An effective architecture of digital twin system to support human decision making and AI‐driven autonomy. (27th November 2020)

• Record Type: Journal Article
• Authors: Mostafa, Fahed; Tao, Longquan; Yu, Wenjin
• Other Names: Ogiela Marek R. guestEditor.; Rahayu Wenny guestEditor.; Palmieri Francesco guestEditor.; Kalyanam Rajesh guestEditor.; Stankovski Vlado guestEditor.
• Is Part Of: Concurrency and computation. Volume 33:Number 19(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-11-27
• Subjects: computational intelligence -- decision making support -- digital twin -- hybrid system -- IoT; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.6111
• Languages: English
• ISSNs: 1532-0626

Abstract

Abstract: With the development of IoT technologies, digital twin has become an increasingly popular concept that is considered the next generation of digitalization for decision making support (human‐oriented) and even fully autonomous. However, although there are a few research projects that have proposed available digital twin architectures, they are either missing critical components or difficult to be converted into a practical application. In this article, everything we proposed had been implemented in our production environment and is facilitating our manufacturing and mining processes. It is initiated by a data analytic maturity model which formulates the evaluation route of data analytics. Then, a novel six‐layer digital twin model is established that aims to set the standards. In this model, we defined that all the automated calculation jobs should be driven by digital twin metadata such as the hyperparameters of machine learning. The metadata will be updated by metadata updating feedback flow which most current digital twin projects are missing.