As industrial digitization accelerates, digital twins have become widespread across manufacturing. But modern production systems are highly dynamic and often reconfigured, which makes manual model development and updates increasingly difficult. The new work addresses this bottleneck by proposing a data-driven method for resource aggregation.
The approach focuses on generating digital twin and simulation models from aggregated data resources, rather than building them by hand. This is intended to improve scalability and reduce the effort needed to keep models in sync with rapidly changing physical systems. The abstract suggests that automating model generation through data-driven aggregation could help manufacturers respond more quickly to reconfigurations.
It is worth noting that the abstract is truncated, so specific technical details about the aggregation method, evaluation results, or implementation are not yet available from this source. The core idea, however, is clear: use data to automate and scale the modeling process for digital twins in dynamic industrial settings.