This study explores the integration of monitored data from Tunnel Boring Machine (TBM) operations into a digital twin framework to generate real-time status information for mechanized tunnelling. The study investigates the potential benefits that can be derived in terms of lean operations and reduced waste of rework.
Using a design science research approach within a case study of a tunnelling project, the researchers developed, tested and refined the Digital Twin Construction (DTC) system and observed use cases of its application. The empirical data collected was analyzed to draw conclusions concerning the feasibility of the integration of TBM excavation data into a digital twin and the impacts of its use in improving flow and avoiding rework by reducing uncertainty.
The study identifies key technical challenges, such as imperfect data interoperability across different systems involved in tunnelling operations and the need for standardized approaches to modelling. It also highlights the value of the digital twin in supporting lean design and construction workflows by providing the project team with information drawn from a dynamic representation of the tunnel’s physical state in short cycle times.
This study presents an innovative computational design algorithm that automates data integration, enabling digital twin generation as a functional product. Furthermore, it includes use cases illustrating how the resulting digital twin supports the improvement of specific operations, such as bracketry design and construction. By addressing both technical and operational dimensions, this case study serves as a valuable resource for researchers and industry practitioners aiming to advance digital twin technology and lean construction in tunnelling and broader construction applications.
