Industrial IoT and Digital Twins for a Smart Factory : An open source toolkit for application design and benchmarking

TLDR

The rapid evolution of digital technology, including IoT, big data, AI, and CPS, has driven the 4th industrial revolution, with Industrial IoT and digital twins as key concepts enabling real‑time data acquisition, virtual representation, analytics, and visualization in smart factories. The study aims to close the gap between research and implementation by evaluating open‑source platforms for integrated IoT and digital‑twin capabilities. The authors assess the capability of existing open‑source platforms to provide real‑time IIoT data acquisition, virtual representation, analytics, and visualization, and benchmark them using industry open data and universal testing tools. The architecture’s performance is demonstrated in a use‑case with industry open data and benchmarked with universal testing tools.

Abstract

The rapid evolution of digital technology and designed intelligence, such as the Internet of Things (IoT), Big data analytics, Artificial Intelligence (AI), Cyber Physical Systems (CPS), has been a catalyst for the 4th industrial revolution (known as industry 4.0). Among other, the two key state-of-the-art concepts in Industry 4.0, are Industrial IoT (IIoT) and digital twins. IIoT facilitates real-time data acquisition, processing and analytics over large amount of sensor data streams produced by sensors installed within a smart factory, while the ‘digital twin’ concept aims to enable smart factories via the digital replication or representation of physical machines, processes, people in cyber-space. This paper explores the capability of present-state open-source platforms to collectively achieve digital twin capabilities, including IoT real-time data acquisition, virtual representation, analytics, and visualisation. The aim of this work is to ‘close the gap’ between research and implementation, through a collective open source IoT and Digital Twin architecture. The performance of the open-source architecture in this work, is demonstrated in a use-case utilising industry ‘open data’, and is bench-marked with universal testing tools.