Towards an Adaptable Architecture for Digital Twin (AADT)

Abstract

A Digital twin (DT) is a virtual replica of a physical object, which has the capability of integrating with a virtual object, such that they exchange data and use the data exchanged to improve each other. It is a confluence of Industry 4.0 technological innovations, such as big data, artificial intelligence, modelling and simulation, Internet of things, optimisation techniques, cyber-physical systems, amongst others; the blend of these technologies fused together for the development of a DT is driven by its use case. A DT has enormous potential, and there is a consensus among the industry, academia and governments that it is one of the most pivotal technologies in Industry 4.0 era that will play a major role in shaping the society. This widely acknowledged notion about DT has not translated into a joint effort to standardise it. As a result, there exists neither a generally accepted definition nor architecture for digital twin. The lack of standard definition, framework or architecture for DT may have a negative impact on the wider adoption and development of DT. The state-of-the-art in DT architecture, for instance, reveals that most of the architectures are designed for specific domains and/or technologies and have components that are named in such a manner that it is difficult to identify commonality in purpose and functionalities. To contribute to the taxonomy of DT architectural components, this study proposes an adaptable architecture for DT (AADT), which is developed based on design science research (DSR) principles. AADT directly addresses the architectural chaos inherited from the growth era of the digital architectural development by establishing standard components traceable to digital twin definitions, requirements, and mandatory functionalities. Rather than proposing yet another domain-specific architecture, AADT provides a systematic process for deriving architectures from requirements, enabling consistent yet flexible implementations. To support the implementation of digital twins, this research develops an implementation framework for digital twin (IFDT) that is a confluence of software development lifecycle and principles of project controls. IFDT consists of a stage gate within every lifecycle phase, which ensures that a digital twin development project is subject to business case viability test and stakeholders’ approval as it progresses from one lifecycle phase to another. AADT is evaluated with the guidance of framework for evaluating design science (FEDS) and ISO Standard 9126. The evaluation of AADT results in the development of a taxonomy of architectural adaptiveness for digital twin systems. The taxonomy organises structural, behavioural, functional and quality adaptiveness into a coherent analytical framework; and therefore, serves as both a conceptual contribution and a practical guide for evaluating future digital twin architectures. In summary, this research, contributes to the taxonomy of digital twin architectural components; develops a technology-agnostic digital twin architecture that can adapt to the requirements of disparate use cases from a wide range of domains; proposes an implementation framework for digital twin; and develops a taxonomy of architectural adaptiveness of digital twin systems.