计算机与现代化 ›› 2022, Vol. 0 ›› Issue (07): 67-73.

• 网络与通信 • 上一篇    下一篇

基于一致性度量的数字孪生模型实时自修正

  

  1. (东华理工大学信息工程学院,江西南昌330013)
  • 出版日期:2022-07-25 发布日期:2022-07-25
  • 作者简介:徐麟(1998—),男,江西抚州人,硕士研究生,研究方向:大数据与智能信息处理,E-mail: xlecit@163.com; 何月顺(1971—),男,湖南永州人,教授,博士生导师,博士,研究方向:人工智能,大数据与智能信息处理,E-mail: heys@ecut.edu.cn; 宋伟宁(1983—),男,山东威海人,讲师,博士,研究方向:智能制造,工业互联网,E-mail: swnwalker @ecut.edu.cn; 许婷婷(1996—),女,江西九江人,硕士研究生,研究方向:深度学习,图形图像处理,E-mail: 1585513771@qq.com。
  • 基金资助:
    国家自然科学基金资助项目(41872243); 国家重点研发计划项目(2018YFB1702700); 江西省放射性地学大数据技术工程实验室开放基金资助项目(JELRGBDT201903)

Real-time Self-correction of Digital Twin Model Based on Consistency Measurement

  1. (School of Information Engineering, East China University of Technology, Nanchang 330013, China)
  • Online:2022-07-25 Published:2022-07-25

摘要: 数字孪生技术解决了信息物理世界的融合难题,在工业互联网领域里获得了十分广泛的应用。为解决数字孪生与物理实体的动态修正问题,本文提出一种基于一致性度量的数字孪生模型实时自修正方法。利用数据变化快慢将模型分为渐变模型和快速模型2个部分,构建参数快速搜索方法,结合拉丁超立方全局搜索和贪婪局部搜索,并引入迭代更新机制,实现物理实体和数字孪生体的一致性度量。实验结果表明,数字孪生模型通过优化模型可调参数的选取过程,改善可调参数选取随机性的问题,实现模型与物理实体高度一致性,达到了模型实时自修正要求。

关键词: 一致性度量, 数字孪生, 实时自修正, 拉丁超立方抽样

Abstract: Digital twin technology solves the problem of integration in the cyber-physical world, and has been widely used in the field of industrial Internet. In order to solve the problem of dynamic correction between digital twin and physical entity, this paper proposes a real-time self-correction method for digital twin model based on consistency measurement. Using the speed of data change, the model is divided into two parts: a gradual model and a fast model. A quick parameter search method is constructed. Combined with Latin hypercube global search and greedy local search, an iterative update mechanism is introduced to achieve the consistency measurement of physical entities and digital twins. The results show that the digital twin model improves the randomness of the adjustable parameter selection by optimizing the model adjustable parameter selection process, achieves ahigh degree of consistency between the model and the physical entity, and meets the requirements of model real time self-correction.

Key words: consistent measurement, digital twin, real-time self-correction, Latin hypercube sampling