Abstract
Research background: The aim of this paper is to synthesize and analyze existing evidence on artificial intelligence-based decision-making algorithms, industrial big data, and Internet of Things sensing networks in digital twin-driven smart manufacturing. Purpose of the article: Using and replicating data from Altair, Catapult, Deloitte, DHL, GAVS, PwC, and ZDNet we performed analyses and made estimates regarding cyber-physical system-based real-time monitoring, product decision-making information systems, and artificial intelligence data-driven Internet of Things systems in digital twin-based cyber-physical production systems. Methods: From the completed surveys, we calculated descriptive statistics of compiled data when appropriate. The data was weighted in a multistep process that accounts for multiple stages of sampling and nonresponse that occur at different points in the survey process. The precision of the online polls was measured using a Bayesian credibility interval. To ensure high-quality data, data quality checks were performed to identify any respondents showing clear patterns of satisficing. Test data was populated and analyzed in SPSS to ensure the logic and randomizations were working as intended before launching the survey. An Internet-based survey software program was utilized for the delivery and collection of responses. The sample weighting was accomplished using an iterative proportional fitting process that simultaneously balanced the distributions of all variables. The interviews were conducted online and data were weighted by five variables (age, race/ethnicity, gender, education, and geographic region) using the Census Bureau’s American Community Survey to reflect reliably and accurately the demographic composition of the United States. Confirmatory factor analysis was employed to test for the reliability and validity of measurement instruments. Findings & Value added: The way Internet of Things-based decision support systems, artificial intelligence-driven big data analytics, and robotic wireless sensor networks configure digital twin-driven smart manufacturing and cyber-physical production systems in sustainable Industry 4.0.
Highlights
Digital twin and data-driven manufacturing processes can enable the development of an autonomous factory setting (Scott et al, 2020) with full-scale operational concreteness and adjustability
Networking distributed digital twins between shop floors enables companies to articulate virtually connected manufacturing systems. (Lu et al, 2020) The swift advancement of cutting-edge generation of big data technologies enables the rise of cyberphysical production systems that are pivotal in identifying smart manufacturing solutions. (Liu et al, 2020a) Digital twins provide technical performance at the kind and instance phases of a production unit. (Park et al, 2020) Among various degrees of smartness and networking of cyber-physical production systems (Poliak et al, 2020), digital twins, constituting a digital duplicate of a physical asset or system, mirroring its features and connections to the factory setting, shape smart manufacturing. (Zheng and Sivabalan, 2020)
A manufacturing asset can be networked and detached by the data network by use of its digital twin. (Lu et al, 2020) A digital twin is an elaborate digital object necessitating massive volumes of data, with visualizing and rendering performance, computational capacity, and intelligence. (Zheng and Sivabalan, 2020) Assimilating a smart agent across the industrial platforms increases the harnessing of the system-level digital twin: groundbreaking supervision algorithms are regulated and tested upfront before being put into service to the physical realm for implementation. (Xia et al, 2020) A production unit-level digital twin facilitates process and systematic productivity improvement for sustainable and smart manufacturing. (Park et al, 2020)
Summary
Digital twin and data-driven manufacturing processes can enable the development of an autonomous factory setting (Scott et al, 2020) with full-scale operational concreteness and adjustability. (Park et al, 2020) Among various degrees of smartness and networking of cyber-physical production systems (Poliak et al, 2020), digital twins, constituting a digital duplicate of a physical asset or system, mirroring its features and connections to the factory setting, shape smart manufacturing. (Zheng and Sivabalan, 2020) An essential component of cyber-physical systems, digital twins can supply decision support to improve engineering product lifecycle administration systems by use of remote monitoring and supervision, highfidelity replication, and solution generation performances. Connectivity and data tracking in every part of the integrated manufacturing operations facilitate factory processes to be converted into data-driven evidence-based routines (Lăzăroiu et al, 2020), while tracing product fault sources, inspecting production coherent bottlenecks, and estimating subsequent resource demands. (Lu et al, 2020) A digital twin represents the technical mainstay for setting up cyber-physical production systems (Nica et al, 2021) in relation to Industry 4.0. (Liu et al, 2020a) A digital twin perpetually coexists with its physical system, configuring instantaneous high-fidelity replications of, and providing pervasive control over, it. (Zheng and Sivabalan, 2020) An essential component of cyber-physical systems, digital twins can supply decision support to improve engineering product lifecycle administration systems by use of remote monitoring and supervision, highfidelity replication, and solution generation performances. (Lim et al, 2020)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
