纺织学报 ›› 2023, Vol. 44 ›› Issue (10): 214-222.doi: 10.13475/j.fzxb.20220509002

• 综合述评 • 上一篇    下一篇

数字孪生在纺纱领域应用的关键技术解析

李新荣1,2(), 韩鹏辉1,2, 李瑞芬3, 贾坤4, 路元江5, 康雪峰6   

  1. 1.天津工业大学 机械工程学院, 天津 300387
    2.天津市现代机电装备技术重点实验室, 天津 300387
    3.无锡纺织机械质量监督检验中心, 江苏 无锡 214062
    4.青岛宏大纺织机械有限责任公司, 山东 青岛 266000
    5.无锡经纬纺织科技试验有限公司, 江苏 无锡 214000
    6.参数技术(上海)软件有限公司北京分公司, 北京 100004
  • 收稿日期:2022-05-31 修回日期:2022-12-12 出版日期:2023-10-15 发布日期:2023-12-07
  • 作者简介:李新荣(1975—),男,教授,博士。主要研究方向为纺织装备智能化。E-mail:lixinrong7507@hotmail.com
  • 基金资助:
    工信部产业技术基础公共服务平台项目(2021-0173-2-1)

Review and analysis on key technology of digital twin in spinning field

LI Xinrong1,2(), HAN Penghui1,2, LI Ruifen3, JIA Kun4, LU Yuanjiang5, KANG Xuefeng6   

  1. 1. School of Mechanical Engineering, Tiangong University, Tianjin 300387, China
    2. Tianjin Key Laboratory of Advanced Mechatronics Equipment Technology, Tianjin 300387, China
    3. Wuxi Textile Machinery Quality Supervision and Inspection Center, Wuxi, Jiangsu 214062, China
    4. Qingdao Hongda Textile Machinery Co., Ltd., Qingdao, Shandong 266000, China
    5. Wuxi Jingwei Textile Technology Test Co., Ltd., Wuxi, Jiangsu 214000, China
    6. Parametric Technology (Shanghai) Software Co., Ltd., Beijing Branch, Beijing 100004, China
  • Received:2022-05-31 Revised:2022-12-12 Published:2023-10-15 Online:2023-12-07

摘要:

为探讨数字孪生在纺纱领域应用前景及价值,进一步促进纺纱领域的高质量发展,首先围绕提升纱线质量分析了纺纱领域的实际特点,并提出了数字孪生在纺纱领域的应用前景;然后分析了纺纱高质量发展中影响成纱质量的因素,以及相关因素的抽象模型与数字孪生抽象模型间的映射关系,并且在此基础上分析了数字孪生在纺纱领域不同情况下的核心理论,着重分析了非理想状态下的数字孪生优化方案;其次根据纺纱领域的特点提出了数字孪生在纺纱领域具体应用的解决方案及其应用的实际价值;最后提出:数字孪生在纺纱领域的应用要重点结合纺纱领域的特点,实现数据模型与机制模型的深度整合。

关键词: 智能制造, 数字孪生, 智能化纺纱, 成纱质量, 体系架构

Abstract:

Significance At present, China's spinning industry is changing from the traditional "win-by-quantity" to "win-by-quality" in order to further occupy the high-end market. However, at this stage, China's spinning industry is still facing problems such as dependence on manual experience, unstable yarn production quality, difficulty in improving yarn quality and so on. The emergence of digital twin technology and its application in other industries provide new solutions to the above problems. However, in the practical application process of digital twins, there are a series of problems that need to be solved urgently, such as unclear structure, lack of ready-made guidance, and disputes over the application form of digital twins, which hinder the further development of the spinning field. Therefore, from the perspective of improving yarn quality, this paper reviews and discusses the practical significance and specific forms of the application of digital twin for the intelligent transformation in the field of spinning.

Progress First of all, this paper introduced the basic concept of digital twins, the application of digital twins in other industries, the actual characteristics of the stage in which the spinning field is closely related to yarn quality, and the application prospect of digital twins in the spinning field. According to the actual characteristics of the spinning field, the yarn production was divided into design stage and production stage, and the characteristics of these two stages were analyzed and abstracted into mathematical expressions. At the same time, the key process of improving yarn quality in the spinning field was summarized as an abstract model, and the mapping relationship with the digital twin abstract model was described. The characteristics of the digital twin application in the ideal state and non-ideal state were analyzed, and the actual characteristics of the spinning field were further combined, and how to use the digital twin theory method to solve the practical problems in the spinning field in the non-ideal state was emphatically analyzed. Based on the discussions and analyses, an architecture system for the application of digital twins in the spinning field was proposed, which mainly describes the logical relationship between the data platform, the yarn quality prediction twin model, the equipment twin model, and the logistics twin model in the application process of digital twins in the spinning field, as well as the specific implementation steps. In addition, the construction processes of these key parts were also introduced.

Conclusion and Prospect In the future, the application of digital twinning in the field of spinning can develop in the direction of improving the accuracy of relevant digital twinning models, especially yarn prediction twinning models, using existing theories to better establish knowledge models, achieving better integration between models, improving the data interaction security of the spinning digital twinning industrial platform, and increasing the precision visualization of key equipment twinning models. In the application process of digital twins in the field of spinning, we should also pay attention to the combination of existing technologies. In addition, a series of relevant standards should also be formulated to finally realize the spinning digital twin standard system and provide reference for the intelligent transformation of spinning enterprises, so as to promote the implementation of the digital twin in the spinning production enterprises, promote the application of the digital twin in the spinning field, ultimately improve the production quality of yarn, promote the high-quality development of the spinning field, and also provide corresponding reference for the intelligent transformation of other fields in the textile industry.

Key words: intelligent manufacturing, digital twin, intelligent spinning, yarn quality, system architecture

中图分类号: 

  • TP317.4

图1

纺纱生产层级关系"

图2

理想状态的协同优化"

图3

非理想状态的数字孪生模型优化过程"

图4

虚实交互的数字孪生模型"

图5

纺纱数字孪生架构体系"

[1] 郭明瑞, 韩晨晨, 卢雨正, 等. 浅谈纺纱流程智能化发展的现状[J]. 棉纺织技术, 2020, 48(5): 81-84.
GUO Mingrui, HAN Chenchen, LU Yuzheng, et al. Disscussion of spinning process intelligent development status[J]. Cotton Textile Technology, 2020, 48(5): 81-84.
[2] 马磊. 物联网技术在纺织行业中的应用[J]. 纺织导报, 2018(3): 22-24.
MA Lei. An overview of lot technology in textile industry[J]. China Textile Leader, 2018(3): 22-24.
[3] 杨华明, 齐泽京, 梅顺齐. 全流程数字化智能化纺纱装备的开发与实践[J]. 纺织科学研究, 2021(6): 38-40.
YANG Huaming, QI Zejing, MEI Shunqi. Development and practice of whole process digital and intelligent spinning equipment[J]. Textile Science Research, 2021 (6): 38-40.
[4] 卫江, 田青, 夏治刚, 等. 100%国产化全流程自动化纺纱车间构建与生产实践[J]. 纺织导报, 2021(6): 54-56,58.
WEI Jiang, TIAN Qing, XIA Zhigang, et al. Construction and production practice of 100% domestic fullprocess automatic spinning workshop[J]. China Textile Leader, 2021(6): 54-56,58.
[5] 刘建忠, 陈洪奎. 在清梳联工序降低成纱棉结的几项改造[J]. 棉纺织技术, 2021, 49(9): 57-59.
LIN Jianzhong, CHEN Hongkui. Modification of reducing yarn neps in blowing-carding unit process[J]. Cotton Textile Technology, 2021, 49(9): 57-59.
[6] 李进彦, 樊建彬, 周义德. 粗细络联自动纺纱系统的设计与应用[J]. 棉纺织技术, 2015, 43(10): 62-66.
LI Jinyan, FAN Jianbin, ZHOU Yide. Design and application of roving-spinning-winding unit automatic spinning system[J]. Cotton Textile Technology, 2015, 43(10): 62-66.
[7] 张立彬, 孙银银, 刘明, 等. JSFA016型智能棉卷搬运系统的开发与应用[J]. 棉纺织技术, 2020, 48(5): 5-9.
ZHANG Libin, SUN Yinyin, LIU Ming, et al. Development and application of JSFA016 intelligent lap handling system[J]. Cotton Textile Technology, 2020, 48(5): 5-9.
[8] 陈平, 李攀, 秦明辉. 筒子纱自动包装生产线控制系统设计[J]. 包装工程, 2021, 42(19): 282-286.
CHEN Ping, LI Pan, QIN Minghui. Design of automatic package production line control system for cheese yarn[J]. Packaging Engineering, 2021, 42(19): 282-286.
[9] 程隆棣, 张洁, 张红霞, 等. 棉纺智能化纺纱关键技术刍议[J]. 纺织导报, 2021(6): 50-53,48.
CHENG Longdi, ZHANG Jie, ZHANG Hongxia, et al. Discussion on the key technology of intelligent cotton spinning[J]. China Textile Leader, 2021(6): 50-53,48.
[10] 袁恒民, 杨康康, 赵凯丽, 等. USTER专家系统在纺纱生产中的应用实践[J]. 棉纺织技术, 2021, 49(2): 53-56.
YUAN Hengmin, YANG Kangkang, ZHAO Kaili, et al. Application practice of USTER expert system in spinning production[J]. Cotton Textile Technology, 2021, 49(2): 53-56.
[11] 夏治刚, 徐卫林, 叶汶祥. 短纤维纺纱技术的发展概述及关键特征解析[J]. 纺织学报, 2013, 34(6): 147-154.
XIA Zhigang, XU Weilin, YE Wenxiang. Review of staple yarn spinning technology and analysis of its key features[J]. Journal of Textile Research, 2013, 34(6): 147-154.
[12] 万由顺, 卫江, 桂长明, 等. 全流程智能化纺纱技术创新点及应用效果[J]. 棉纺织技术, 2020, 48(1): 28-33.
WAN Youshun, WEI Jiang, GUI Changming, et al. Innovation point and application effect of whole process intelligent spinning technology[J]. Cotton Textile Technology, 2020, 48(1): 28-33.
[13] 王士合. 传统纺纱设备智能化升级改造思路探讨[J]. 棉纺织技术, 2020, 48(7): 52-55.
WANG Shihe. Discussion on intelligent upgrade and transformation idea of traditional spinning equipment[J]. Cotton Textile Technology, 2020, 48(7): 52-55.
[14] 夏治刚, 徐傲, 万由顺, 等. 基于碳中和的人-机-料-法-环五位一体纺纱新技术解析[J]. 纺织学报, 2022, 43(1): 58-66, 88.
XIA Zhigang, XU Ao, WAN Youshun, et al. Analysis of new five-element-integration spinning technology based on human-machine-material method-environment for carbon neutralization[J]. Journal of Textile Research, 2022, 43(1): 58-66, 88.
[15] 侯芝富, 朱春光, 宋圣山. 差别化纤维的纺纱质量控制要点[J]. 棉纺织技术, 2020, 48(9): 43-47.
HOU Zhifu, ZHU Chunguang, SONG Shengshan. Differential fiber spinning quality control key points[J]. Cotton Textile Technology, 2020, 48(9): 43-47.
[16] 马瑞, 席萍, 王育楠. 纺织行业强韧性稳增长机遇何在[N]. 中国纺织报, 2022-01-17.
MA Rui, XI Ping, WANG Yunan. What are the opportunities for strong, resilient and stable growth in the textile industry[N]. China Textile News, 2022-01-17.
[17] JLGA B, CL A, FT A, et al. A digital twin-based approach for the management of geometrical deviations during assembly processes[J]. Journal of Manufacturing Systems, 2021, 58: 108-117.
doi: 10.1016/j.jmsy.2020.04.020
[18] FAHIM M, SHARMA V, CAO T, et al. Machine learning-based digital twin for predictive modeling in wind turbines[J]. IEEE Access, 2022(10): 14184-14194.
[19] 殷士勇, 鲍劲松, 杨芸, 等. 环锭纺纱信息物理生产系统建模方法[J]. 纺织学报, 2021, 42(2): 65-73.
YIN Shiyong, BAO Jinsong, YANG Yun, et al. Modeling method of cyber physical production system for ring spinning[J]. Journal of Textile Research, 2021, 42(2): 65-73.
doi: 10.1177/004051757204200112
[20] 王波波, 郑小虎, 申兴旺, 等. 基于Elasticsearch的纺纱生产数据追溯方法[J]. 纺织学报, 2021, 42(12): 55-62.
WANG Bobo, ZHENG Xiaohu, SHEN Xingwang, et al. Method for data tracing based on Elasticsearch during spinning production[J]. Journal of Textile Research, 2021, 42(12): 55-62.
[21] 郑小虎, 鲍劲松, 马清文, 等. 基于模拟退火遗传算法的纺纱车间调度系统[J]. 纺织学报, 2020, 41(6): 36-41.
ZHENG Xiaohu, BAO Jinsong, MA Qingwen, et al. Spinning workshop collaborative scheduling method based on simulated annealing genetic algorithm[J]. Journal of Textile Research, 2020, 41(6): 36-41.
[22] 陶飞, 刘蔚然, 刘检华, 等. 数字孪生及其应用探索[J]. 计算机集成制造系统, 2018, 24(1): 1-18.
TAO Fei, LIU Weiran, LIU Jianhua, et al. Digital twin and its potential application exploration[J]. Computer Integrated Manufacturing Systems, 2018, 24(1): 1-18.
[23] GRIEVES, MICHAEL W. Product lifecycle management: the new paradigm for enterprises[J]. International Journal of Product Development, 2005, 2(1/2): 71.
doi: 10.1504/IJPD.2005.006669
[24] 严瑛, 李飞飞. 浅谈计算机配棉系统的发展与应用[J]. 棉纺织技术, 2014, 42(4): 13-16.
YAN Ying, LI Feifei. Discussion on development and application of computer cotton assorting system[J]. Cotton Textile Technology, 2014, 42(4): 13-16.
[25] 刘彬, 项前, 杨建国, 等. 基于遗传神经网络的纱线质量预测[J]. 东华大学学报(自然科学版), 2013, 39(4): 504-508.
LIU Bin, XIANG Qian, YANG Jianguo, et al. Combining the genetic algorithm with artificial neural networks for yarn quality forecasting[J]. Journal of Donghua University(Natural Science), 2013, 39(4): 504-508.
[26] 杨建国, 熊经纬, 徐兰, 等. 基于改进极限学习机的纱线质量预测[J]. 东华大学学报(自然科学版), 2015, 41(4): 494-497,508.
YANG Jianguo, XIONG Jingwei, XU Lan, et al. Yarn quality prediction based on improved extreme learning machine[J]. Journal of Donghua University(Natural Science), 2015, 41(4): 494-497,508.
[27] 查刘根, 谢春萍. 应用四层BP神经网络的棉纱成纱质量预测[J]. 纺织学报, 2019, 40(1): 52-56,61.
CHA Liugen, XIE Chunping. Prediction of cotton yarn quality based on four-layer BP neural network[J]. Journal of Textile Research, 2019, 40(1): 52-56,61.
[28] 罗荃, 熊伟. 棉纱质量微观管理控制分析[J]. 纺织器材, 2022, 49(2): 58-62.
LUO Quan, XIONG Wei. Control and analysis on micro-management of cotton yarn quality[J]. Textile Accessories, 2022, 49(2): 58-62.
[29] 李金键, 任家智, 梁灼, 等. 棉纺精梳机钳板摆轴的动力学分析[J]. 纺织学报, 2021, 42(6): 160-165.
LI Jinjian, REN Jiazhi, LIANG Zhuo. et al. Dynamic Analysis on nipper pendulum shaft in cotton combers[J]. Journal of Textile Research, 2021, 42(6): 160-165.
[30] 阎汉生. 5G技术在智能制造系统中的应用前景研究[J]. 中国宽带, 2022, 18(4): 81-83.
YAN Hansheng. Research on the application prospect of 5G technology in intelligent manufacturing system[J]. China Broadband, 2022, 18 (4): 81-83.
[31] 杨柏蔼, 赵山, 刘芳. 无服务器计算技术研究综述[J]. 计算机工程与科学, 2022, 44(4): 611-619.
YANG Boai, ZHAO Shan, LIU Fang. A survey on serverless computing[J] Computer Engineering & Science, 2022, 44(4): 611-619.
[32] 翟强, 程洪, 黄瑞, 等. 智能汽车中人工智能算法应用及其安全综述[J]. 电子科技大学学报, 2020, 49(4): 490-498,510.
ZHAI Qiang, CHENG Hong, HUANG Rui, et al. A survey: artificial intelligence and its security in intelligent vehicle[J]. Journal of University of Electronic Science and Technology of China, 2020, 49(4): 490-498,510.
[33] 《国防科技工业》编辑部. 美欧军工领域发力数字孪生技术应用[J]. 国防科技工业, 2019(2): 36-37.
The Editorial Department of Defense Science & Technology Industry. Application of digital twin technology in military industry in the United States and Europe[J]. Defense Science & Technology Industry, 2019 (2): 36-37.
[34] 段明皞, 张南, 耿华, 等. 基于数字孪生的装配车间实时监控系统开发[J]. 制造业自动化, 2021, 43(12): 110-112.
DUAN Minghao, ZHANG Nan, GENG Hua, et al. Development of real-time monitoring system for assembly workshop based on digital twin[J] Manufacturing Automation, 2021, 43(12): 110-112.
[1] 郑小虎, 刘正好, 陈峰, 张洁, 汪俊亮. 纺织工业智能发展现状与展望[J]. 纺织学报, 2023, 44(08): 205-216.
[2] 乌婧, 江振林, 吉鹏, 谢锐敏, 陈烨, 陈向玲, 王华平. 纺织品前瞻性制备技术及应用研究现状与发展趋势[J]. 纺织学报, 2023, 44(01): 1-10.
[3] 张洁, 徐楚桥, 汪俊亮, 郑小虎. 数据驱动的机器人化纺织生产智能管控系统研究进展[J]. 纺织学报, 2022, 43(09): 1-10.
[4] 毛慧敏, 孙磊, 屠佳佳, 史伟民. 纱线自动接头机关键技术[J]. 纺织学报, 2022, 43(09): 21-26.
[5] 高晓飞, 齐立哲, 孙云权. 面向柔性面料立体缝纫的随形机械手设计[J]. 纺织学报, 2022, 43(09): 27-33.
[6] 刘锋, 徐杰, 柯文博. 基于深度强化学习的服装缝制过程实时动态调度[J]. 纺织学报, 2022, 43(09): 41-48.
[7] 邵景峰, 董梦园. 相依竞争失效模型下细纱机性能退化对成纱质量的影响[J]. 纺织学报, 2022, 43(06): 171-179.
[8] 邵景峰, 石小敏. 基于非支配排序遗传算法的细纱工艺参数优化[J]. 纺织学报, 2022, 43(01): 80-88.
[9] 纪柏林, 王碧佳, 毛志平. 纺织染整领域支撑低碳排放的关键技术[J]. 纺织学报, 2022, 43(01): 113-121.
[10] 杜劲松, 余雅芸, 赵妮, 谢子昂, 费中华, 潘静姝. 不同类型服装企业智能制造能力成熟度评价模型[J]. 纺织学报, 2021, 42(05): 162-167.
[11] 汪松松, 彭来湖, 戴宁, 沈春娅, 胡旭东. 基于工业互联网的针织机械互联互通结构研究[J]. 纺织学报, 2020, 41(01): 165-173.
[12] 周亚勤, 汪俊亮, 鲍劲松, 张洁. 纺织智能制造标准体系架构研究与实现[J]. 纺织学报, 2019, 40(04): 145-151.
[13] 林惠婷, 高备, 张玉泽, 史倩倩, 汪军. 转杯纺旁路通道设计对成纱质量的影响[J]. 纺织学报, 2019, 40(02): 153-158.
[14] 查刘根, 谢春萍. 应用四层BP神经网络的棉纱成纱质量预测[J]. 纺织学报, 2019, 40(01): 52-56.
[15] 杨瑞华 刘超 薛元 高卫东. 转杯复合纺成纱器内流场模拟及纱线质量分析[J]. 纺织学报, 2018, 39(03): 26-30.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!