Artificial intelligence-based decision-making algorithms, Internet of Things sensing networks, and sustainable cyber-physical management systems in big data-driven cognitive manufacturing

• Published in: Oeconomia Copernicana Vol. 13; no. 4; pp. 1047 - 1080
• Main Authors: Lăzăroiu, George, Androniceanu, Armenia, GRECU, Iulia, Grecu, Gheorghe, Neguriță, Octav
• Format: Journal Article
• Language: English
• Published: Torun Institute of Economic Research 01.12.2022; Instytut Badań Gospodarczych; Nicolaus Copernicus University Press
• Subjects: Algorithms; Artificial intelligence; Automation; Bibliometrics; Big Data; Data analysis; Decision making; Digitization; Internet of Things; Manufacturing; Process planning; Supranational / Global Economy; Value creation; Artificial Intelligence of Things; cyberphysical system; realtime scheduling algorithm; smart device; sustainable product lifecycle managment; cognitive manufacturing; big datadriven deep learning
• ISSN: 2083-1277; 2353-1827; 2353-1827
• DOI: 10.24136/oc.2022.030

Research background: With increasing evidence of cognitive technologies progressively inte-grating themselves at all levels of the manufacturing enterprises, there is an instrumental need for comprehending how cognitive manufacturing systems can provide increased value and precision in complex operational processes. Purpose of the article: In this research, prior findings were cumulated proving that cognitive manufacturing integrates artificial intelligence-based decision-making algorithms, real-time big data analytics, sustainable industrial value creation, and digitized mass production. Methods: Throughout April and June 2022, by employing Preferred Reporting Items for System-atic Reviews and Meta-analysis (PRISMA) guidelines, a quantitative literature review of ProQuest, Scopus, and the Web of Science databases was performed, with search terms including “cognitive Industrial Internet of Things”, “cognitive automation”, “cognitive manufacturing systems”, “cognitively-enhanced machine”, “cognitive technology-driven automation”, “cognitive computing technologies,” and “cognitive technologies.” The Systematic Review Data Repository (SRDR) was leveraged, a software program for the collecting, processing, and analysis of data for our research. The quality of the selected scholarly sources was evaluated by harnessing the Mixed Method Appraisal Tool (MMAT). AMSTAR (Assessing the Methodological Quality of Systemat-ic Reviews) deployed artificial intelligence and intelligent workflows, and Dedoose was used for mixed methods research. VOSviewer layout algorithms and Dimensions bibliometric mapping served as data visualization tools. Findings value added: Cognitive manufacturing systems is developed on sustainable product lifecycle management, Internet of Things-based real-time production logistics, and deep learning-assisted smart process planning, optimizing value creation capabilities and artificial intelligence-based decision-making algorithms. Subsequent interest should be oriented to how predictive maintenance can assist in cognitive manufacturing by use of artificial intelligence-based decision-making algorithms, real-time big data analytics, sustainable industrial value creation, and digit-ized mass production.