基于数字孪生和深度迁移学习的电主轴热误差建模方法

doi:10.3901/JME.2025.03.052

机械工程学报 ›› 2025, Vol. 61 ›› Issue (3): 52-66.doi: 10.3901/JME.2025.03.052

• 特邀专栏：人机联合认知赋能的高端装备设计、制造与运维 • 上一篇

扫码分享

基于数字孪生和深度迁移学习的电主轴热误差建模方法

马帅¹, 冷杰武¹, 陈祝云², 李巍华², 李波^3,4, 刘强¹

1. 广东工业大学省部共建精密电子制造技术与装备国家重点实验室广州 510006;
2. 华南理工大学机械与汽车工程学院广州 510640;
3. 湖北文理学院机械工程学院襄阳 441053;
4. 襄阳华中科技大学先进制造工程研究院襄阳 441106

收稿日期:2024-02-21 修回日期:2024-08-04 发布日期:2025-03-12
作者简介:马帅，男，1996年出生，博士研究生。主要研究方向为深度迁移学习和数字孪生。E-mail:isms_edu@163.com;陈祝云，男，1990年出生，博士，副研究员。主要研究方向为机械信号处理，数字孪生，装备智能运维。E-mail:mezychen@scut.edu.cn;刘强(通信作者)，男，1978年出生，博士，教授，博士研究生导师。主要研究方向柔性产线变型设计，智能制造关键技术。E-mail:liuqiang@gdut.edu.cn
基金资助:
国家自然科学基金(52205101)、湖北省科技重大专项(2021AA003)、广东省基础与应用基础研究基金(2021A1515110708、202201010615)和广州市基础与应用基础研究基金资助项目。

Thermal Error Modeling Method towards Electric Spindles Based on Digital Twin and Deep Transfer Learning

MA Shuai¹, LENG Jiewu¹, CHEN Zhuyun², LI Weihua², LI Bo^3,4, LIU Qiang¹

1. State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangdong University of Technology, Guangzhou 510006;
2. School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640;
3. School of Mechanical Engineering, Hubei University of Arts and Sciences, Xiangyang 441053;
4. XY-HUST Advanced Manufacturing Engineering Research Institute, Xiangyang 441106

Received:2024-02-21 Revised:2024-08-04 Published:2025-03-12

摘要/Abstract

摘要： 热误差是电主轴系统误差的主要来源之一，热误差建模是提高系统可靠性的重要手段。电主轴装载刀具加工时，需要在多个方向上运动，导致实时测量困难，难以采集足够的热误差样本。不同工况下的数据分布差异较大，在某一工况下训练的热误差预测模型难以在其他工况下取得满意的预测精度。针对上述问题，提出了一种基于数字孪生和深度迁移学习的电主轴热误差建模方法。首先，建立电主轴系统热行为数字孪生模型，模拟出不同工况下的温度场和热变形数据，缓解实际场景中热误差样本缺失的限制。其次，开发基于领域对抗机制的卷积双向长短期记忆网络，数字孪生模型生成的虚拟数据用作源域，真实数据作为目标域，不同尺度的卷积层构成特征提取器，分别提取源域和目标域温度数据的空间特征，处理多维温度特征的共线性问题。构建双向长短期记忆网络作为预测器，处理温度与热误差的时序关系并输出预测值。同时，结合领域适配的对抗训练技术，利用域判别器混淆两域特征，最小化两域数据分布，提高模型的泛化能力。最后，搭建多源数据协同采集平台，获取不同工况下的真实数据，通过不同迁移任务验证，结果表明：在热误差标签样本缺失的情况下，该方法成功实现热误差建模，具备较好的预测性能。

关键词: 电主轴, 热误差建模, 数字孪生, 深度迁移学习, 领域适配

Abstract: Thermal error is one of the main sources of electric spindle system errors, and thermal error modeling is an important means to improve system reliability. In machining scenarios where the electric spindle is loaded with tools, it needs to move in multiple directions, which makes real-time measurement difficult and difficult to collect sufficient thermal error samples. Furthermore, the data distribution under different working conditions presents large discrepancies, and a well-trained model under one working condition failed to obtain satisfactory prediction accuracy when applied to another working condition. To address these issues, a thermal error modeling approach based on digital twins and deep transfer learning is proposed. Firstly, a digital twin model of the thermal behavior of the electric spindle system is established, where the temperature fields and thermal deformation data under different working conditions can be simulated to alleviate the limitation of the scarcity of the thermal error samples in real scenarios. Secondly, a convolutional bidirectional long short-term memory network based on the domain adversarial mechanism is developed. The virtual data generated by the digital twin model is used as the source domain, and the real data is used as the target domain. Convolutional layers of different scales are used as the feature extractor to extract the spatial features of the temperature data from both the source and target domains so as to address the collinearity issue of multi-dimensional temperature features. The bidirectional long short-term memory network is constructed as a predictor to process the time-series relationship between temperature and thermal error and output predictions. Additionally, the adversarial training technique of domain adaptation is employed to confuse the two domain features and minimize the distribution discrepancies between both domains, thereby improving the model's generalization ability. Finally, a multi-source data collaborative collection platform is established to obtain real data under variable working conditions. Different transfer tasks are constructed to validate the proposed method and the results showed the proposed method successfully achieves thermal error modeling in the absence of labeled thermal error samples and exhibits good prediction performance.

Key words: electric spindles, thermal error modeling, digital twin, deep transfer learning, domain adaptation

中图分类号:

TP391
TP399

马帅, 冷杰武, 陈祝云, 李巍华, 李波, 刘强. 基于数字孪生和深度迁移学习的电主轴热误差建模方法[J]. 机械工程学报, 2025, 61(3): 52-66.

MA Shuai, LENG Jiewu, CHEN Zhuyun, LI Weihua, LI Bo, LIU Qiang. Thermal Error Modeling Method towards Electric Spindles Based on Digital Twin and Deep Transfer Learning[J]. Journal of Mechanical Engineering, 2025, 61(3): 52-66.

参考文献

[1] BRYAN J. International status of thermal error research (1990)[J]. CIRP Annals，1990，39(2):645-656.
[2] MAYR J，JEDRZEJEWSKI J，UHLMANN E，et al. Thermal issues in machine tools[J]. CIRP Annals，2012，61(2):771-791.
[3] MAREŠ M，HOREJŠ O，HAVLÍK L. Thermal error compensation of a 5-axis machine tool using indigenous temperature sensors and CNC integrated Python code validated with a machined test piece[J]. Precision Engineering，2020，66:21-30.
[4] LI Z，WANG Q，ZHU B，et al. Thermal error modeling of high-speed electric spindle based on Aquila Optimizer optimized least squares support vector machine[J]. Case Studies in Thermal Engineering，2022，39:102432.
[5] WEI X，YE H，MIAO E，et al. Thermal error modeling and compensation based on Gaussian process regression for CNC machine tools[J]. Precision Engineering，2022，77:65-76.
[6] TAN F，YIN G，ZHENG K，et al. Thermal error prediction of machine tool spindle using segment fusion LSSVM[J]. The International Journal of Advanced Manufacturing Technology，2021，116(1):99-114.
[7] LIU Y，MIAO E，LIU H，et al. Robust machine tool thermal error compensation modelling based on temperature-sensitive interval segmentation modelling technology[J]. The International Journal of Advanced Manufacturing Technology，2020，106(1):655-669.
[8] ZHANG X，LIU Y，LOU P，et al. Thermal error modeling for heavy duty CNC machine tool based on convolution neural network[C]//2019 IEEE 3rd Information Technology，Networking，Electronic and Automation Control Conference (ITNEC). IEEE，2019:665-669.
[9] CHEN Y，CHEN J，XU G. A data-driven model for thermal error prediction considering thermoelasticity with gated recurrent unit attention[J]. Measurement，2021，184:109891.
[10] LIU J，MA C，GUI H，et al. Thermally-induced error compensation of spindle system based on long short term memory neural networks[J]. Applied Soft Computing，2021，102:107094.
[11] GUO J，XIONG Q，CHEN J，et al. Study of static thermal deformation modeling based on a hybrid CNN-LSTM model with spatiotemporal correlation[J]. The International Journal of Advanced Manufacturing Technology，2022:1-13.
[12] LIU P，DU Z，LI H，et al. Thermal error modeling based on BiLSTM deep learning for CNC machine tool[J]. Advances in Manufacturing，2021，9(2):235-249.
[13] CHEN Z，XIA J，LI J，et al. Generalized open-set domain adaptation in mechanical fault diagnosis using multiple metric weighting learning network[J]. Advanced Engineering Informatics，2023，57:102033.
[14] 赵树煊，张洁，汪俊亮，等. 基于两阶段深度迁移学习的面料疵点检测算法[J]. 机械工程学报，2021，57(17):86-97. ZHAO Shuxuan，ZHANG Jie，WANG Junliang，et al. Fabric defect detection algorithm based on two-stage deep transfer learning[J]. Journal of Mechanical Engineering，2021，57(17):86-97
[15] 邓柯楠，高栋，马守东，等. 基于迁移学习的铣削机器人定位误差补偿方法[J]. 机械工程学报，2022，58(14):170-180. DENG Kenan，GAO Dong，MA Shoudong，et al. An efficient error compensation method for milling robot based on transfer learning[J]. Journal of Mechanical Engineering，2022，58(14):170-180
[16] CHEN Z，LIAO Y，LI J，et al. A multi-source weighted deep transfer network for open-set fault diagnosis of rotary machinery[J]. IEEE Transactions on Cybernetics，2023，53(3):1982-1993.
[17] 陈祝云，钟琪，黄如意，等. 基于增强迁移卷积神经网络的机械智能故障诊断[J]. 机械工程学报，2021，57(21):96-105. CHEN Zhuyun，ZHONG Qi，HUANG Ruyi，et al. Intelligent fault diagnosis for machinery based on enhanced transfer convolutional neural network[J]. Journal of Mechanical Engineering，2021，57(21):96-105
[18] LI P，LOU P，YAN J，et al. The thermal error modeling with deep transfer learning[J]. Journal of Physics:Conference Series，2020，1576(1):12003.
[19] ZHANG X，WANG C，LOU P，et al. Machine Tools Thermal Error Modeling with Imbalanced Data Based on Transfer Learning[C]//2020 IEEE 5th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA). IEEE，2020:214-218.
[20] GRIEVES M，VICKERS J. Digital twin:Mitigating unpredictable，undesirable emergent behavior in complex systems[J]. Transdisciplinary Perspectives on Complex Systems:New Findings and Approaches，2017:85-113.
[21] TAO F，ZHANG H，LIU A，et al. Digital twin in industry:State-of-the-art[J]. IEEE Transactions on Industrial Informatics，2018，15(4):2405-2415.
[22] LENG J，WANG D，SHEN W，et al. Digital twins-based smart manufacturing system design in Industry 4.0:A review[J]. Journal of Manufacturing Systems，2021，60:119-137.
[23] LIU J，GUI H，MA C. Digital twin system of thermal error control for a large-size gear profile grinder enabled by gated recurrent unit[J]. Journal of Ambient Intelligence and Humanized Computing，2023，14(2):1269-1295.
[24] LU Q，ZHU D，WANG M，et al. Digital twin-driven thermal error prediction for CNC machine tool spindle[J]. Lubricants，2023，11(5):219.
[25] GANIN Y，USTINOVA E，AJAKAN H，et al. Domain-adversarial training of neural networks[J]. The Journal of Machine Learning Research，2016，17(1):2096-2030.
[26] JIAN B，GUO Y，HU C，et al. Prediction of spindle thermal deformation and displacement using back propagation neural network[J]. Sensors & Materials，2020，32:431-445.
[27] CHENG Y，ZHANG X，ZHANG G，et al. Thermal error analysis and modeling for high-speed motorized spindles based on LSTM-CNN[J]. The International Journal of Advanced Manufacturing Technology，2022，121(5):3243-3257.
[28] WU C，XIANG S，XIANG W. Spindle thermal error prediction approach based on thermal infrared images:A deep learning method[J]. Journal of Manufacturing Systems，2021，59:67-80.
[29] ZOU Z，YAN W，MA W，et al. Development of thermal error mapping model for the dry gear hobbing machine based on CNN-DAE integrated structure and its application[J]. The International Journal of Advanced Manufacturing Technology，2021，113(7):2343-2354.
[30] CHEN Y，ZHOU H，CHEN J，et al. Spindle thermal error modeling method considering the operating condition based on long short-term memory[J]. Engineering Research Express，2021，3(3):35019.
[31] LIANG Y C，LI W D，LOU P，et al. Thermal error prediction for heavy-duty CNC machines enabled by long short-term memory networks and fog-cloud architecture[J]. Journal of Manufacturing Systems，2022，62:950-963.
[32] LIU Y，LI K，TSAI Y. Spindle thermal error prediction based on LSTM deep learning for a CNC machine tool[J] Applied Sciences，2021，11(12):5444.

基于数字孪生和深度迁移学习的电主轴热误差建模方法

Thermal Error Modeling Method towards Electric Spindles Based on Digital Twin and Deep Transfer Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	胡炳涛, 钟锐锐, 冯毅雄, 杨晨, 王天跃, 洪兆溪, 谭建荣. 人-信息-物理互联环境下数字车间制造能力建模与自适应调度[J]. 机械工程学报, 2025, 61(3): 23-39.
[2]	宋轶民, 王睿哲, 连宾宾, 李祺, 孙涛. 基于数字孪生技术的并联机器人筒段类部组件装配系统[J]. 机械工程学报, 2025, 61(1): 44-59.
[3]	张超, 周光辉, 李晶晶, 魏智博, 秦天宇. 面向航空复杂零件智能工艺规划的孪生工艺模型构建与应用研究[J]. 机械工程学报, 2024, 60(6): 32-43.
[4]	王跃飞, 王超, 许于涛, 孙睿, 肖锴, 王凯林. 边-云协同下智能制造单元作业的数字孪生任务调度方法[J]. 机械工程学报, 2024, 60(6): 137-152.
[5]	姜文涛, 刘晓明, 李培源, 陈海, 张煦松. 机械式真空快速切换开关机构多目标优化设计[J]. 机械工程学报, 2024, 60(6): 153-162.
[6]	刘达新, 王科, 刘振宇, 许嘉通, 谭建荣. 基于数据融合与知识推理的机器人装配单元数字孪生建模方法研究[J]. 机械工程学报, 2024, 60(5): 36-50.
[7]	石健, 刘冬, 王少萍. 基于数字孪生的机电液系统PHM关键技术综述[J]. 机械工程学报, 2024, 60(4): 66-81.
[8]	孙文彪, 熊万里, 原帅, 曾旭, 汪剑. 磁化效应对高速磁悬浮外圆磨削电主轴回转精度影响规律研究[J]. 机械工程学报, 2024, 60(23): 236-245.
[9]	刘培, 蒋群艳, 杨嘉华, 焦磊, 冯展鹰, 胡长明, 刘庭煜, 倪中华. 基于数字孪生的大型天线阵面装配位姿快速调控方法[J]. 机械工程学报, 2024, 60(22): 415-426.
[10]	杨亮亮, 来孝楠, 何西旺, 李鹏, 郭正刚, 宋学官. 面向飞机机翼数字孪生的在线加速度积分方法[J]. 机械工程学报, 2024, 60(2): 342-355.
[11]	陈健, 孟义兴, 袁慎芳, 徐秋慧, 王卉. 融合导波监测的搭接结构裂纹扩展寿命孪生预测[J]. 机械工程学报, 2024, 60(16): 34-42.
[12]	刘岳开, 王天杨, 褚福磊. 基于低延迟可解释性深度学习的复杂旋转机械关键部件知识嵌入与诊断方法研究[J]. 机械工程学报, 2024, 60(12): 107-115.
[13]	叶文昌, 郭必成, 邓朝晖, 王伟, 邹伶俐, 刘超, 尹刚刚, 姜峰. 刀具智能化关键技术的研究进展及发展趋势[J]. 机械工程学报, 2023, 59(23): 265-282.
[14]	侯正航, 何卫平, 王淑侠, 胡余彭, 肖一帆. 基于数字孪生的弧齿型导引头伺服机构动态装调技术研究[J]. 机械工程学报, 2023, 59(22): 433-443.
[15]	李宏坤, 魏代同, 陈玉刚, 许书本. 数字孪生驱动的旋转叶盘振动状态全景感知方法[J]. 机械工程学报, 2023, 59(21): 270-282.