页Chinese Journal of Scientific Instrument

基　　金：国家自然科学基金(52175486,51805457);四川省科技计划项目(2022YFG0218);流体动力与机电系统国家重点实验室开放基金课题(GZKF-202104);衢州市科技计划项目(2022K90);中央高校基本科研业务费专项资金(2682022ZTPY061)项目资助。

摘　　要：热误差建模和补偿是提高机床加工精度的重要手段。将得到的热误差模型应用到类似或相近任务中,对减少模型构建和数据收集的成本具有重要意义。本文提出了一种简易迁移学习(EasyTL)融合域内对齐的主轴热误差建模方法,以实现不同工况下误差模型的迁移复用。建立基于域内对齐和距离矩阵全组合择优的热误差迁移模型参数选取方法,获得最优组合。进一步分析不同类型的域内对齐和距离矩阵各自对模型迁移性能的影响。最后,将迁移模型与kNN典型机器学习模型和卷积神经网络深度模型进行比较验证,分别预测不同工况下主轴Z向和Y向的热误差。此外,根据预测的主轴热误差进行工件补偿加工实验。该方法为热误差建模及补偿提供了一种新思路。Thermal error modeling and compensation is an important tool to improve the machining accuracy of machine tools.It is important to apply the obtained thermal error models to similar tasks to reduce the cost of model construction and data collection.In this article,an easy transfer learning(EasyTL)with intra-domain alignment method for spindle thermal error modeling is proposed to realize the transfer reuse of error models under different working conditions.Further,the respective effects of different types of intra-domain alignment and distance matrices on model migration performance are analyzed.Finally,the EasyTL model is compared and validated with machine learning kNN and deep learning CNN to predict the thermal errors of the Z-direction and Y-direction of spindle under different working conditions,respectively.This method provides a new idea for modeling and compensating the thermal errors of machine spindles.In addition,a workpiece compensation machining experiment is carried out according to the thermal error of the spindle established by the thermal error prediction.The average error of the workpiece after compensation is reduced.This method provides a new idea for the thermal error modeling and compensation.

关 键 词：数控机床 热误差建模 迁移学习 域内对齐 变工况 

分 类 号：TH164[机械工程—机械制造及自动化]