面向加工领域的数字孪生模型自适应迁移方法

doi:10.16183/j.cnki.jsjtu.2021.167

摘要/Abstract

摘要：

在多品种小批量生产制造车间中,针对特定场景所建立的数字孪生模型,由于缺乏工况变化的自适应能力,导致加工质量预测精度不足.对此,提出一种数字孪生模型自适应迁移方法.通过搭建可迁移的数字孪生模型,实现机理和算法模型融合的加工质量在线预测;提出数字孪生模型迁移流程和迁移策略,基于特征数据分析计算,选择待迁移的源模型;同时,结合迁移学习理论实现简单和复杂变工况下的数字孪生模型迁移.以钻削加工为例,搭建钻削实验平台并对数字孪生模型迁移的可行性进行验证.研究结果表明,变化工况下,迁移后模型仍能保持预测误差低于1.5%.该方法为提高数字孪生模型自适应能力提供了新的思路.

关键词: 数字孪生, 质量预测, 工况变化, 迁移学习

Abstract:

In the multi-variety and small batch manufacturing workshop, digital twin model is mostly established for specific scenarios. Due to its lack of adaptive ability under working conditions, the prediction accuracy of machining quality is insufficient. To solve this problem, an adaptive transferring method of the digital twin model is proposed. By building the transferable digital twin model, the online prediction of machining quality based on the fusion of mechanism and algorithm model is realized. The transferring process and strategy of the digital twin model are proposed. Based on the analysis and calculation of characteristic data, the source model to be transferred is selected. At the same time, in combination with the transfer learning theory, the transfer of digital twin models is realized under simple and complex changing conditions. Taking drilling as an example, the drilling experiment platform is built and the feasibility of digital twin model transfer is verified. The results show that the model can keep the mean absolute error of prediction less than 1.5% under changing working conditions. This method provides a new idea to improve the adaptive ability of digital twin models.

Key words: digital twin, quality prediction, change of working conditions, transfer learning

中图分类号:

TG525

沈慧, 刘世民, 许敏俊, 黄德林, 鲍劲松, 郑小虎. 面向加工领域的数字孪生模型自适应迁移方法[J]. 上海交通大学学报, 2022, 56(1): 70-80.

SHEN Hui, LIU Shimin, XU Minjun, HUANG Delin, BAO Jingsong, ZHENG Xiaohu. Adaptive Transferring Method of Digital Twin Model for Machining Domain[J]. Journal of Shanghai Jiao Tong University, 2022, 56(1): 70-80.

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

图11

表2

参考文献 29

[1]	RIOS J, HERNANDEZ J C, OLIVA M, et al. Product avatar as digital counterpart of a physical individual product: Literature review and implications in an aircraft[J]. Transdisciplinary Lifecycle Analysis of Systems, 2015: 657-666.
[2]	庄存波, 刘检华, 熊辉, 等. 产品数字孪生体的内涵、体系结构及其发展趋势[J]. 计算机集成制造系统, 2017, 23(4):753-768.
	ZHUANG Cunbo, LIU Jianhua, XIONG Hui, et al. Connotation, architecture and trends of product digital twin[J]. Computer Integrated Manufacturing Systems, 2017, 23(4):753-768.
[3]	TAO F, CHENG J F, QI Q L, et al. Digital twin-driven product design, manufacturing and service with big data[J]. The International Journal of Advanced Manufacturing Technology, 2018, 94(9/10/11/12):3563-3576. doi: 10.1007/s00170-017-0233-1 URL
[4]	LU Y Q, LIU C, WANG K I K, et al. Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues[J]. Robotics and Computer-Integrated Manufacturing, 2020, 61:101837. doi: 10.1016/j.rcim.2019.101837 URL
[5]	陶飞, 刘蔚然, 张萌, 等. 数字孪生五维模型及十大领域应用[J]. 计算机集成制造系统, 2019, 25(1):1-18.
	TAO Fei, LIU Weiran, ZHANG Meng, et al. Five-dimension digital twin model and its ten applications[J]. Computer Integrated Manufacturing Systems, 2019, 25(1):1-18.
[6]	CHENG D J, ZHANG J, HU Z T, et al. A digital twin-driven approach for on-line controlling quality of marine diesel engine critical parts[J]. International Journal of Precision Engineering and Manufacturing, 2020, 21(10):1821-1841. doi: 10.1007/s12541-020-00403-y URL
[7]	ZHANG S Z, KANG C F, LIU Z F, et al. A product quality monitor model with the digital twin model and the stacked auto encoder[J]. IEEE Access, 2020, 8:113826-113836. doi: 10.1109/Access.6287639 URL
[8]	WANG K J, LEE Y H, ANGELICA S. Digital twin design for real-time monitoring—A case study of die cutting machine[J]. International Journal of Production Research, 2020: 1-15.
[9]	LIU S M, LU Y Q, LI J, et al. Multi-scale evolution mechanism and knowledge construction of a digital twin mimic model[J]. Robotics and Computer-Integrated Manufacturing, 2021, 71:102123. doi: 10.1016/j.rcim.2021.102123 URL
[10]	ZHENG X C, PSAROMMATIS F, PETRALI P, et al. A quality-oriented digital twin modelling method for manufacturing processes based on a multi-agent architecture[J]. Procedia Manufacturing, 2020, 51:309-315. doi: 10.1016/j.promfg.2020.10.044 URL
[11]	胡富琴, 杨芸, 刘世民, 等. 航天薄壁件旋压成型数字孪生高保真建模方法[DB/OL]. (2020-12-03)[2021-10-10]. https://kns.cnki.net/kcms/detail/detail.aspx?dbcode=CAPJ&dbname=CAPJLAST&filename=JSJJ20201202006&uniplatform=NZKPT&v=l5%25mmd2FDG1c37fujR8sUdeYLf9B5r65UCl4%25mmd2Fa2zSBKWwIqELwei0ELnCptUEaWMpEu2k.
	HU Fuqin, YANG Yun, LIU Shimin, et al. Digital Twin High-fidelity Modeling Method for Spinning Forming of Aerospace Thin-walled Parts[DB/OL]. (2020-12-03)[2021-10-10]. https://kns.cnki.net/kcms/detail/detail.aspx?dbcode=CAPJ&dbname=CAPJLAST&filename=JSJJ20201202006&uniplatform=NZKPT&v=l5%25mmd2FDG1c37fujR8sUdeYLf9B5r65UCl4%25mmd2Fa2zSBKWwIqELwei0ELnCptUEaWMpEu2k.
[12]	QIAO Q Z, WANG J J, YE L K, et al. Digital twin for machining tool condition prediction[J]. Procedia CIRP, 2019, 81:1388-1393. doi: 10.1016/j.procir.2019.04.049 URL
[13]	CHRISTIAND, KISWANTO G. Digital twin approach for tool wear monitoring of micro-milling[J]. Procedia CIRP, 2020, 93:1532-1537. doi: 10.1016/j.procir.2020.03.140 URL
[14]	胡家文, 蒋祖华, 韩李杰. 工况时变下设备预防维护策略[J]. 上海交通大学学报, 2016, 50(5):736-741.
	HU Jiawen, JIANG Zuhua, HAN Lijie. Preventive maintenance for machine operating in dynamic environmental state[J]. Journal of Shanghai Jiao Tong University, 2016, 50(5):736-741.
[15]	姚锡凡, 景轩, 张剑铭, 等. 走向新工业革命的智能制造[J]. 计算机集成制造系统, 2020, 26(9):2299-2320.
	YAO Xifan, JING Xuan, ZHANG Jianming, et al. Towards smart manufacturing for new industrial revolution[J]. Computer Integrated Manufacturing Systems, 2020, 26(09):2299-2320.
[16]	WEI Y L, HU T L, ZHOU T T, et al. Consistency retention method for CNC machine tool digital twin model[J]. Journal of Manufacturing Systems, 2021, 58:313-322. doi: 10.1016/j.jmsy.2020.06.002 URL
[17]	CHAKRABORTY S, ADHIKARI S. Machine learning based digital twin for dynamical systems with multiple time-scales[J]. Computers & Structures, 2021, 243:106410. doi: 10.1016/j.compstruc.2020.106410 URL
[18]	孙惠斌, 潘军林, 张纪铎, 等. 面向切削过程的刀具数字孪生模型[J]. 计算机集成制造系统, 2019, 25(6):1474-1480.
	SUN Huibin, PAN Junlin, ZHANG Jiduo, et al. Digital twin model for cutting tools in machining process[J]. Computer Integrated Manufacturing Systems, 2019, 25(6):1474-1480.
[19]	ZHANG C Y, XU W J, LIU J Y, et al. A reconfigurable modeling approach for digital twin-based manufacturing system[J]. Procedia CIRP, 2019, 83:118-125. doi: 10.1016/j.procir.2019.03.141 URL
[20]	ZHANG C Y, XU W J, LIU J Y, et al. Digital twin-enabled reconfigurable modeling for smart manufacturing systems[J]. International Journal of Computer Integrated Manufacturing, 2021, 34(7/8):709-733. doi: 10.1080/0951192X.2019.1699256 URL
[21]	TAO J F, QIN C J, XIAO D Y, et al. A pre-generated matrix-based method for real-time robotic drilling chatter monitoring[J]. Chinese Journal of Aeronautics, 2019, 32(12):2755-2764. doi: 10.1016/j.cja.2019.09.001 URL
[22]	DONG S, ZHENG K, LIAO W H. Stability of lateral vibration in robotic rotary ultrasonic drilling[J]. International Journal of Mechanical Sciences, 2018, 145:346-352. doi: 10.1016/j.ijmecsci.2018.07.004 URL
[23]	庄福振, 罗平, 何清, 等. 迁移学习研究进展[J]. 软件学报, 2015, 26(1):26-39.
	ZHUANG Fuzhen, LUO Ping, HE Qing, et al. Survey on transfer learning research[J]. Journal of Software, 2015, 26(1):26-39.
[24]	储成龙. 钛合金铣削表面粗糙度预测建模[D]. 南京: 南京航空航天大学, 2010.
	CHU Chenglong. Prediction modelling of surface roughness of Ti alloy milling[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2010.
[25]	许敏俊, 刘世民, 沈慧, 等. 数字孪生驱动下的弱刚性钻削毛刺控制[DB/OL]. (2021-06-18)[2021-10-10]. https://kns.cnki.net/kcms/detail/detail.aspx?dbcode=CAPJ&dbname=CAPJLAST&filename=JSJJ2021061700C&uniplatform=NZKPT&v=EfDktvpY4SBOwwS6TS4QLlTZjbR7nWvc3en%25mmd2FMDFVvXB9vWzS2wo6b3C0cHx8SIpv.
	XU Minjun, LIU Shimin, SHEN Hui, et al. Burr control of weak rigid drilling process driven by digital twin[DB/OL].(2021-06-18)[2021-10-10]. https://kns.cnki.net/kcms/detail/detail.aspx?dbcode=CAPJ&dbname=CAPJLAST&filename=JSJJ2021061700C&uniplatform=NZKPT&v=EfDktvpY4SBOwwS6TS4QLlTZjbR7nWvc3en%25mmd2FMDFVvXB9vWzS2wo6b3C0cHx8SIpv.
[26]	DAY O, KHOSHGOFTAAR T M. A survey on heterogeneous transfer learning[J]. Journal of Big Data, 2017, 4(1):1-42. doi: 10.1186/s40537-016-0062-3 URL
[27]	YOSINSKI J, CLUNE J, BENGIO Y, et al. How transferable are features in deep neural networks? [DB/OL].(2014-09-06)[2021-10-10]. https://arxiv.org/abs/1411.1792v1.
[28]	LONG M, CAO Y, WANG J, et al. Learning transferable features with deep adaptation networks[DB/OL].(2015-07-06)[2021-10-10]. https://dl.acm.org/doi/10.5555/3045118.3045130.
[29]	TZENG E, HOFFMAN J, ZHANG N, et al. Deep domain confusion: Maximizing for domain invariance[EB/OL].(2014-12-10)[2021-10-10]. https://arxiv.org/abs/1412.3474.

序号	模型种类	MAE/%
1	迁移前模型	4.54
2	迁移后模型	0.92
3	特征数据训练模型	6.39

序号	模型种类	MAE/%
1	迁移前模型	3.95
2	迁移后模型	1.49
3	特征数据训练模型	6.73