Abstract

Digital twins (DTs) is a promising technology in the revolution of the industry and essential for Industry 4.0. DTs play a vital role in improving distributed manufacturing, providing up-to-date operational data representation of physical assets, supporting decision-making, and avoiding the potential risks in distributed manufacturing systems. Furthermore, DTs need to collaborate within distributed manufacturing systems to predict the risks and reach consensus-based decision-making. However, DTs collaboration suffers from single failure due to attack and connection in a centralized manner, data interoperability, authentication, and scalability. To overcome the above challenges, we have discussed the major high-level requirements for the DTs collaboration. Then, we have proposed a conceptual framework to fulfill the DTs collaboration requirements by using the combination of blockchain, predictive analysis techniques, and DTs technologies. The proposed framework aims to empower more intelligence DTs based on blockchain technology. In particular, we propose a concrete ledger-based collaborative DTs framework that focuses on real-time operational data analytics and distributed consensus algorithms. Furthermore, we describe how the conceptual framework can be applied using smart transportation system use cases, i.e., smart logistics and railway predictive maintenance. Finally, we highlighted the future direction to guide interested researchers in this interesting area.

Highlights

  • Industry 4.0 revolution is considered to be a new paradigm of digital, autonomous, and decentralized control with the Industrial Internet of Things (IIoT), Machine Learning (ML), big data, and edge computing [1,2]

  • We explore how blockchain employing in Digital twins (DTs) collaboration with highlighting the benefits of the combination

  • We propose the conceptual framework of the data driving-based DTs collaboration with the help of blockchain technology

Read more

Summary

Introduction

Industry 4.0 revolution is considered to be a new paradigm of digital, autonomous, and decentralized control with the Industrial Internet of Things (IIoT), Machine Learning (ML), big data, and edge computing [1,2]. For smart manufacturing, distributed manufacturing is a form of decentralized manufacturing practiced by enterprises using digitalization [3,4] It uses an effective collaboration form in terms of information sharing, analytics, and collaborative decision-making in real-time. Multiple DTs are used to represent a distributed production system in hierarchical levels [6]: (i) DTs in a flat network represent individual things at the machine level. They exchange information with each other on things and learn about their operation and behavior to build a common understanding of the machine condition, (ii) DTs for things in a tree or a chain represent the sub-system level and the system level where each DT is passing on information to the level

Objectives
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call