Industrial Artificial Intelligence, Internet of Things Smart Devices, and Big Data-driven Decision-Making in Digital-Twin-based Cyber-Physical Production Systems.

AuthorBreillat, Richard
  1. Introduction

    Manufacturing is going through a significant shift brought about by the advancements in process and data technology (Durkin, 2019; Kovacova and Kliestik, 2017; Nica, 2017; Trettin et al., 2019), in addition to information science, and thus machine learning algorithms will catalyze predictive patterns throughout the companies in consonance with the digital twin notion. (Kusiak, 2020) Data represents the regulator of the performance of production digital twin systems, reinforcing its top-level applications. (Kong et al., 2020)

  2. Conceptual Framework and Literature Review

    Digital twin shapes the configuration of smart manufacturing, incessantly harmonizing with its physical system, furnishing instantaneous first-rate replications of the system, and providing widespread supervision over it. (Zheng and Sivabalan, 2020) The cutting-edge digital twin tools enable the handling of geometrical heterogeneities via a range of phases thoroughly networked with big data technologies (Abakumova and Primierova, 2018; Dusmanescu et al., 2016; Lazaroiu, 2018; Popescu et al., 2017; Valaskova et al., 2018) that organize an uninterrupted and well-defined stream of information among the various procedures of the digital operations along the entire product development (Atwell et al., 2019; Eysenck et al., 2019; Lazaroiu et al., 2017; Popescu et al., 2019), derived from input coming from production, assembly, and analysis. (Polini and Corrado, 2020) Digital twins, mirroring perpetually the operations of physical objects, are instrumental in making smart decisions (Cimini et al., 2020), being effective tools to bolster product advancement, but necessitating that the product be fashioned to use all of its capabilities. (Pereira Pessoa and Jauregui Becker, 2020)

  3. Methodology and Empirical Analysis

    The data used for this study was obtained and replicated from previous research conducted by Deloitte, Gartner, Job Wizards/Konica Minolta, and PTC. I performed analyses and made estimates regarding benefits of digital twins in companies, digital twin business values, practical actions to advance digital twin strategies, and different digital twins that enterprises can use. Data collected from 4,300 respondents are tested against the research model by using structural equation modeling.

  4. Results and Discussion

    A virtual and reliable image of physical output resource, by comprising diverse patterns and manufacturing big data of resource, digital twin is instrumental in designing the cyber-physical production systems. (Zhang et al., 2020) Digital twin technology offers a viable manner for instantaneous supervision of the online inspection system. (Zheng et al., 2020) To maximize the traceability and the lifecycle management, and to supply an individual point of source of element-specific information, the digital twin technology connects various data sets customized to the demands of distinct types of end users. The input exchange among devices in the production network is determined by machine-readable, adjustable, and self-identifying data formats. (Schmetz et al., 2020) (Tables 1-6)

  5. Conclusions and Implications

    Digital twin represents the technical cornerstone for setting up cyber-physical production systems in Industry 4.0. (Liu et al., 2020)...

To continue reading

Request your trial

VLEX uses login cookies to provide you with a better browsing experience. If you click on 'Accept' or continue browsing this site we consider that you accept our cookie policy. ACCEPT