Towards a connected Digital Twin Learning Ecosystem in manufacturing: Enablers and challenges. (September 2022)

• Record Type: Journal Article
• Authors: García, Álvaro; Bregon, Anibal; Martínez-Prieto, Miguel A.
• Is Part Of: Computers & industrial engineering. Volume 171(2022)
• Publication Date: 2022-09
• Subjects: Digital twin -- Learning ecosystem -- Manufacturing -- Human–machine collaboration -- Learning factory -- Cyber–physical system; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2022.108463
• Languages: English
• ISSNs: 0360-8352

Abstract

Abstract: The evolution of digital twin, leveraged by the progressive physical–digital convergence, has provided smart manufacturing systems with knowledge-generation ecosystems based on new models of collaboration between the workforce and industrial processes. Digital twin is expected to be a decision-making solution underpinned by real-time communication and data-driven enablers, entailing close cooperation between workers, systems and processes. But industry will need to face the challenges of building and supporting new technical and digital infrastructures, while workers' skills development eventually manages to include the increased complexity of industrial processes. This paper is intended to reach a better understanding of learning opportunities offered by emerging Industry 4.0 digital twin ecosystems in manufacturing. Diverse learning approaches focused on the potential application of the digital twin concept in theoretical and real manufacturing ecosystems are reviewed. In addition, we propose an original definition of Digital Twin Learning Ecosystem and the conceptual layered architecture. Existing key enablers of the digital twin physical–digital convergence, such as collaborative frameworks, data-driven approaches and augmented interfaces, are also described. The role of the Learning Factory concept is highlighted, providing a common understanding between academia and industry. Academic applications and complex demonstration scenarios are combined in line with the enablement of connected adaptive systems and the empowerment of workforce skills and competences. The adoption of digital twin in production is still at an initial stage in the manufacturing industry, where specific human and technological challenges must be addressed. The research priorities presented in this work are considered as a recognised basis in industry, which should help digital twin with the objective of its progressive integration as a future learning ecosystem. Graphical abstract: Highlights: Industry 4.0 digital twin ecosystem fosters learning opportunities in manufacturing. Effective physical–digital learning ecosystems require a connected infrastructure. Digital twin offers a complete immersion between systems, workers and processes. Digital twin connects academic applications and complex demonstration scenarios. Digital twin helps improving human–machine interaction and decision-making process.