.png){kind=icon}
返回
A digital shadow framework using distributed system concepts
.png){kind=icon}
PRE
AI
DOI：10.1007/s10845-022-02028-6.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Digital twin (DT) is a research topic that gained momentum in the Industry 4.0 era. The goal of DT is to create a virtual real-time intelligent system that is a typical twin of the physical system. DT provides analysis, prognosis, planning, and rapid response when needed. Digital shadow (DS) is an artifact concept of DT that provides a real-time replica of the physical system. Information in a DS is passed in one direction only, from the physical system to the virtual one. While in DT, the information goes in both directions. The definition and roles of DS and DT are overlapping. However, DS can be defined as the main component of a DT system. In this paper, DS roles are specified. Based on these roles, A DS framework architecture is proposed, and the communication system between its components. The proposed framework design is built using distributed system concepts such as event-driven architecture, microservices, and containerization. These concepts are well defined and utilized in the software engineering domain. The originality of the proposed framework is the definition of a systematic approach for designing and integrating digital models (DMs) from different vendors and domains. An experiment is designed to prove the framework's ability to shadow a physical system in real-time. Multiple DMs are implemented and deployed on the proposed DS framework. These DMs are used to shadow a natural gas compressor system. Experimental results prove the practicality of our proposed DS framework to operate in real-time.
Keyword:
Industry 4
0
Digital twin
Digital shadow
Distributed systems
Modeling
Simulation
期刊
IF:
7.4
论文数:
3.5K
被引数:
1.1W
机构
引用论文
Digital Twin Shop-Floor: A New Shop-Floor Paradigm Towards Smart Manufacturing数字孪生车间: 面向智能制造的新车间范式.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏分享收藏Integration of Digital Twin, Machine-Learning and Industry 4.0 Tools for Anomaly Detection: An Application to a Food PlantSENSORSOAAI
SENSORSIF3.5
OAAI分享收藏
查看更多内容